The increasing number of studies that underline the relationship between industry 4.0 and sustainability shows that sustainability is one of the pillars of smart factories. Through a bibliometric performance and network analysis (BPNA), this research describes the existing relationship between industry 4.0 and sustainability, the strategic themes from 2010 to March 2019, as well as the research gaps for proposing future work. With this goal in mind, 894 documents and 5621 keywords were included for bibliometric analysis, which were treated with the support of Science Mapping Analysis Software Tool (SciMAT). The bibliometric performance analysis presented the number of publications over time and the most productive journals. The strategic diagram shown 12 main research clusters, which were measured according to bibliometric indicators. Moreover, the network structure of each cluster was depicted, and the patterns found were discussed based on the documents associated to the network. Our findings show the scientific efforts are focused to enhance economic and environmental aspects and highlights a lack of effort relating the social sphere. Finally, the paper concludes the challenges, perspectives, and suggestions for the potential future work in the field of study relating to industry 4.0 and sustainability.

Human motion detection is getting considerable attention in the field of Artificial Intelligence (AI) driven healthcare systems. Human motion can be used to provide remote healthcare solutions for vulnerable people by identifying particular movements such as falls, gait and breathing disorders. This can allow people to live more independent lifestyles and still have the safety of being monitored if more direct care is needed. At present wearable devices can provide real-time monitoring by deploying equipment on a person’s body. However, putting devices on a person’s body all the time makes it uncomfortable and the elderly tend to forget to wear them, in addition to the insecurity of being tracked all the time. This paper demonstrates how human motions can be detected in a quasi-real-time scenario using a non-invasive method. Patterns in the wireless signals present particular human body motions as each movement induces a unique change in the wireless medium. These changes can be used to identify particular body motions. This work produces a dataset that contains patterns of radio wave signals obtained using software-defined radios (SDRs) to establish if a subject is standing up or sitting down as a test case. The dataset was used to create a machine learning model, which was used in a developed application to provide a quasi-real-time classification of standing or sitting state. The machine-learning model was able to achieve 96.70% accuracy using the Random Forest algorithm using 10 fold cross-validation. A benchmark dataset of wearable devices was compared to the proposed dataset and results showed the proposed dataset to have similar accuracy of nearly 90%. The machine-learning models developed in this paper are tested for two activities but the developed system is designed and applicable for detecting and differentiating x number of activities.

Precision Agriculture (PA) and Agriculture 4.0 (A4.0) have been widely discussed as a medium to address the challenges related to agricultural production. In this research, we present a Systematic Literature Review (SLR) supported by a Bibliometric Performance and Network Analysis (BPNA) of the use of A4.0 technologies and PA techniques in the coffee sector. To perform the SLR, 87 documents published since 2011 were extracted from the Scopus and Web of Science databases and processed through the Preferred Reporting Items for Systematic reviews and Meta-Analyzes (PRISMA) protocol. The BPNA was carried out to identify the strategic themes in the field of study. The results present 23 clusters with different levels of development and maturity. We also discovered and presented the thematic network structure of the most used A4.0 technologies in the coffee sector. Our findings shows that Internet of Things, Machine Learning and geostatistics are the most used technologies in the coffee sector, we also present the main challenges and trends related to technological adoption in coffee systems. We believe that the demonstrated results have the potential to be considered by researchers in future works and decision making related to the field of study.

The Internet of Things (IoT) devices, networks, and applications have become an integral part of modern societies. Despite their social, economic, and industrial benefits, these devices and networks are frequently targeted by cybercriminals. Hence, IoT applications and networks demand lightweight, fast, and flexible security solutions to overcome these challenges. In this regard, artificial-intelligence-based solutions with Big Data analytics can produce promising results in the field of cybersecurity. This article proposes a lightweight dense random neural network (DnRaNN) for intrusion detection in the IoT. The proposed scheme is well suited for implementation in resource-constrained IoT networks due to its inherent improved generalization capabilities and distributed nature. The suggested model was evaluated by conducting extensive experiments on a new generation IoT security dataset ToN_IoT. All the experiments were conducted under different hyperparameters and the efficiency of the proposed DnRaNN was evaluated through multiple performance metrics. The findings of the proposed study provide recommendations and insights in binary class and multiclass scenarios. The proposed DnRaNN model attained attack detection accuracy of 99.14% and 99.05% for binary class and multiclass classifications, respectively.

In agriculture science, accurate information of moisture content (MC) in fruits and vegetables in an automated fashion can be vital for astute quality and grading evaluation. This demands for a viable, feasible and cost-effective technique for the defect recognition using timely detection of MC in fruits and vegetables to maintain a healthy sensory characteristic of fruits. Here we propose a non-invasive machine learning (ML) driven technique to monitor variations of MC in fruits using the terahertz (THz) waves with Swissto12 material characterization kit (MCK) in the frequency range of 0.75 THz to 1.1 THz. In this regard, multi-domain features are extracted from time-, frequency-, and time-frequency domains, and applied three ML algorithms such as support vector machine (SVM), k-nearest neighbour (KNN) and Decision Tree (D-Tree) for the precise assessment of MC in both apple and mango slices. The results illustrated that the performance of SVM exceeded other classifiers results using 10-fold validation and leave-one-observation-out-cross-validation techniques. Moreover, all three classifiers exhibited 100% accuracy for day 1 and 4 with 80% MC value (freshness) and 2% MC value (staleness) of both fruits' slices, respectively. Similarly, for day 2 and 3, an accuracy of 95% was achieved with intermediate MC values in both fruits' slices. This study will pave a new direction for the real-time quality evaluation of fruits in a non-invasive manner by incorporating ML with THz sensing at a cellular level. It also has a strong potential to optimize economic benefits by the timely detection of fruits quality in an automated fashion.

The atrial fibrillation (AF) is one of the most well-known cardiac arrhythmias in clinical practice, with a prevalence of 1–2% in the community, which can increase the risk of stroke and myocardial infarction. The detection of AF electrocardiogram (ECG) can improve the early detection of diagnosis. In this paper, we have further developed a framework for processing the ECG signal in order to determine the AF episodes. We have implemented machine learning and deep learning algorithms to detect AF. Moreover, the experimental results show that better performance can be achieved with long short-term memory (LSTM) as compared to other algorithms. The initial experimental results illustrate that the deep learning algorithms, such as LSTM and convolutional neural network (CNN), achieved better performance (10%) as compared to machine learning classifiers, such as support vectors, logistic regression, etc. This preliminary work can help clinicians in AF detection with high accuracy and less probability of errors, which can ultimately result in reduction in fatality rate.