As a tremendous amount of service being streamed online to their users along with massive digital privacy information transmitted in recent years, the internet has become the backbone of most people's everyday workflow. The extending usage of the internet, however, also expands the attack surface for cyberattacks. If no effective protection mechanism is implemented, the internet will only be much vulnerable and this will raise the risk of data getting leaked or hacked. The focus of this paper is to propose an Intrusion Detection System (IDS) based on the Convolutional Neural Network (CNN) to reinforce the security of the internet. The proposed IDS model is aimed at detecting network intrusions by classifying all the packet traffic in the network as benign or malicious classes. The Canadian Institute for Cybersecurity Intrusion Detection System (CICIDS2017) dataset has been used to train and validate the proposed model. The model has been evaluated in terms of the overall accuracy, attack detection rate, false alarm rate, and training overhead. A comparative study of the proposed model's performance against nine other well-known classifiers has been presented.

This paper presents an investigation of the rapid variations in the temperature of metal melt pool for Additive Manufacturing (AM) processes. The melt pool is created by scanning a high-power laser beam across a metal powder bed. Rapid heating and cooling processes are involved in the layer-by-layer fabrication of the metal part. Recent advances in Machine Learning and Deep Learning algorithms provide efficient ways to analyze large sets of data in search of correlations that would otherwise be extremely time-consuming. The use of Machine Learning and Deep Learning algorithms to understand temperature variations in AM fabrication process will allow to predict the formation of porosity before it occurs. The objective of this research is to advance the AM technology using enhanced Deep Learning techniques to provide in-situ analysis of the melt pool temperature that can lead to a reliable manufacturing of Three-Dimensional (3D) metal parts/components. In specific, Deep Learning based porosity prediction for Additive Manufacturing (DLAM) methods have been proposed. In DLAMs, several state-of-the-art Deep Learning algorithms such as Convolutional Neural Networks (CNN) using transfer learning, and Residual-Recurrent Convolutional Neural Networks (Res-RCNN) are proposed for effectively performing the end-to-end porosity prediction in real-time using thermal images of melt pool. Experimental results, in this research, show that the Res-RCNN has an overall accuracy of 99.49% and inference time of $8.67ms$ , and the Res-RCNN outperforms other baseline models. The Res-RCNN’s recursive architecture allows the network to view each input image multiples times and at varying feature levels, which enables a slight boost in porosity prediction accuracy over the commonly used transfer learning CNN models.

Energy harvesting is crucial for battery-powered smart sensing systems to remain functional for a longer period of time without any intervention. Utilizing road vibrations, as the source to harvest energy, for smart road sensing systems is of a significant interest. Many studies on implementing distinctive designs for vibration-sourced harvesters are currently in progress. In this paper, a vibration-sourced piezoelectric energy harvester, which has been validated by the simulation results from COMSOL Multiphysics, is proposed. The design comprises two Lead Zirconate Titanate (piezoelectric ceramic material) PZT-5J mass-spring oriented cantilever bimorphs to capture the vibrations and three silicone rubbers to increase the stress applied on the bimorphs. This productive piezoelectric energy harvester has been designed to be used in low- and high-vibration conditions. A maximum power output of 57 mW has been obtained by the designed energy harvester. The simulation results prove that the proposed piezoelectric energy harvester design is efficient to supply power to sensors and wireless systems used in smart road applications. Based on the obtained simulation results, a prototype has been developed. Considering the real environmental aspects, the prototype has been modified to accommodate the requirement of sustaining and long-lasting design.

Research collaboration among interdisciplinary teams has become a common trend in recent days. However, there is a lack of evidence in literature regarding which disciplines play dominant roles in interdisciplinary research settings. It is also unclear whether the dominant role of disciplines vary between STEM (Science, Technology, Engineering, and Mathematics) and non-STEM focused research. This study considers metadata of the research projects funded by the Australian Research Council Discovery Grant Project scheme. Applying network analytics, this study investigates the contribution of individual disciplines in the successfully funded projects. It is noted that the disciplines Engineering, Biological Sciences and Technology appear as the principal disciplines in interdisciplinary research having a STEM focus. By contrast, non-STEM interdisciplinary research is led by three disciplines—Studies in Human Societies, Language, Communication and Culture, and History and Archaeology. For projects entailing interdisciplinarity between STEM and non-STEM disciplines, the STEM discipline of Medical and Health Sciences and the non-STEM disciplines of Psychology and Cognitive Science and Studies in Human Societies appear as the leading contributors. Overall, the network-based visualisation reveals that research interdisciplinarity is implemented in a heterogeneous way across STEM and non-STEM disciplines, and there are gaps in inter-disciplinary collaborations among some disciplines.

Wireless sensor networks are characterized by very tight code size and power constraints and by a lack of well-established standard software development platforms such as Posix. In this article, we present a comparative study between a few fairly different such platforms, namely MANTIS, TinyOS, and ZigBee, when considering them from the application developer's perspective, that is, by focusing mostly on functional aspects, rather than on performance or code size. In other words, we compare both the tasking model used by these platforms and the API libraries they offer. Sensor network applications are basically event based, so most of the software platforms are also built on considering event handling mechanism, however some use a more traditional thread based model. In this article, we consider implementations of a simple generic application in MANTIS, TinyOS, and the Ember ZigBee development framework, with the goal of depicting major differences between these platforms, and suggesting a programming style aimed at maximizing portability between them.

In this paper, an Intrusion Detection System (IDS) in the Controller Area Network (CAN) bus of modern vehicles has been proposed. NESLIDS is an anomaly detection algorithm based on the supervised Deep Neural Network (DNN) architecture that is designed to counter three critical attack categories: Denial-of-service (DoS), fuzzy, and impersonation attacks. Our research scope included modifying DNN parameters, e.g. number of hidden layer neurons, batch size, and activation functions according to how well it maximized detection accuracy and minimized the false positive rate (FPR) for these attacks. Our methodology consisted of collecting CAN Bus data from online and in real-time, injecting attack data after data collection, preprocessing in Python, training the DNN, and testing the model with different datasets. Results show that the proposed IDS effectively detects all attack types for both types of datasets. NESLIDS outperforms existing approaches in terms of accuracy, scalability, and low false alarm rates.