Machine Learning and Synthetic Minority Oversampling Techniques for Imbalanced Data: Improving Machine Failure Prediction

Prediction of machine failure is challenging as the dataset is often imbalanced with a low failure rate.The common approach to han-dle classification involving imbalanced data is to balance the data using a sampling approach such as random undersampling,random oversampling,or Synthetic Minority Oversampling Technique(SMOTE)algorithms.This paper compared the classification performance of three popular classifiers(Logistic Regression,Gaussian Naïve Bayes,and Support Vector Machine)in predicting machine failure in the Oil and Gas industry.The original machine failure dataset consists of 20,473 hourly data and is imbalanced with 19945(97%)‘non-failure’and 528(3%)‘failure data’.The three independent variables to predict machine failure were pressure indicator,flow indicator,and level indicator.The accuracy of the classifiers is very high and close to 100%,but the sensitivity of all classifiers using the original dataset was close to zero.The performance of the three classifiers was then evaluated for data with different imbalance rates(10%to 50%)generated from the original data using SMOTE,SMOTE-Support Vector Machine(SMOTE-SVM)and SMOTE-Edited Nearest Neighbour(SMOTE-ENN).The classifiers were evaluated based on improvement in sensitivity and F-measure.Results showed that the sensitivity of all classifiers increases as the imbalance rate increases.SVM with radial basis function(RBF)kernel has the highest sensitivity when data is balanced(50:50)using SMOTE(Sensitivitytest=0.5686,Ftest=0.6927)compared to Naïve Bayes(Sensitivitytest=0.4033,Ftest=0.6218)and Logistic Regression(Sensitivitytest=0.4194,Ftest=0.621).Overall,the Gaussian Naïve Bayes model consistently improves sensitivity and F-measure as the imbalance ratio increases,but the sensitivity is below 50%.The classifiers performed better when data was balanced using SMOTE-SVM compared to SMOTE and SMOTE-ENN.

Blockchain-Enabled Cybersecurity Provision for Scalable Heterogeneous Network:A Comprehensive Survey

Blockchain-enabled cybersecurity system to ensure and strengthen decentralized digital transaction is gradually gaining popularity in the digital era for various areas like finance,transportation,healthcare,education,and supply chain management.Blockchain interactions in the heterogeneous network have fascinated more attention due to the authentication of their digital application exchanges.However,the exponential development of storage space capabilities across the blockchain-based heterogeneous network has become an important issue in preventing blockchain distribution and the extension of blockchain nodes.There is the biggest challenge of data integrity and scalability,including significant computing complexity and inapplicable latency on regional network diversity,operating system diversity,bandwidth diversity,node diversity,etc.,for decision-making of data transactions across blockchain-based heterogeneous networks.Data security and privacy have also become the main concerns across the heterogeneous network to build smart IoT ecosystems.To address these issues,today’s researchers have explored the potential solutions of the capability of heterogeneous network devices to perform data transactions where the system stimulates their integration reliably and securely with blockchain.The key goal of this paper is to conduct a state-of-the-art and comprehensive survey on cybersecurity enhancement using blockchain in the heterogeneous network.This paper proposes a full-fledged taxonomy to identify the main obstacles,research gaps,future research directions,effective solutions,andmost relevant blockchain-enabled cybersecurity systems.In addition,Blockchain based heterogeneous network framework with cybersecurity is proposed in this paper tomeet the goal of maintaining optimal performance data transactions among organizations.Overall,this paper provides an in-depth description based on the critical analysis to overcome the existing work gaps for future research where it presents a potential cybersecurity design with key requirements of blockchain across a heterogeneous network.

Neural Machine Translation Models with Attention-Based Dropout Layer

In bilingual translation,attention-based Neural Machine Translation(NMT)models are used to achieve synchrony between input and output sequences and the notion of alignment.NMT model has obtained state-of-the-art performance for several language pairs.However,there has been little work exploring useful architectures for Urdu-to-English machine translation.We conducted extensive Urdu-to-English translation experiments using Long short-term memory(LSTM)/Bidirectional recurrent neural networks(Bi-RNN)/Statistical recurrent unit(SRU)/Gated recurrent unit(GRU)/Convolutional neural network(CNN)and Transformer.Experimental results show that Bi-RNN and LSTM with attention mechanism trained iteratively,with a scalable data set,make precise predictions on unseen data.The trained models yielded competitive results by achieving 62.6%and 61%accuracy and 49.67 and 47.14 BLEU scores,respectively.From a qualitative perspective,the translation of the test sets was examined manually,and it was observed that trained models tend to produce repetitive output more frequently.The attention score produced by Bi-RNN and LSTM produced clear alignment,while GRU showed incorrect translation for words,poor alignment and lack of a clear structure.Therefore,we considered refining the attention-based models by defining an additional attention-based dropout layer.Attention dropout fixes alignment errors and minimizes translation errors at the word level.After empirical demonstration and comparison with their counterparts,we found improvement in the quality of the resulting translation system and a decrease in the perplexity and over-translation score.The ability of the proposed model was evaluated using Arabic-English and Persian-English datasets as well.We empirically concluded that adding an attention-based dropout layer helps improve GRU,SRU,and Transformer translation and is considerably more efficient in translation quality and speed.

A Hybrid Marine Predator Algorithm for Thermal-aware Routing Scheme in Wireless Body Area Networks

Thermal-aware routing protocols in WBANs consider temperature factors in the routing process for preventing overheating of the tissues surrounding the sensor nodes.However,providing an energy-efficient and thermal-aware routing in WBANs is a challenging issue.To deal with this problem,this article presents a novel temperature-aware routing protocol that applies Mamdani-based Fuzzy Logic Controllers(FLCs)for selecting the next forwarding node in routing data packets.These FLCs apply five important input factors such as the priority of the packet,and sensor node's remaining energy,temperature,distance,and link path loss.Also,a new hybrid version of the Marine Predator Algorithm(MPA),named MPAOA is presented by combining the exploration and exploitation phases of the MPA and Arithmetic Optimization Algorithm(AOA).This algorithm is effectively applied for selecting the best possible set of fuzzy rules for FLCs and tuning their fuzzy sets.Extensive experiments conducted in the Castalia simulator exhibit that the proposed temperature and priority-aware routing scheme can outperform other well-known routing schemes such as LATOR,TTRP,TAEO,ATAR,and EOCC-TARA in terms of metrics such as sensor nodes lifetime,the average temperature of the sensor nodes,and the percentage of the packets routed through non-overheated paths.Besides,it is shown that the MPAOA outperforms other algorithms such as Bat Algorithm(BA),Genetic Algorithm(GA),AOA,and MPA regarding the specified metrics.