Search

Worker safety in the industrial, construction, and energy sectors is the primary concern of governments, organizations, and project managers. Traditional monitoring systems are tedious, laborious, subjective, expensive, and inaccurate. Therefore, the development of automated and accurate systems for real-time monitoring and detecting personal protective equipment (PPE) compliance is urgently needed. This study provides valuable insights and contributions to the field of workers’ safety in the industrial, construction, and energy sectors. It aims to evaluate the potential contribution of providing a robust and accurate real-time PPE compliance monitoring system using state-of-the-art deep learning techniques with real-world videos collected from surveillance cameras. Furthermore, it presents a systematic framework for developing, evaluating, and selecting the most suitable model for real-world applications, starting from data collection and ending with system deployment and maintenance. To the best of our knowledge, the collected dataset in this work is the largest PPE’s dataset, with approximately 7.7 million labels representing different PPEs in 386,011 video frames collected from several surveillance cameras. The techniques adopted to generate different models and evaluated for PPE are CenterNet, Vision Transformer, and YOLOv7. Moreover, an optimized real-time inference engine is developed leveraging the high-computing power of GPUs in the system. The experimental results demonstrate that the models developed using YOLO are the most accurate and can be better generalized to detect PPE compliance in new working environments, achieving mean average precisions of 92.36% and 66.70% on Test Set I and Test Set II, respectively. In addition, they achieve real-time detection of PPE compliance.

MoS2 is a two-dimensional layered transition metal dichalcogenide with unique electronic and optical properties. The fabrication of ultrathin MoS2 is vitally important, since interlayer interactions in its ultrathin varieties will become thickness-dependent, providing thickness-governed tunability and diverse applications of those properties. Unlike with a number of studies that have reported detailed information on direct bandgap emission from MoS2 monolayers, reliable experimental evidence for thickness-induced evolution or transformation of the indirect bandgap remains scarce. Here, the sulfurization of MoO3 thin films with nominal thicknesses of 30 nm, 5 nm and 3 nm was performed. All sulfurized samples were examined at room temperature with spectroscopic ellipsometry and photoluminescence spectroscopy to obtain information about their dielectric function and edge emission spectra. This investigation unveiled an indirect-to-indirect crossover between the transitions, associated with two different Λ and K valleys of the MoS2 conduction band, by thinning its thickness down to a few layers.

k-Nearest Neighbor (k-NN) is a non-parametric algorithm widely used for the estimation and classification of data points especially when the dataset is distributed in several classes. It is considered to be a lazy machine learning algorithm as most of the computations are done during the testing phase instead of performing this task during the training of data. Hence it is practically inefficient, infeasible and inapplicable while processing huge datasets i.e. Big Data. On the other hand, clustering techniques (unsupervised learning) greatly affect results if you do normalization or standardization techniques, difficult to determine "k" Value. In this paper, some novel techniques are proposed to be used as pre-state mechanism of state-of-the-art k-NN Classification Algorithm. Our proposed mechanism uses unsupervised clustering algorithm on large dataset before applying k-NN algorithm on different clusters that might running on single machine, multiple machines or different nodes of a cluster in distributed environment. Initially dataset, possibly having multi dimensions, is pass through clustering technique (K-Means) at master node or controller to find the number of clusters equal to the number of nodes in distributed systems or number of cores in system, and then each cluster will be assigned to exactly one node or one core and then applies k-NN locally, each core or node in clusters sends their best result and the selector choose best and nearest possible class from all options. We will be using one of the gold standard distributed framework. We believe that our proposed mechanism could be applied on big data. We also believe that the architecture can also be implemented on multi GPUs or FPGA to take flavor of k-NN on large or huge datasets where traditional k-NN is very slow.

Feature modeling is a common approach for configuring and capturing commonalities and variations among different Software Product Lines (SPL) products. This process is carried out by a set of SPL design teams, each working on a different configuration of the desired product. The integration of these configurations leads to inconsistencies in the final product design. The typical solution involves extensive deliberation and unnecessary resource usage, which makes SPL inconsistency resolution an expensive and unoptimized process. We present the first comprehensive evaluation of swarm intelligence (using Particle Swarm Optimization) to the problem of resolving inconsistencies in a configured integrated SPL product. We call it o-SPLIT (optimization-based Software Product LIne Tool) and validate o-SPLIT with standard ERP, SPLOT (Software Product Lines Online Tools), and BeTTy (BEnchmarking and TesTing on the analYsis) product configurations along with diverse feature set sizes. The results show that Particle Swarm Optimization can successfully optimize SPL product configurations. Finally, we implement o-SPLIT as a decision-support tool in a real, local SPL setting and acquire subjective feedback from SPL designers which shows that the teams are convinced of the usability and high-level decision support provided by o-SPLIT.

A Software Product Line (SPL) is a collection of software for configuring software products in which sets of features are configured by different teams of product developers. This process often leads to inconsistencies (or dissatisfaction of constraints) in the resulting product configurations, whose resolution consumes considerable business resources. In this paper, we aim to solve this problem by learning, or mathematically modeling, all previous patterns of feature selection by SPL developers, and then use these patterns to predict inconsistent configuration patterns at runtime. We propose and implement an informative Predictive Analytics tool called predictive Software Product LIne Tool (p-SPLIT) which provides runtime decision support to SPL developers in three ways: 1) by identifying configurations of feature selections (patterns) that lead to inconsistent product configurations, 2) by identifying feature selection patterns that lead to consistent product configurations, and 3) by predicting feature inconsistencies in the product that is currently being configured (at runtime). p-SPLIT provides the first application of Predictive Analytics for the SPL feature modeling domain at the application engineering level. With different experiments in representative SPL settings, we obtained 85% predictive accuracy for p-SPLIT and a 98% Area Under the Curve (AUC) score. We also obtained subjective feedback from the practitioners who validate the usability of p-SPLIT in providing runtime decision support to SPL developers. Our results prove that p-SPLIT technology is a potential addition for the global SPL product configuration community, and we further validate this by comparing p-SPLIT's characteristics with state-of-the-art SPL development solutions.

Distinguishing between different handedness of circularly polarized light can be a useful additional property in photodetector technology. The integration of this functionality can be obtained either using optical media with chiro‐optical response, or by the employment of chiral metamaterials. In this work, 3D chiral metasurfaces composed by a 3D helix array, are integrated onto a micrometer‐scale silicon‐based transistor and act as optical filter for circularly polarized light. The technological process involving focused electron beam induced deposition for helix manufacturing is carefully studied with respect to its effect on the phototransistor response. The integrated system exhibits a photoresponse which is dependent on the circular polarization, with a promising asymmetry factor in the visible spectral range. The proposed technology can pave the way for novel potential applications in diverse areas such as materials science, bioimaging, and quantum computing. [ABSTRACT FROM AUTHOR]

MoS2 is a two-dimensional layered transition metal dichalcogenide with unique electronic and optical properties. The fabrication of ultrathin MoS2 is vitally important, since interlayer interactions in its ultrathin varieties will become thickness-dependent, providing thickness-governed tunability and diverse applications of those properties. Unlike with a number of studies that have reported detailed information on direct bandgap emission from MoS2 monolayers, reliable experimental evidence for thickness-induced evolution or transformation of the indirect bandgap remains scarce. Here, the sulfurization of MoO3 thin films with nominal thicknesses of 30 nm, 5 nm and 3 nm was performed. All sulfurized samples were examined at room temperature with spectroscopic ellipsometry and photoluminescence spectroscopy to obtain information about their dielectric function and edge emission spectra. This investigation unveiled an indirect-to-indirect crossover between the transitions, associated with two different Λ and K valleys of the MoS2 conduction band, by thinning its thickness down to a few layers. [ABSTRACT FROM AUTHOR]

A complex Laboratory Developed Test (LDT) is a clinical test developed within a single laboratory. It is typically configured from many feature constraints from clinical repositories, which are part of the existing Laboratory Information Management System (LIMS). Although these clinical repositories are automated, support for managing patient information with test results of an LDT is also integrated within the existing LIMS. Still, the support to configure LDTs design needs to be made available even in standard LIMS packages. The manual configuration of LDTs is a complex process and can generate configuration inconsistencies because many constraints between features can remain unsatisfied. It is a risky process and can lead patients to undergo unnecessary treatments. We proposed an optimized solution (optLDT) based on Genetic Algorithms to automate the configuration and resolve the inconsistencies in LDTs. Opt-LDT encodes LDT configuration as an optimization problem and generates a consistent configuration that satisfies the constraints of the features. We tested and validated opt-LDT for a local secondary care hospital in a real healthcare environment. Our results, averaged over ten runs, show that opt-LDT resolves 90% of inconsistencies while taking between 6 and 6.5 s for each configuration. Moreover, positive feedback based on a subjective questionnaire from clinicians regarding the performance, acceptability, and efficiency of opt-LDT motivates us to present our results for regulatory approval. [ABSTRACT FROM AUTHOR]

Recent advancements in communication technology have transformed the way the industrial system works. This digitalization has improved the way of communication between different actors involved in cyber physical production systems (CPPS), such as users, suppliers, and manufacturers, thus making the whole process transparent. The utilization of emerging new technologies in CPPS can cause vulnerable spots that can be exploited by attackers to launch sophisticated distributed denial of service (DDoS) attacks, hence threatening the availability of the production systems. Existing machine learning based intrusion detection systems (IDS) often rely on unrealistic datasets for training and validation, thus missing the crucial testing phase with real-time scenarios. The results generated by the ML models are based on predictions at each flow level and cannot provide summarized information about malicious entities. To address this limitation, this study proposed an efficient IDS system that uses both rule-based detection and ML-based approaches to detect DDoS attacks damaging the infrastructure of CPPS. For training and validation of the system, we use real-time network traffic extracted from a real industrial scenario, referred to as Farm-to-Fork (F2F) supply chain system. Both, attacks and normal traffic were captured, and bidirectional features were extracted through CIC-FLOWMETER. We make use of 8 ML supervised and unsupervised approaches to detect the malicious flows; and then a rule-based detection mechanism is used to calculate the frequency of the malicious flows and to assign different severity levels based on the computed frequency. The overall results show that supervised models outperform unsupervised approaches and achieve an accuracy 99.97% and TPR 99.96%. Overall, the weighted accuracy when tested and deployed in a real-time scenario is around 98.71%. The results prove that the system works better when considering real-time scenarios and provides comprehensive information about the detected results that can be used to take different mitigation actions.

Renewable energy sources, widely considered as distribution generation units, will be essential parts of the future electrical network. They will be integrated into the network at all voltage levels and act as the main controlling elements in the microgrid to stabilize the network. However, the objective of determining the suitable busbar to integrate the renewable generation source and its maximum capacity is still an indecisive problem. This article presents a methodology to select suitable busbars to integrate the renewable generation unit. A bus selection index is proposed based on three criteria, i.e. voltage deviation, active power loss, and grid energy infeed. The developed algorithm considers network busbar voltage limit and branch loading as constraints and the solution is determined using analytical technique. Algorithm is implemented in MATLAB, and MATPOWER is used for the power flow analysis. Furthermore, the proposed methodology is analysed on CIGRE and IEEE medium voltage benchmark network.

An extremely close integration of a dual band sub-6GHz 4G antenna with a 28GHz 5G antenna is proposed in this article. Firstly, a dual band 4G LTE (Long term Evolution) antenna is designed on an inexpensive substrate. The proposed antenna operates in the 2.5 GHz and 3.5GHz LTE bands. The antenna has dimensions of 63x5.6x0.5mm³, indicating an electrically small design. As the width of the antenna is less than 7 mm, it could be easily mounted on commercial mobile devices. The patterns for both the bands are almost omnidirectional as desired by the low frequency antennas. The proposed antennas do not carry any additional miniaturization or tuning circuitry hence simplifying fabrication process. Secondly, an angled dipole with Yagi topology is proposed, which works in the 28GHz mmWave 5G band. The angled dipole has dimensions 28.3 x 5.6 x 0.5mm³, which is also electrically compact and has a high front to back ratio. The microwave and millimetre wave antennas are placed orthogonally for minimal mutual coupling. The characteristics of both the antennas are not affected by the presence of the other element. Detailed results are shown in this article. [ABSTRACT FROM AUTHOR]

As a key component of a circular economy, remanufacturing is gaining popularity across various sectors. This paper focuses on the wind energy sector, a major player in renewable technologies, which is gradually recognizing its increasing resource-intensive material usage. We present a case study outlining a method for selecting parts from an industrial supply chain partner’s inventory. This strategy is further employed to streamline the manufacturing processes for the chosen part. We utilized the Weighted Sum method, a multi-criteria decision-making strategy, in both instances. We discuss how expertise of process specialists and multi-criteria decision-making techniques could be synthesised for adopting a remanufacturing approach. Data from the commercial partners was collected and any identifying information was stripped. From this, we discovered that the Yaw gear pinion shaft is the top candidate for remanufacturing due to its high commercial value. After comparing various additive manufacturing technologies, Arc Directed Energy Deposition stands out as the best fit for remanufacturing this particular pinion shaft. Although our initial aim was to consider additive manufacturing technologies as solutions for remanufacturing, we show how even conventional manufacturing processes, such as friction welding, could emerge as strong contenders.