Seismic risk assessment and hotspots prioritization: a developing country perspective.

Natural disasters pose a negative impact not only on human lives but also on infrastructures such as healthcare systems, supply chains, logistics, manufacturing, and service industries. The frequency of such calamities has grown over time, which not only poses a threat to human survival and the living environment but is also detrimental to the economic growth and sustainable development of society. Earthquakes cause the most destruction compared to other natural disasters, especially in developing countries where the conventional reactive approach to dealing with disasters gives less chance for the appropriate utilization of already limited resources. Additionally, mismanagement of the resources and the lack of a unified action plan hinder the purpose of helping the grieving population. Considering the foregoing, this study presents a methodology for identifying hotspots and helping prioritize pre- and post-disaster management action by conducting a thorough seismic risk assessment while taking into consideration the case of a developing country as its focus. This methodology allows for rapid risk assessment against any given scenario by providing quantitative estimates of the repercussions such as physical damage to the buildings, casualties including injuries, economic losses, displaced households, debris, shelter requirements, and hospital functionality. In short, it could help prioritize actions with greater impacts and serve as a foundation for the formulation of policies and plans intended to increase the resilience of a resource-constrained community. Thus, the findings can be utilized by government agencies, emergency management organizations, non-government organizations, and aiding countries as a decision support tool.

Machining of Triangular Holes in D2 Steel by the Use of Non-Conventional Electrodes in Die-Sinking Electric Discharge Machining.

Electric discharge machining is relatively a slow process in terms of machining time and material removal rate. The presence of overcut and the hole taper angle caused by the excessive tool wear are other challenges in the electric discharge machining die-sinking process. The areas of focus to solve these challenges in the performance of electric discharge machines include increasing the rate of material removal, decreasing the rate of tool wear, and reducing the rate of hole taper angle and overcut. Triangular cross-sectional through-holes have been produced in D2 steel through die-sinking electric discharge machining (EDM). Conventionally, the electrode with uniform triangular cross-section throughout the electrode length is used to machine triangular holes. In this study, new designs of electrodes (non-conventional designs) are employed by introducing circular relief angles. For material removal rate (MRR), tool wear rate (TWR), overcut, taper angle, and surface roughness of the machined holes, the machining performance of conventional and unconventional electrode designs is compared. A significant improvement in MRR (32.6% increase) has been achieved by using non-conventional electrode designs. Similarly, the hole quality resulted by non-conventional electrodes is way better than hole quality corresponding to conventional electrode designs, especially in terms of overcut and hole taper angle. A reduction of 20.6% in overcut and a reduction of 72.5% in taper angle can be achieved through newly designed electrodes. Finally, one electrode design has been selected (electrode with 20 degree relief angle) as the most appropriate electrode resulting in better EDM performance in terms of MRR, TWR, overcut, taper angle, and surface roughness of triangular holes.

Correction: RCER: Reliable Cluster-based Energy-aware Routing protocol for heterogeneous Wireless Sensor Networks.

[This corrects the article DOI: 10.1371/journal.pone.0222009.].

Fault Detection in Wireless Sensor Networks through the Random Forest Classifier.

Wireless Sensor Networks (WSNs) are vulnerable to faults because of their deployment in unpredictable and hazardous environments. This makes WSN prone to failures such as software, hardware, and communication failures. Due to the sensor's limited resources and diverse deployment fields, fault detection in WSNs has become a daunting task. To solve this problem, Support Vector Machine (SVM), Convolutional Neural Network (CNN), Stochastic Gradient Descent (SGD), Multilayer Perceptron (MLP), Random Forest (RF), and Probabilistic Neural Network (PNN) classifiers are used for classification of gain, offset, spike, data loss, out of bounds, and stuck-at faults at the sensor level. Out of six faults, two of them are induced in the datasets, i.e., spike and data loss faults. The results are compared on the basis of their Detection Accuracy (DA), True Positive Rate (TPR), Matthews Correlation Coefficients (MCC), and F1-score. In this paper, a comparative analysis is performed among the classifiers mentioned previously on real-world datasets. Simulations show that the RF algorithm secures a better fault detection rate than the rest of the classifiers.

Machine Learning Algorithms and Fault Detection for Improved Belief Function Based Decision Fusion in Wireless Sensor Networks.

Decision fusion is used to fuse classification results and improve the classification accuracy in order to reduce the consumption of energy and bandwidth demand for data transmission. The decentralized classification fusion problem was the reason to use the belief function-based decision fusion approach in Wireless Sensor Networks (WSNs). With the consideration of improving the belief function fusion approach, we have proposed four classification techniques, namely Enhanced K-Nearest Neighbor (EKNN), Enhanced Extreme Learning Machine (EELM), Enhanced Support Vector Machine (ESVM), and Enhanced Recurrent Extreme Learning Machine (ERELM). In addition, WSNs are prone to errors and faults because of their different software, hardware failures, and their deployment in diverse fields. Because of these challenges, efficient fault detection methods must be used to detect faults in a WSN in a timely manner. We have induced four types of faults: offset fault, gain fault, stuck-at fault, and out of bounds fault, and used enhanced classification methods to solve the sensor failure issues. Experimental results show that ERELM gave the first best result for the improvement of the belief function fusion approach. The other three proposed techniques ESVM, EELM, and EKNN provided the second, third, and fourth best results, respectively. The proposed enhanced classifiers are used for fault detection and are evaluated using three performance metrics, i.e., Detection Accuracy (DA), True Positive Rate (TPR), and Error Rate (ER). Simulations show that the proposed methods outperform the existing techniques and give better results for the belief function and fault detection in WSNs.