Modelling Electricity Consumption During the COVID19 Pandemic: Datasets, Models, Results and a Research Agenda.

The COVID19 pandemic has impacted the global economy, social activities, and Electricity Consumption (EC), affecting the performance of historical data-based Electricity Load Forecasting (ELF) algorithms. This study thoroughly analyses the pandemic's impact on these models and develop a hybrid model with better prediction accuracy using COVID19 data. Existing datasets are reviewed, and their limited generalization potential for the COVID19 period is highlighted. A dataset of 96 residential customers, comprising 36 and six months before and after the pandemic, is collected, posing significant challenges for current models. The proposed model employs convolutional layers for feature extraction, gated recurrent nets for temporal feature learning, and a self-attention module for feature selection, leading to better generalization for predicting EC patterns. Our proposed model outperforms existing models, as demonstrated by a detailed ablation study using our dataset. For instance, it achieves an average reduction of 0.56% & 3.46% in MSE, 1.5% & 5.07% in RMSE, and 11.81% & 13.19% in MAPE over the pre- and post-pandemic data, respectively. However, further research is required to address the varied nature of the data. These findings have significant implications for improving ELF algorithms during pandemics and other significant events that disrupt historical data patterns.

Towards Smart Home Automation Using IoT-Enabled Edge-Computing Paradigm.

Smart home applications are ubiquitous and have gained popularity due to the overwhelming use of Internet of Things (IoT)-based technology. The revolution in technologies has made homes more convenient, efficient, and even more secure. The need for advancement in smart home technology is necessary due to the scarcity of intelligent home applications that cater to several aspects of the home simultaneously, i.e., automation, security, safety, and reducing energy consumption using less bandwidth, computation, and cost. Our research work provides a solution to these problems by deploying a smart home automation system with the applications mentioned above over a resource-constrained Raspberry Pi (RPI) device. The RPI is used as a central controlling unit, which provides a cost-effective platform for interconnecting a variety of devices and various sensors in a home via the Internet. We propose a cost-effective integrated system for smart home based on IoT and Edge-Computing paradigm. The proposed system provides remote and automatic control to home appliances, ensuring security and safety. Additionally, the proposed solution uses the edge-computing paradigm to store sensitive data in a local cloud to preserve the customer's privacy. Moreover, visual and scalar sensor-generated data are processed and held over edge device (RPI) to reduce bandwidth, computation, and storage cost. In the comparison with state-of-the-art solutions, the proposed system is 5% faster in detecting motion, and 5 ms and 4 ms in switching relay on and off, respectively. It is also 6% more efficient than the existing solutions with respect to energy consumption.

An Efficient Anomaly Recognition Framework Using an Attention Residual LSTM in Surveillance Videos.

Video anomaly recognition in smart cities is an important computer vision task that plays a vital role in smart surveillance and public safety but is challenging due to its diverse, complex, and infrequent occurrence in real-time surveillance environments. Various deep learning models use significant amounts of training data without generalization abilities and with huge time complexity. To overcome these problems, in the current work, we present an efficient light-weight convolutional neural network (CNN)-based anomaly recognition framework that is functional in a surveillance environment with reduced time complexity. We extract spatial CNN features from a series of video frames and feed them to the proposed residual attention-based long short-term memory (LSTM) network, which can precisely recognize anomalous activity in surveillance videos. The representative CNN features with the residual blocks concept in LSTM for sequence learning prove to be effective for anomaly detection and recognition, validating our model's effective usage in smart cities video surveillance. Extensive experiments on the real-world benchmark UCF-Crime dataset validate the effectiveness of the proposed model within complex surveillance environments and demonstrate that our proposed model outperforms state-of-the-art models with a 1.77%, 0.76%, and 8.62% increase in accuracy on the UCF-Crime, UMN and Avenue datasets, respectively.

Atrous Convolutions and Residual GRU Based Architecture for Matching Power Demand with Supply.

Nowadays, for efficient energy management, local demand-supply matching in power grid is emerging research domain. However, energy demand is increasing day by day in many countries due to rapid growth of the population and most of their work being reliant on electronic devices. This problem has highlighted the significance of effectively matching power demand with supply for optimal energy management. To resolve this issue, we present an intelligent deep learning framework that integrates Atrous Convolutional Layers (ACL) with Residual Gated Recurrent Units (RGRU) to establish balance between the demand and supply. Moreover, it accurately predicts short-term energy and delivers a systematic method of communication between consumers and energy distributors as well. To cope with the varying nature of electricity data, first data acquisition step is performed where data are collected from various sources such as smart meters and solar plants. In the second step a pre-processing method is applied on raw data to normalize and clean the data. Next, the refined data are passed to ACL for spatial feature extraction. Finally, a sequential learning model RGRU is used that learns from complicated patterns for the final output. The proposed model obtains the smallest values of Mean Square Error (MSE) including 0.1753, 0.0001, 0.0177 over IHEPC, KCB, and Solar datasets, respectively, which manifests better performance as compared to existing approaches.

Towards Efficient Electricity Forecasting in Residential and Commercial Buildings: A Novel Hybrid CNN with a LSTM-AE based Framework.

Due to industrialization and the rising demand for energy, global energy consumption has been rapidly increasing. Recent studies show that the biggest portion of energy is consumed in residential buildings, i.e., in European Union countries up to 40% of the total energy is consumed by households. Most residential buildings and industrial zones are equipped with smart sensors such as metering electric sensors, that are inadequately utilized for better energy management. In this paper, we develop a hybrid convolutional neural network (CNN) with an long short-term memory autoencoder (LSTM-AE) model for future energy prediction in residential and commercial buildings. The central focus of this research work is to utilize the smart meters' data for energy forecasting in order to enable appropriate energy management in buildings. We performed extensive research using several deep learning-based forecasting models and proposed an optimal hybrid CNN with the LSTM-AE model. To the best of our knowledge, we are the first to incorporate the aforementioned models under the umbrella of a unified framework with some utility preprocessing. Initially, the CNN model extracts features from the input data, which are then fed to the LSTM-encoder to generate encoded sequences. The encoded sequences are decoded by another following LSTM-decoder to advance it to the final dense layer for energy prediction. The experimental results using different evaluation metrics show that the proposed hybrid model works well. Also, it records the smallest value for mean square error (MSE), mean absolute error (MAE), root mean square error (RMSE) and mean absolute percentage error (MAPE) when compared to other state-of-the-art forecasting methods over the UCI residential building dataset. Furthermore, we conducted experiments on Korean commercial building data and the results indicate that our proposed hybrid model is a worthy contribution to energy forecasting.

Finite Element Analysis of Manufacturing Deformation in Polymer Matrix Composites.

This paper introduces a unique finite element analysis (FEA) technique designed to predict elastic response in polymer matrix composites (PMCs). Extensive research has been conducted to model the manufacturing process of multiple 'L'-shaped components, fabricated from SPRINTTM materials (GLP 43 and GLP 96) at two thicknesses (15 mm and 25 mm). Three distinct FEA methodologies were utilised to determine the impact of thermal loads and rigid fixtures. An error deviation of 3.23% was recorded when comparing simulation results to experimental data, thereby validating the effectiveness of the FEA methodology.

Influence of the Duty Cycle of Pulse Electrodeposition-Coated Ni-Al2O3 Nanocomposites on Surface Roughness Properties.

In this study, the viability of duty cycle variation was explored as a potential method to improve the mechanical and surface roughness properties of Ni-Al2O3 nanocoatings through pulse electrodeposition. The areal and surface roughness properties of nanocomposite pulse electrodeposition-coated materials with varying duty cycles from 20% to 100% was studied with the analysis of bearing area curves and power spectral densities. Results demonstrate that with decrease in duty cycle, there was an enhancement in aerial roughness properties from 0.348 to 0.195 µm and surface roughness properties from 0.779 to 0.245 µm. The change in surface roughness was due to grain size variation, resulting from the varying time intervals during pulse coatings. This increase in grain size with the change in duty cycle was confirmed with the scanning electron microscope. In addition, an increase in grain size from 0.32 to 0.92 µm with an increase in duty cycle resulted in a decrease in nanohardness from 4.21 to 3.07 GPa. This work will provide a novel method for obtaining Ni-Al2O3 nanocomposite coatings with improved surface roughness and hardness properties for wider industrial applications.

Experimental Study on the Effect of Micro-Texture on EHL Point-Contact Film Thickness Subject to Sliding Conditions.

Processing texture on contact surfaces can improve the friction performance of mechanical comments. In this research, micro-dimple textures with various parameter were processed on a steel ball's surface with a picosecond laser. Then, the EHL (elastohydrodynamic lubrication) oil film thickness was measured on an optical ball-on-disc tribometer subjected to pure sliding conditions. The effects of sliding velocity, load, dimple location and dimple depth on the film thickness were analyzed. The results showed that the dimple affected the pressure distribution in the contact area, which in turn changed the distribution of the local film thickness. An increase in the local film thickness occurred between the dimple and outlet of the contact region, while a decrease in the film thickness formed from the dimple to the entrance of the contact area and both sides of the dimple's edge. Velocity and applied loads affected the film thickness distribution as well. As the sliding velocity increased, the film thickness increasing region enlarged, while the film thickness-decreasing area shrank. The increase in load resulted in a negative effect on the increase in film thickness. This study will provide a reference for point-contact designs with low friction conditions.

Further Investigations and Parametric Analysis of Microstructural Alterations under Rolling Contact Fatigue.

Bearing elements under rolling contact fatigue (RCF) exhibit microstructural features, known as white etching bands (WEBs) and dark etching regions (DERs). The formation mechanism of these microstructural features has been questionable and therefore warranted this study to gain further understanding. Current research describes mechanistic investigations of standard AISI 52100 bearing steel balls subjected to RCF testing under tempering conditions. Subsurface analyses of RCF-tested samples at tempering conditions have indicated that the microstructural alterations are progressed with subsurface yielding and primarily dominated by thermal tempering. Furthermore, bearing balls are subjected to static load tests in order to evaluate the effect of lattice deformation. It is suggested from the comparative analyses that a complete rolling sequence with non-proportional stress history is essential for the initiation and progression of WEBs, supported by the combination of carbon flux, assisted by dislocation and thermally activated carbon diffusion. These novel findings will lead to developing a contemporary and new-fangled prognostic model applied to microstructural alterations.

Optimized Dual Fire Attention Network and Medium-Scale Fire Classification Benchmark.

Vision-based fire detection systems have been significantly improved by deep models; however, higher numbers of false alarms and a slow inference speed still hinder their practical applicability in real-world scenarios. For a balanced trade-off between computational cost and accuracy, we introduce dual fire attention network (DFAN) to achieve effective yet efficient fire detection. The first attention mechanism highlights the most important channels from the features of an existing backbone model, yielding significantly emphasized feature maps. Then, a modified spatial attention mechanism is employed to capture spatial details and enhance the discrimination potential of fire and non-fire objects. We further optimize the DFAN for real-world applications by discarding a significant number of extra parameters using a meta-heuristic approach, which yields around 50% higher FPS values. Finally, we contribute a medium-scale challenging fire classification dataset by considering extremely diverse, highly similar fire/non-fire images and imbalanced classes, among many other complexities. The proposed dataset advances the traditional fire detection datasets by considering multiple classes to answer the following question: what is on fire? We perform experiments on four widely used fire detection datasets, and the DFAN provides the best results compared to 21 state-of-the-art methods. Consequently, our research provides a baseline for fire detection over edge devices with higher accuracy and better FPS values, and the proposed dataset extension provides indoor fire classes and a greater number of outdoor fire classes; these contributions can be used in significant future research. Our codes and dataset will be publicly available at https://github.com/tanveer-hussain/DFAN.

Semi Salix Leaf Textured Gas Mechanical Face Seal with Enhanced Opening Performance.

Seal performance of a novel gas mechanical face seal with semi salix leaf textures was introduced and theoretically investigated with the purpose of enhancing hydrostatic and hydrodynamic opening performance. First, a theoretical model of a laser surface textured gas mechanical face seal with semi salix leaf textures was developed. Second, the impact of operating and texturing parameters on open force, leakage, and friction torque was numerically investigated and has been discussed based on gas lubrication theory. Numerical results demonstrate that the semi salix leaf textured gas face seal has larger hydrostatic and hydrodynamic effects than the semi ellipse textured seal because of the effect of the inlet groove. All semi salix leaf textured surfaces had better open performance than the semi ellipse textured surface, which means that the inlet groove plays an important role in improving open performance and consequently decreasing contact friction during the start-up stage. Texturing parameters also influenced the seal performance of thee semi salix leaf textured gas face seal. When the inclination angle was 50°, the radial proportion of the inlet groove was 0.8, the dimple number was 9, and the open force resulted in the maximum value. This research has demonstrated the positive effects of the applications of a semi salix leaf textured gas mechanical face seal that combines the excellent hydrostatic and hydrodynamic effects of groove texture and the excellent wear resistance of microporous textures.

Friction Behavior of a Textured Surface against Several Materials under Dry and Lubricated Conditions.

This paper reports research on the frictional behavior of a textured surface against several materials under dry and lubricated conditions, and this is aimed to provide design guidelines on the surface texturing for wide-ranging industrial applications. Experiments were performed on a tribo-tester with the facility of simulating A ball-on-plate model in reciprocating motion under dry, oil-lubricated, and water-lubricated conditions. To study the frictional behavior of textured SiC against various materials, three types of ball-bearing -elements, 52100 steel, silicon nitride (Si3N4), and polytetrafluoroethylene (PTFE), were used. Friction and wear performance of an un-textured surface and two types of widely used micro-scale texture surfaces, grooves and circular dimples, were examined and compared. The results demonstrated that the effect of surface textures on friction and wear performance is influenced by texture parameters and the materials of friction pairs. The circular-dimple texture and the groove texture, with certain texture parameters, played a positive role in improving friction and wear performance under specific operating conditions used in this research for SiC-steel and SiC-Si3N4 friction pairs; however, there was no friction and wear improvement for the textured SiC-PTFE friction pair. The results of this study offer an understanding and a knowledge base to enhance the performance of bearing elements in complex interacting systems.

Vision Sensor-Based Real-Time Fire Detection in Resource-Constrained IoT Environments.

Fire detection and management is very important to prevent social, ecological, and economic damages. However, achieving real-time fire detection with higher accuracy in an IoT environment is a challenging task due to limited storage, transmission, and computation resources. To overcome these challenges, early fire detection and automatic response are very significant. Therefore, we develop a novel framework based on a lightweight convolutional neural network (CNN), requiring less training time, and it is applicable over resource-constrained devices. The internal architecture of the proposed model is inspired by the block-wise VGG16 architecture with a significantly reduced number of parameters, input size, inference time, and comparatively higher accuracy for early fire detection. In the proposed model, small-size uniform convolutional filters are employed that are specifically designed to capture fine details of input fire images with a sequentially increasing number of channels to aid effective feature extraction. The proposed model is evaluated on two datasets such as a benchmark Foggia's dataset and our newly created small-scaled fire detection dataset with extremely challenging real-world images containing a high-level of diversity. Experimental results conducted on both datasets reveal the better performance of the proposed model compared to state-of-the-art in terms of accuracy, false-positive rate, model size, and running time, which indicates its robustness and feasible installation in real-world scenarios.

A Review of Friction Performance of Lubricants with Nano Additives.

It has been established in literature that the addition of nanoparticles to lubricants at an optimum concentration results in a lower coefficient of friction compared to lubricants with no nanoparticle additives. This review paper shows a comparison of different lubricants based on the COF (coefficient of friction) with nanoadditives. The effect of the addition of nanoparticles on the friction coefficient was analyzed for both synthetic and biolubricants separately. The limitations associated with the use of nanoparticles are explained. The mechanisms responsible for a reduction in friction when nanoparticles are used as an additive are also discussed. Various nanoparticles that have been most widely used in recent years showed good performance within lubricants, including CuO (copper oxide), MoS2 (molybdenum disulfide), and TiO2 (titanium dioxide). The paper also indicates some research gaps that need to be addressed.

CuO Bionanocomposite with Enhanced Stability and Antibacterial Activity against Extended-Spectrum Beta-Lactamase Strains.

Worldwide, bacterial resistance to beta-lactam antibiotics is the greatest challenge in public health care. To overcome the issue, metal-based nanoparticles were extensively used as an alternative to traditional antibiotics. However, their unstable nature limits their use. In the present study a very simple, environmentally friendly, one-pot synthesis method that avoids the use of organic solvents has been proposed to design stable, novel nanocomposites. Formulation was done by mixing biogenic copper oxide (CuO) nanomaterial with glycerol and phospholipids isolated from egg yolk in an appropriate ratio at optimum conditions. Characterization was done using dynamic light scattering DLS, Zeta potential, high performance liquid chromatography (HPLC), and transmission electron microscopy (TEM). Further, its antibacterial activity was evaluated against the extended-spectrum beta-lactamase strains based on zone of inhibition and minimal inhibitory concentration (MIC) indices. Results from this study have demonstrated the formulation of stable nanocomposites with a zeta potential of 34.9 mV. TEM results indicated clear dispersed particles with an average of 59.3 ± 5 nm size. Furthermore, HPLC analysis of the egg yolk extract exhibits the presence of phospholipids in the sample and has significance in terms of stability. The newly formed nanocomposite has momentous antibacterial activity with MIC 62.5 µg/mL. The results suggest that it could be a good candidate for drug delivery in terms of bactericidal therapeutic applications.

WEENet: An Intelligent System for Diagnosing COVID-19 and Lung Cancer in IoMT Environments.

The coronavirus disease 2019 (COVID-19) pandemic has caused a major outbreak around the world with severe impact on health, human lives, and economy globally. One of the crucial steps in fighting COVID-19 is the ability to detect infected patients at early stages and put them under special care. Detecting COVID-19 from radiography images using computational medical imaging method is one of the fastest ways to diagnose the patients. However, early detection with significant results is a major challenge, given the limited available medical imaging data and conflicting performance metrics. Therefore, this work aims to develop a novel deep learning-based computationally efficient medical imaging framework for effective modeling and early diagnosis of COVID-19 from chest x-ray and computed tomography images. The proposed work presents "WEENet" by exploiting efficient convolutional neural network to extract high-level features, followed by classification mechanisms for COVID-19 diagnosis in medical image data. The performance of our method is evaluated on three benchmark medical chest x-ray and computed tomography image datasets using eight evaluation metrics including a novel strategy of cross-corpse evaluation as well as robustness evaluation, and the results are surpassing state-of-the-art methods. The outcome of this work can assist the epidemiologists and healthcare authorities in analyzing the infected medical chest x-ray and computed tomography images, management of the COVID-19 pandemic, bridging the early diagnosis, and treatment gap for Internet of Medical Things environments.

Wear Performance Analysis of Ni⁻Al2O3 Nanocomposite Coatings under Nonconventional Lubrication.

This article presents a wear study of Ni⁻Al2O3 nanocomposite coatings in comparison to uncoated steel contacts under reciprocating motion. A ball-on-flat type contact configuration has been used in this study in which a reciprocating flat steel sample has been used in a coated and uncoated state against a stationary steel ball under refrigerant lubrication. The next generation of environmentally friendly refrigerant HFE-7000 has been used itself as lubricant in this study without the influence of any external lubricant. The thermodynamic applications and performance of HFE-7000 is being studied worldwide, as it is replacing the previous generation of refrigerants. No work however has been previously performed to evaluate the wear performance of HFE-7000 using nanocomposite coatings. The wear scar developed on each of the flat and ball samples was studied using a Scanning Electron Microscope (SEM). The micrographs show that a combination of adhesive and abrasive wear occurs when using uncoated steel samples. Micro-delamination is observed in the case of Ni⁻Al2O3 nanocomposite coatings accompanied by adhesive and abrasive wear. Wear volume of the wear track was calculated using a White Light Interferometer. Energy-Dispersive X-ray Spectroscopic (EDS) analysis of the samples reveals fluorine and oxygen on the rubbing parts when tested using coated as well as uncoated samples. The formation of these fluorinated and oxygenated tribo-films helps to reduce wear and their formation is accelerated by increasing the refrigerant temperature. Ni⁻Al2O3 nanocomposite coatings show good wear performance at low and high loads in comparison to uncoated contacts. At intermediate loads the coated contacts resulted in increased wear, especially at low loads. This increase in wear is associated with the delamination of the coating and the slow formation of protective surface films under these testing conditions.

Electrochemical Study of Polymer and Ceramic-Based Nanocomposite Coatings for Corrosion Protection of Cast Iron Pipeline.

Coating is one of the most effective measures to protect metallic materials from corrosion. Various types of coatings such as metallic, ceramic and polymer coatings have been investigated in a quest to find durable coatings to resist electrochemical decay of metals in industrial applications. Many polymeric composite coatings have proved to be resistant against aggressive environments. Two major applications of ferrous materials are in marine environments and in the oil and gas industry. Knowing the corroding behavior of ferrous-based materials during exposure to these aggressive applications, an effort has been made to protect the material by using polymeric and ceramic-based coatings reinforced with nano materials. Uncoated and coated cast iron pipeline material was investigated during corrosion resistance by employing EIS (electrochemical impedance spectroscopy) and electrochemical DC corrosion testing using the "three electrode system". Cast iron pipeline samples were coated with Polyvinyl Alcohol/Polyaniline/FLG (Few Layers Graphene) and TiO2/GO (graphene oxide) nanocomposite by dip-coating. The EIS data indicated better capacitance and higher impedance values for coated samples compared with the bare metal, depicting enhanced corrosion resistance against seawater and "produce water" of a crude oil sample from a local oil rig; Tafel scans confirmed a significant decrease in corrosion rate of coated samples.

Electrochemical Comparison of SAN/PANI/FLG and ZnO/GO Coated Cast Iron Subject to Corrosive Environments.

ZnO/GO (Graphene Oxide) and SAN (Styrene Acrylonitrile)/PANI (Polyaniline)/FLG (Few Layers Graphene) nanocomposite coatings were produced by solution casting and sol-gel methods, respectively, to enhance corrosion resistance of ferrous based materials. Corrosive seawater and 'produced crude oil water' environments were selected as electrolytes for this study. Impedance and coating capacitance values obtained from Electrochemical Impedance Spectroscopy (EIS) Alternating Current (AC technique) showed enhanced corrosion resistance of nanocomposites coatings in the corrosive environments. Tafel scan Direct Current (DC technique) was used to find the corrosion rate of nanocomposite coating. SAN/PANI/FLG coating reduced the corrosion of bare metal up to 90% in seawater whereas ZnO/GO suppressed the corrosion up to 75% having the impedance value of 100 Ω. In produced water of crude oil, SAN/PANI/FLG reduced the corrosion up to 95% while ZnO/GO suppressed the corrosion up to 10%. Hybrid composites of SAN/PANI/FLG coatings have demonstrated better performances compared to ZnO/GO in the corrosive environments under investigation. This study provides fabrication of state-of-the-art novel anti corrosive nanocomposite coatings for a wide range of industrial applications. Reduced corrosion will result in increased service lifetime, durability and reliability of components and system and will in turn lead to significant cost savings.

Performance Analysis of Retrofitted Tribo-Corrosion Test Rig for Monitoring In Situ Oil Conditions.

Oils and lubricants, once extracted after use from a mechanical system, can hardly be reused, and should be refurbished or replaced in most applications. New methods of in situ oil and lubricant efficiency monitoring systems have been introduced for a wide variety of mechanical systems, such as automobiles, aerospace aircrafts, ships, offshore wind turbines, and deep sea oil drilling rigs. These methods utilize electronic sensors to monitor the "byproduct effects" in a mechanical system that are not indicative of the actual remaining lifecycle and reliability of the oils. A reliable oil monitoring system should be able to monitor the wear rate and the corrosion rate of the tribo-pairs due to the inclusion of contaminants. The current study addresses this technological gap, and presents a novel design of a tribo-corrosion test rig for oils used in a dynamic system. A pin-on-disk tribometer test rig retrofitted with a three electrode-potentiostat corrosion monitoring system was used to analyze the corrosion and wear rate of a steel tribo-pair in industrial grade transmission oil. The effectiveness of the retrofitted test rig was analyzed by introducing various concentrations of contaminants in an oil medium that usually leads to a corrosive working environment. The results indicate that the retrofitted test rig can effectively monitor the in situ tribological performance of the oil in a controlled dynamic corrosive environment. It is a useful method to understand the wear-corrosion synergies for further experimental work, and to develop accurate predictive lifecycle assessment and prognostic models. The application of this system is expected to have economic benefits and help reduce the ecological oil waste footprint.