In the era of industry 4.0, safety, efficiency and reliability of industrial machinery is an elementary concern in trade sectors. The accurate remaining useful life (RUL) prediction of an equipment in due time allows us to effectively plan the maintenance operation and mitigate the downtime to raise the revenue of business. In the past decade, data driven based RUL prognostic methods had gained a lot of interest among the researchers. There exist various deep learning-based techniques which have been used for accurate RUL estimation. One of the widely used technique in this regard is the long short-term memory (LSTM) networks. To further improve the prediction accuracy of LSTM networks, this paper proposes a model in which effective pre-processing steps are combined with LSTM network. C-MAPSS turbofan engine degradation dataset released by NASA is used to validate the performance of the proposed model. One important factor in RUL predictions is to determine the starting point of the engine degradation. This work proposes an improved piecewise linear degradation model to determine the starting point of deterioration and assign the RUL target labels. The sensors data is pre-processed using the correlation analysis to choose only those sensors measurement which have a monotonous behavior with RUL, which is then filtered through a moving median filter. The updated RUL labels from the degradation model together with the pre-processed data are used to train a deep LSTM network. The deep neural network when combined with dimensionality reduction and piece-wise linear RUL function algorithms achieves improved performance on aircraft turbofan engine sensor dataset. We have tested our proposed model on all four sub-datasets in C-MAPSS and the results are then compared with the existing methods which utilizes the same dataset in their experimental work. It is concluded that our model yields improvement in RUL prediction and attains minimum root mean squared error and score function values.

The industry-based internet of things (IIoT) describes how IIoT devices enhance and extend their capabilities for production amenities, security, and efficacy. IIoT establishes an enterprise-to-enterprise setup that means industries have several factories and manufacturing units that are dependent on other sectors for their services and products. In this context, individual industries need to share their information with other external sectors in a shared environment which may not be secure. The capability to examine and inspect such large-scale information and perform analytical protection over the large volumes of personal and organizational information demands authentication and confidentiality so that the total data are not endangered after illegal access by hackers and other unauthorized persons. In parallel, these large volumes of confidential industrial data need to be processed within reasonable time for effective deliverables. Currently, there are many mathematical-based symmetric and asymmetric key cryptographic approaches and identity- and attribute-based public key cryptographic approaches that exist to address the abovementioned concerns and limitations such as computational overheads and taking more time for crucial generation as part of the encipherment and decipherment process for large-scale data privacy and security. In addition, the required key for the encipherment and decipherment process may be generated by a third party which may be compromised and lead to man-in-the-middle attacks, brute force attacks, etc. In parallel, there are some other quantum key distribution approaches available to produce keys for the encipherment and decipherment process without the need for a third party. However, there are still some attacks such as photon number splitting attacks and faked state attacks that may be possible with these existing QKD approaches. The primary motivation of our work is to address and avoid such abovementioned existing problems with better and optimal computational overhead for key generation, encipherment, and the decipherment process compared to the existing conventional models. To overcome the existing problems, we proposed a novel dynamic quantum key distribution (QKD) algorithm for critical public infrastructure, which will secure all cyber–physical systems as part of IIoT. In this paper, we used novel multi-state qubit representation to support enhanced dynamic, chaotic quantum key generation with high efficiency and low computational overhead. Our proposed QKD algorithm can create a chaotic set of qubits that act as a part of session-wise dynamic keys used to encipher the IIoT-based large scales of information for secure communication and distribution of sensitive information.

Disease outbreaks are nowadays a critical issue despite the development and rapid growth of technology. One of the major challenges facing healthcare professionals and healthcare industries is disease prevention and control by technology. Due to busy work schedules, maintaining a healthy lifestyle has become impossible, so the solution to these previous challenges is the intelligent health monitoring system. Over the past few years, a lot of research has been done on the use of Machine learning (ML) techniques in healthcare applications. With wearable devices, ML greatly helps in tracking human activities and vital signs as well as helping to monitor and diagnose patients’ health so it plays a huge role in elderly care. Research and development of more applications for wearable devices has been underway in the past five years, due to significant technological advances in medical sensors. Despite the widespread use of wearable devices, there is little research on machine learning applications of these devices. This paper presents a review of the different areas of recent ML research for healthcare wearable devices. It also discusses the different challenges facing ML applications on wearable devices.

In healthcare services, application development is considered the most complex and time-consuming phase. As it is difficult to plan and time-intense, it requires high maintenance. Healthcare applications need strict compliance and the scope of application is immense along with associates, classes in services, and classified system. Application designing in healthcare with the help of traditional approaches such as monolithic and service-oriented architecture (SOA) generate problems in different areas like service availability, remote access to services, service provisioning, scalability, healthcare systems integration with each other. That is why there is a need for less sophisticated and user-friendly healthcare systems, which are easy to plan and develop, inexpensive requirement maintenance, and agile testing. To overcome the aforesaid issues in the domain of healthcare application development, this paper develops a framework of micro services for the development of healthcare services using cloud computing infrastructure. Micro-service-based techniques provide lightly coupled and fine-grained methodology. With the use of micro services technique presented in this work, the efficiency, scalability, and performance are improved. In this research, an approach for development and deployment properly in the cloud for healthcare applications is developed. Thus, it contributes to the system design approach and system analysis. Quantitative and qualitative results are reported showing the advantages of micro services approach used.