Performance optimization of energy-efficient solar absorbers for thermal energy harvesting in modern industrial environments using a solar deep learning model.

Thermal energy harvesting has seen a rise in popularity in recent years due to its potential to generate renewable energy from the sun. One of the key components of this process is the solar absorber, which is responsible for converting solar radiation into thermal energy. In this paper, a smart performance optimization of energy efficient solar absorber for thermal energy harvesting is proposed for modern industrial environments using solar deep learning model. In this model, data is collected from multiple sensors over time that measure various environmental factors such as temperature, humidity, wind speed, atmospheric pressure, and solar radiation. This data is then used to train a machine learning algorithm to make predictions on how much thermal energy can be harvested from a particular panel or system. In a computational range, the proposed solar deep learning model (SDLM) reached 83.22 % of testing and 91.72 % of training results of false positive absorption rate, 69.88 % of testing and 81.48 % of training results of false absorption discovery rate, 81.40 % of testing and 72.08 % of training results of false absorption omission rate, 75.04 % of testing and 73.19 % of training results of absorbance prevalence threshold, and 90.81 % of testing and 78.09 % of training results of critical success index. The model also incorporates components such as insulation and orientation to further improve its accuracy in predicting the amount of thermal energy that can be harvested. Solar absorbers are used in industrial environments to absorb the sun's radiation and turn it into thermal energy. This thermal energy can then be used to power things such as heating and cooling systems, air compressors, and even some types of manufacturing operations. By using a solar deep learning model, businesses can accurately predict how much thermal energy can be harvested from a particular solar absorber before making an investment in a system.

Response score-based protein structure analysis for cancer prediction aided by the Internet of Things.

Medical diagnosis through prediction and analysis is par excellence in integrating modern technologies such as the Internet of Things (IoT). With the aid of such technologies, clinical assessments are eased with protracted computing. Specifically, cancer research through structure prediction and analysis is improved through human and machine interventions sustaining precision improvements. This article, therefore, introduces a Protein Structure Prediction Technique based on Three-Dimensional Sequence. This sequence is modeled using amino acids and their folds observed during the pre-initial cancer stages. The observed sequences and the inflammatory response score of the structure are used to predict the impact of cancer. In this process, ensemble learning is used to identify sequence and folding responses to improve inflammations. This score is correlated with the clinical data for structures and their folds independently for determining the structure changes. Such changes through different sequences are handled using repeated ensemble learning for matching and unmatching response scores. The introduced idea integrated with deep ensemble learning and IoT combination, notably employing stacking method for enhanced cancer prediction precision and interdisciplinary collaboration. The proposed technique improves prediction precision, data correlation, and change detection by 11.83%, 8.48%, and 13.23%, respectively. This technique reduces correlation time and complexity by 10.43% and 12.33%, respectively.

Hybrid Control of the DC Microgrid Using Deep Neural Networks and Global Terminal Sliding Mode Control with the Exponential Reaching Law.

The direct current (DC) microgrid is one of the key research areas for our advancement toward carbon-free energy production. In this paper, a two-step controller is designed for the DC microgrid using a combination of the deep neural network (DNN) and exponential reaching law-based global terminal sliding mode control (ERL-GTSMC). The DC microgrid under consideration involves multiple renewable sources (wind, PV) and an energy storage unit (ESU) connected to a 700 V DC bus and a 4-12 kW residential load. The proposed control method eliminates the chattering phenomenon and offers quick reaching time by utilizing the exponential reaching law (ERL). In the two-step control configuration, first, DNNs are used to find maximum power point tracking (MPPT) reference values, and then ERL-based GTSMC is utilized to track the reference values. The real dynamics of energy sources and the DC bus are mathematically modeled, which increases the system's complexity. Through the use of Lyapunov stability criteria, the stability of the control system is examined. The effectiveness of the suggested hybrid control algorithm has been examined using MATLAB simulations. The proposed framework has been compared to traditional sliding mode control and terminal sliding mode control to showcase its superiority and robustness. Experimental tests based on the hardware-in-the-loop (HIL) setup are then conducted using 32-bit TMS320F28379D microcontrollers. Both MATLAB and HIL results show strong performance under a range of environmental circumstances and system uncertainties.

Quad-port MIMO antenna with high isolation characteristics for sub 6-GHz 5G NR communication.

A four-port MIMO antenna with high isolation is presented. The antenna is primarily envisioned to cover the n48 band of Frequency Range-1 (FR-1) with TDD duplex mode. The engineered antenna has electrical dimensions of 90 × 90 × 1.57 mm3. The size miniaturization of a single antenna unit is achieved through an optimized placement of slots and extended arms. The quad-antennas are then placed orthogonally to achieve antenna diversity. The antenna resonates at 3.56 GHz and 5.28 GHz having 2:1 VSWR fractional bandwidth of 1.82% and 2.12%. The proposed resonator provides 88.34% and 79.28% efficiency at lower and upper bands, respectively. The antenna is an exceptional radiator regarding MIMO diversity performance owing to high inter-element isolation. The values of envelope correlation coefficient < 0.05, channel capacity loss is nearly 0.1 bits/sec/Hz, and total active reflection coefficient is - 24.26. The full ground plane profile aids in high directivity and cross-pol isolation. The antenna exhibits a gain of 4.2 dBi and 2.8 dBi, respectively, justifying intended application requirements. There is a good coherence between simulation and experimental results. The self-decoupled antenna poses its application in 5G and WLAN Communication Applications.

Sickle-shaped high gain and low profile based four port MIMO antenna for 5G and aeronautical mobile communication.

The construction of the four-port MIMO antenna in the form of a sickle is provided in the article. Initially, the single port element is designed and optimized. Next, a structure with two ports is created, and lastly, a design with four ports is completed. This process is repeated until the design is optimized. Three types of parametric analysis are considered, including variations in length, widths of sickle-shaped patches, and varying sizes of DGS. The frequency range of 2-8 GHz is used for structural investigation. The - 18.77 dB of return loss was observed at 3.825 GHz for a single-element structure. The optimized one-port structure provides a return loss of - 19.79 dB at 3.825 GHz. The port design offers a bandwidth of 0.71 GHz (3.515-4.225). The four-port design represents two bands that are observed at 3 GHz and 5.43 GHz. Both bands provide the return loss at respectively - 19.79 dB and - 20.53 dB with bandwidths of 1.375 GHz (2.14-3.515) and 0.25 GHz (5.335-5.585). The healthy isolation among both transmittance and reflectance response is achieved. The low-profile material was used to create the design that was presented. The article includes a comparison of the findings that were measured and those that were simulated. The four-port design that has been shown offers a total gain of 15.93 dB, a peak co-polar value of 5.46 dB, a minimum return loss of - 20.53 dB, a peak field distribution of 46.43 A/m and a maximum bandwidth of 1.375 GHz. The values for all diversity parameters like ECC are near zero, the Negative value of TARC, Near to zero MEG, DG is almost 10 dB, and a zero value of CCL is achieved. All diversity parameter performance is within the allowable range. The design is well suited for 5G and aeronautical mobile communication applications.

Designing a Graphene Metasurface Organic Material Sensor for Detection of Organic Compounds in Wastewater.

In many fields, such as environmental monitoring, food safety, and medical diagnostics, the identification of organic compounds is essential. It is crucial to create exceptionally sensitive and selective sensors for the detection of organic compounds in order to safeguard the environment and human health. Due to its outstanding electrical, mechanical, and chemical characteristics, the two-dimensional carbon substance graphene has recently attracted much attention for use in sensing applications. The purpose of this research is to create an organic material sensor made from graphene for the detection of organic substances like phenol, ethanol, methanol, chloroform, etc. Due to its high surface-to-volume ratio and potent interactions with organic molecules, graphene improves the sensor's performance while the metasurface structure enables the design of highly sensitive and selective sensing elements. The suggested sensor is highly sensitive and accurate at detecting a broad spectrum of organic molecules, making it appropriate for a number of applications. The creation of this sensor has the potential to have a substantial impact on the field of organic sensing and increase the safety of food, medicine, and the environment. The graphene metasurface organic material sensor (GMOMS) was categorized into three types denoted as GMOMS1, GMOMS2, and GMOMS3 based on the specific application of the graphene chemical potential (GCP). In GMOMS1, GCP was applied on both the CSRR and CS surfaces. In GMOMS2, GCP was applied to the CS surface and the surrounding outer region of the CSRR. In GMOMS3, GCP was applied to the CSRR and the surrounding outer region of the CSRR surface. The results show that all three designs exhibit high relative sensitivity, with the maximum values ranging from 227 GHz/RIU achieved by GMOMS1 to 4318 GHz/RIU achieved by GMOMS3. The FOM values achieved for all the designs range from 2.038 RIU-1 achieved by GMOMS2 to 31.52 RIU-1 achieved by GMOMS3, which is considered ideal in this paper.

Development of Split Ring Resonator Shaped Six Element 2 × 3 Multiple Input Multiple Output Antenna for the C/X/Ku/K Band Applications.

In this manuscript, we have numerically investigated and experimentally verified the six-element split ring resonator and circular patch-shaped multiple input, multiple output antenna operating in the 1-25 GHz band. MIMO antennas are analyzed in terms of several physical parameters, such as reflectance, gain, directivity, VSWR, and electric field distribution. The parameters of the MIMO antenna, for instance, the envelope correlation coefficient (ECC), channel capacity loss (CCL), the total active reflection coefficient (TARC), directivity gain (DG), and mean effective gain (MEG), are also investigated for identification of a suitable range of these parameters for multichannel transmission capacity. Ultrawideband operation at 10.83 GHz is possible for the theoretically designed and practically executed antenna with the return loss and gain values of -19 dB and -28 dBi, respectively. Overall, the antenna offers minimum return loss values of -32.74 dB for the operating band of 1.92 to 9.81 GHz with a bandwidth of 6.89 GHz. The antennas are also investigated in terms of a continuous ground patch and a scattered rectangular patch. The proposed results are highly applicable for the ultrawideband operating MIMO antenna application in satellite communication with C/X/Ku/K bands.

Design and Development of Ultrabroadband, High-Gain, and High-Isolation THz MIMO Antenna with a Complementary Split-Ring Resonator Metamaterial.

The need for high-speed communication has created a way to design THz antennas that operate at high frequencies, speeds, and data rates. In this manuscript, a THz MIMO antenna is designed using a metamaterial. The two-port antenna design proposed uses a complementary split-ring resonator patch. The design results are also compared with a simple patch antenna to show the improvement. The design shows a better isolation of 50 dB. A broadband width of 8.3 THz is achieved using this complementary split-ring resonator design. The percentage bandwidth is 90%, showing an ultrabroadband response. The highest gain of 10.34 dB is achieved with this design. Structural parametric optimization is applied to the complementary split-ring resonator MIMO antenna design. The designed antenna is also optimized by applying parametric optimization to different geometrical parameters. The optimized design has a 20 µm ground plane, 14 µm outer ring width, 6 µm inner ring width, and 1.6 µm substrate thickness. The proposed antenna with its broadband width, high gain, and high isolation could be applied in high-speed communication devices.

Enhanced Sensitivity of Binary/Ternary Locally Resonant Porous Phononic Crystal Sensors for Sulfuric Acid Detection: A New Class of Fluidic-Based Biosensors.

This research presented a comprehensive study of a one-dimensional (1D) porous silicon phononic crystal design as a novel fluidic sensor. The proposed sensor is designed to detect sulfuric acid (H2SO4) within a narrow concentration range of 0-15%. Sulfuric acid is a mineral acid extensively utilized in various physical, chemical, and industrial applications. Undoubtedly, its concentration, particularly at lower levels, plays a pivotal role in these applications. Hence, there is an urgent demand for a highly accurate and sensitive tool to monitor even the slightest changes in its concentration, which is crucial for researchers. Herein, we presented a novel study on the optimization of the phononic crystal (PnC) sensor. The optimization process involves a comparative strategy between binary and ternary PnCs, utilizing a multilayer stack comprising 1D porous silicon (PSi) layers. Additionally, a second comparison is conducted between conventional Bragg and local resonant PnCs to demonstrate the design with the highest sensitivity. Moreover, we determine the optimum values for the materials' thickness and number of periods. The results revealed that the ternary local resonant PnC design with the configuration of {silicone rubber/[PSi1/PSi2/PSi3]N/silicone rubber} is the optimal sensor design. The sensor provided a super sensitivity of 2.30 × 107 Hz for a concentration change of just 2%. This exceptional sensitivity is attributed to the presence of local resonant modes within the band gap of PnCs. The temperature effects on the local resonant modes and sensor performance have also been considered. Furthermore, additional sensor performance parameters such as quality factor, figure of merit, detection limit, and damping rate have been calculated to demonstrate the effectiveness of the proposed liquid sensor. The transfer matrix method was utilized to compute the transmission spectra of the PnC, and Hashin's expression was employed to manipulate the porous silicon media filled with sulfuric acid at various concentrations. Lastly, the proposed sensor can serve as an efficient tool for detecting acidic rain, contaminating freshwater, and assessing food and liquid quality, as well as monitoring other pharmaceutical products.

A Novel Design of Complementary Split Ring Resonator Metamaterial-Based Low-Profile MIMO Antenna with Defected Ground Structure for S/C/X/Ka Band Applications.

The article represents the design of two port-based printed MIMO antenna structures that have the advantages of low profile, simple structure, good isolation, peak gain, directive gain, and reflection coefficient. The performance characteristics are observed for the four design structures by cropping the patch region, loading the slits near the hexagonal-shaped patch, and adding and removing the slots in the ground area. The antenna provides a least reflection coefficient of -39.44 dB, a maximum electric field of patch region of 33.3 V/cm, a total gain of 5.23 dB, and good values of total active reflection coefficient and diversity gain. The proposed design provides nine bands' response, a peak bandwidth of 2.54 GHz, and a peak bandwidth of 26.127 dB. The four proposed structures are fabricated using a low-profile material to support mass production. The comparison among simulated and fabricated structures is included to check the authenticity of the work. The performance assessment of the proposed design with other published articles is carried out for the performance observation. The suggested technique is analyzed over the wideband of frequency region 1 GHz to 14 GHz. The multiple band responses make the proposed work suitable for wireless applications in S/C/X/Ka bands.

Numerical analysis of hafnium oxide and phase change material-based multi-layered infrared and visible frequency sensor for biomolecules sensing application.

We report on the results of a numerical investigation into a phase transition material and hafnium (IV) oxide-based refractive index sensor with a wide spectral range, including both the visible and infrared regions of the electromagnetic spectrum. The sensor relies on hafnium (IV) oxide and a phase transition material (HfO2). Three layered versions of the proposed structure are studied; each configuration is built from alternating layers of HfO2, silica, Ge2Sb2Te5(GST), and silver. The three different arrangements have all been studied. The reflectance response of such multilayer structures is discussed in this manuscript for refractive indices ranging from 1 to 2.4. In addition, we have investigated how the varying heights of the materials affect the overall performance of the structure. Finally, we have supplied several formulae for resonating traces that may be used to calculate the sensing behaviour across a specific wavelength range and refractive index values. The corresponding equations are shown below. We have computed numerous equation traces throughout this inquiry to calculate the wavelength and refractive index values. Computational methods may be used to analyze the proposed structure, which might aid in creating biosensors for detecting a wide variety of biomolecules and biomarkers, such as saliva-cortisol, urine, glucose, cancerous and cancerous, and hemoglobin.

Numerical analysis of Phase change material and graphene-based tunable refractive index sensor for infrared frequency spectrum.

Here, we present the findings of parametric analysis into a phase transition material Ge2Sb2Te5(GST)-based, graphene-based, with a wide dynamic range in the infrared and visible electromagnetic spectrum. The suggested structure is studied in multi-layered configurations, built up with layers of GST, graphene, silicon, and silver materials. These multilayer structures' reflectance behavior has been described for refractive indices between 1.3 and 2.5. The complete design is simulated using a computational process called the finite element method. Additionally, we have investigated the impact of material heights on the structure's performance in general. We have presented several resonating tracing curves in polynomial equations to determine the sensing behavior across a specific wavelength range and refractive index values. The proposed design is also investigated at various inclined angles of incidence to ascertain its wide-angle stability. A computational study of the proposed structure can assist in the evolution of biosensors to identify a wide range of biomolecules, including malignant, hemoglobin urine, saliva-cortisol, and glucose.

Broadband and Efficient Metamaterial Absorber Design Based on Gold-MgF2-Tungsten Hybrid Structure for Solar Thermal Application.

We have presented a solar absorber design with gold-MgF2-tungsten materials. The solar absorber design is optimized with nonlinear optimization mathematical method to find and optimize geometrical parameters. The wideband absorber is made of a three-layer structure composed of tungsten, magnesium fluoride, and gold. This study analyzed the absorber's performance using numerical methods over the sun wavelength range of 0.25 µm to 3 µm. The solar AM 1.5 absorption spectrum is a benchmark against which the proposed structure's absorbing characteristics are evaluated and discussed. It is necessary to analyze the behavior of the absorber under a variety of various physical parameter conditions in order to determine the results and structural dimensions that are optimal. The nonlinear parametric optimization algorithm is applied to obtain the optimized solution. This structure can absorb more than 98% of light across the near-infrared and visible light spectrums. In addition, the structure has a high absorption efficiency for the far range of the infrared spectrum and the THz range. The absorber that has been presented is versatile enough to be used in a variety of solar applications, both narrowband and broadband. The design of the solar cell that has been presented will be of assistance in designing a solar cell that has high efficiency. The proposed optimized design with optimized parameters will help design solar thermal absorbers.

5G Technology in Healthcare and Wearable Devices: A Review.

Wearable devices with 5G technology are currently more ingrained in our daily lives, and they will now be a part of our bodies too. The requirement for personal health monitoring and preventive disease is increasing due to the predictable dramatic increase in the number of aging people. Technologies with 5G in wearables and healthcare can intensely reduce the cost of diagnosing and preventing diseases and saving patient lives. This paper reviewed the benefits of 5G technologies, which are implemented in healthcare and wearable devices such as patient health monitoring using 5G, continuous monitoring of chronic diseases using 5G, management of preventing infectious diseases using 5G, robotic surgery using 5G, and 5G with future of wearables. It has the potential to have a direct effect on clinical decision making. This technology could improve patient rehabilitation outside of hospitals and monitor human physical activity continuously. This paper draws the conclusion that the widespread adoption of 5G technology by healthcare systems enables sick people to access specialists who would be unavailable and receive correct care more conveniently.

Employment of Self-Adaptive Bayesian Neural Network for Systematic Antenna Design: Improving Wireless Networks Functionalities.

The performance of wireless networks is related to the optimized structure of the antenna. Therefore, in this paper, a Machine Learning (ML)-assisted new methodology named Self-Adaptive Bayesian Neural Network (SABNN) is proposed, aiming to optimize the antenna pattern for next-generation wireless networks. In addition, the statistical analysis for the presented SABNN is evaluated in this paper and compared with the current Gaussian Process (GP). The training cost and convergence speed are also discussed in this paper. In the final stage, the proposed model's measured results are demonstrated, showing that the system has optimized outcomes with less calculation time.

Design and Fabrication of Compact, Multiband, High Gain, High Isolation, Metamaterial-Based MIMO Antennas for Wireless Communication Systems.

We proposed a novel approach based on a complementary split-ring resonator metamaterial in a two-port MIMO antenna, giving high gain, multiband results with miniature size. We have also analyzed a circular disk metasurface design. The designs are also defected using ground structure by reducing the width of the ground plane to 8 mm and etching all other parts of the ground plane. The electric length of the proposed design is 0.5λ × 0.35λ × 0.02λ. The design results are also investigated for a different variation of complementary split-ring resonator ring sizes. The inner and outer ring diameters are varied to find the optimized solution for enhanced output performance parameters. Good isolation is also achieved for both bands. The gain and directivity results are also presented. The results are compared for isolation, gain, structure size, and the number of ports. The compact, multiband, high gain and high isolation design can apply to WiMAX, WLAN, and satellite communication applications.

Fault-Level Grading of Photovoltaic Cells Employing Lightweight Deep Learning Models.

The deployment of photovoltaic (PV) cells as a renewable energy resource has been boosted recently, which enhanced the need to develop an automatic and swift fault detection system for PV cells. Prior to isolation for repair or replacement, it is critical to judge the level of the fault that occurred in the PV cell. The aim of this research study is the fault-level grading of PV cells employing deep neural network models. The experiment is carried out using a publically available dataset of 2,624 electroluminescence images of PV cells, which are labeled with four distinct defect probabilities defined as the defect levels. The deep architectures of the classical artificial neural networks are developed while employing hand-crafted texture features extracted from the EL image data. Moreover, optimized architectures of the convolutional neural network are developed with a specific emphasis on lightweight models for real-time processing. The experiments are performed for two-way binary classification and multiclass classification. For the first binary categorization, the proposed CNN model outperformed the state-of-the-art solution with a margin of 1.3% in accuracy with a significant 50% less computational complexity. In the second binary classification task, the CPU-based proposed model outperformed the GPU-based solution with a margin of 0.9% accuracy with an 8× lighter architecture. Finally, the multiclass categorization of PV cells is performed and the state-of-the-art results with 83.5% accuracy are achieved. The proposed models offer a lightweight, efficient, and computationally cheaper CPU-based solution for the real-time fault-level categorization of PV cells.

A Novel Multi-Task Learning Network Based on Melanoma Segmentation and Classification with Skin Lesion Images.

Melanoma is known worldwide as a malignant tumor and the fastest-growing skin cancer type. It is a very life-threatening disease with a high mortality rate. Automatic melanoma detection improves the early detection of the disease and the survival rate. In accordance with this purpose, we presented a multi-task learning approach based on melanoma recognition with dermoscopy images. Firstly, an effective pre-processing approach based on max pooling, contrast, and shape filters is used to eliminate hair details and to perform image enhancement operations. Next, the lesion region was segmented with a VGGNet model-based FCN Layer architecture using enhanced images. Later, a cropping process was performed for the detected lesions. Then, the cropped images were converted to the input size of the classifier model using the very deep super-resolution neural network approach, and the decrease in image resolution was minimized. Finally, a deep learning network approach based on pre-trained convolutional neural networks was developed for melanoma classification. We used the International Skin Imaging Collaboration, a publicly available dermoscopic skin lesion dataset in experimental studies. While the performance measures of accuracy, specificity, precision, and sensitivity, obtained for segmentation of the lesion region, were produced at rates of 96.99%, 92.53%, 97.65%, and 98.41%, respectively, the performance measures achieved rates for classification of 97.73%, 99.83%, 99.83%, and 95.67%, respectively.

Design and Fabrication of a Low-Cost, Multiband and High Gain Square Tooth-Enabled Metamaterial Superstrate Microstrip Patch Antenna.

The manuscript represents a novel square tooth-enabled superstrate metamaterial loaded microstrip patch antenna for the multiple frequency band operation. The proposed tooth-based metamaterial antenna provides better gain and directivity. Four antenna structures are numerically investigated for the different geometry of the patch and tooth. These proposed structures are simulated, fabricated, measured, and compared for the frequency range of 3 GHz to 9 GHz. The electrical equivalent model of the split-ring resonator is also analyzed in the manuscript. The comparative analysis of all of the proposed structures has been carried out, in terms of several bands, reflectance response, VSWR, gain and bandwidth. The results are compared with previously published works. The effects are simulated using a high-frequency structure simulator tool with the finite element method. The measured and fabricated results are compared for verification purposes. The proposed structure provides seven bands of operation and 8.57 dB of gain. It is observed that the proposed design offers the multiple frequency band operation with a good gain. The proposed tooth-based metamaterial antenna suits applications, such as the surveillance radar, satellite communication, weather monitoring and many other wireless devices.

SARS-CoV-2 detecting rapid metasurface-based sensor.

We have proposed a novel approach to detect COVID-19 by detecting the ethyl butanoate which high volume ratio is present in the exhaled breath of a COVID-19 infected person. We have employed a refractive index sensor (RIS) with the help of a metasurface-based slotted T-shape perfect absorber that can detect ethyl butanoate present in exhaled breath of COVID-19 infected person with high sensitivity and in-process SARS-CoV-2. The optimized structure of the sensor is obtained by varying several structure parameters including structure length and thickness, slotted T-shape resonator length, width, and thickness. Sensor's performance is evaluated based on numerous factors comprising of sensitivity, Q factor, detection limit, a figure of merit (FOM), detection accuracy, and other performance defining parameters. The proposed slotted T-shape RIS achieved the largest sensitivity of 2500 nm/RIU, Q factor of 131.06, a FOM of 131.58 RIU-1, detection limit of 0.0224 RIU.