Loss Values Research Articles

THE X-BAND MICROWAVE ABSORPTION CHARACTERISTICS OF POROUS ACTIVATED CARBON FROM NATURAL RESOURCES

Porous activated carbon (PAC) from bamboo, sisal, and coconut coir fibres with two carbonization steps were prepared and the microwave absorbing characteristics in the frequency range of 8 GHz to 12 GHz were investigated. The PAC based on bamboo, sisal and coconut coir had BET surface areas of 354.79, 141.91, and 25.70 m2/g, respectively. The return loss of -27.3, -25.6 and -16.4 dB was achieved for PAC from bamboo, sisal, and coconut fiber at 10.46, 11.08 and 11.00 GHz, respectively. The microwave absorption of more than 99% for porous activated carbon of bamboo and sisal, and more than 90% for porous activated carbon of coconut coir fiber, is indicated by these return loss values. It is shown by these results that biomass resources can be considered a promising lightweight, cost-effective, and eco-friendly microwave absorber material.

Evolution and modeling of texture changes and drying kinetics of bamboo shoots under high-humidity air-impingement blanching.

This study investigated the effect of hot water blanching (HWB), high-humidity air-impingement blanching (HHAIB), different HHAIB blanching times (2, 4, 6, 8, and 10min), and different HHAIB blanching temperatures (80, 85, 90, and 95°C) on texture quality, lignin content, weight loss, color, microstructure, and drying kinetics of bamboo shoots. After HWB treatment, the lignin content of bamboo shoots was apparently lower than that of HHAIB and the samples obtained the highest weight loss value of 6.13%. Both the texture values (brittleness and chewiness) and lignin content of bamboo shoots exhibited an overall downward trend as the HHAIB blanching time and blanching temperature increased. Specifically, the lignin content of bamboo shoots decreased from 5.59% to 4.58% with an increase in HHAIB blanching time from 2 to 10min and dropped from 5.48% to 4.63% as HHAIB blanching temperature increased from 80 to 85°C, respectively. The lignin content was proved to be positively correlated (p<0.05) with texture attributes (brittleness and chewiness). A second polynomial model was obtained for fitting the variation kinetics of lignin content during thermal processing. Reducing the HHAIB blanching time and blanching temperature would obtain a lower weight loss and a better color performance (ΔE and L*). Additionally, microstructure observation revealed that the distribution density of microchannels initially increased and then decreased with the extension of blanching time, while it continuously became firmer as HHAIB blanching temperature increased. Overall, the optimal processing parameters were achieved under the HHAIB blanching temperature of 85°C for 6min, ensuring a high-quality performance of bamboo shoot products.

Microstructural, dielectric, electrical, electromagnetic, and magnetic property enhancements in GdIG /TrIG/ Mn0.2Co0.3Zn0.5Fe2O4 ferrites composites for electronic devices application

Gadolinium garnet ferrite (GdIG) and terbium garnet ferrite (TrIG), known for their favourable magnetic and dielectric characteristics, were combined with doped zinc spinel ferrite (GdIG)x-(TrIG)y/Mn0.2Co0.3Zn0.5Fe2O4(1-x-y) (at x=1 y=0, x=0 y=1, x=y=0.5, x=y=0.25, x=y=0) to achieve improved permittivity, permeability and magnetic properties with reduced magneto-dielectric losses. Our study details the synthesis process and the resulting enhancements in structural, magnetic, and dielectric properties of the prepared samples. Analysis of the X-ray diffraction (XRD) patterns confirmed the presence of a crystalline structure characterized by both cubic spinel and cubic garnet phases in the composites. The microstructures of the composites were analysed with field emission scanning electron microscopy (FESEM), revealing the variation in a grain size from 0.11 μm to 0.96 μm at x =y=0.5. A thorough link between the crystal structure and XRD spectra, transmission electron microscope (TEM), and selected area electron diffraction (SAED) patterns have all been investigated in order to enhance the characterisation of the samples. At 1KHz, the composites exhibit highest electrical resistivity values of 5.9×106 Ωm and 2.6×106 Ωm. With the incorporation of spinel ferrites in garnet ferrite composite (x=y=0.25) the highest value of dielectric constant (885.2) and low value of dielectric loss (0.07) at 100 KHz has been obtained. Permeability values, derived from permittivity data, showed an increase in real permeability values of from 1.4×1012 to 9.2×1017 for x=y=0.5 to x=y=0.25 composite. Vibrating sample magnetometer (VSM) further confirm that the composite x=y=0.25 has highest magnetic saturation (148.8 emu/g), coercivity (502 Oe) and microwave operating frequency (33.6 GHz). The observed high dielectric constant, low loss values, switching field distribution and good magnetic properties suggest the potential suitability of these samples for various electronic devices like: high frequency devices, antennas, switching devices and magnetic recording devices.

A Novel Approach to Identifying Hibernating Myocardium Using Radiomics-Based Machine Learning.

Background To assess the feasibility of a machine learning (ML) approach using radiomics features of perfusion defects on rest myocardial perfusion imaging (MPI) to detect the presence of hibernating myocardium. Methodology Data of patients who underwent 99mTc-sestamibi MPI and 18F-FDG PET/CT for myocardial viability assessment were retrieved. Rest MPI data were processed on ECToolbox, and polar maps were saved using theNFile PMap tool. The reference standard for defining hibernating myocardium was the presence of mismatched perfusion-metabolism defect with impaired myocardial contractility at rest. Perfusion defects on the polar maps were delineated with regions of interest (ROIs) after spatial resampling and intensity discretization. Replicable random sampling allocated 80% (257) of the perfusion defects of the patients from January 2017 to September 2022 to the training set and the remaining 20% (64) to the validation set. An independent dataset of perfusion defects from 29 consecutive patients from October 2022 to January 2023 was used as the testing set for model evaluation. One hundred ten first and second-order texture features were extracted for each ROI. After feature normalization and imputation, 14 best-ranked features were selected using a multistep feature selection process including the Logistic Regression and Fast Correlation-Based Filter. Thirteen supervised ML algorithms were trained with stratified five-fold cross-validation on the training set and validated on the validation set. The ML algorithms with a Log Loss of <0.688 and <0.672 in the cross-validation and validation steps were evaluated on the testing set. Performance matrices of the algorithms assessed included area under the curve (AUC), classification accuracy (CA), F1 score, precision, recall, and specificity. To provide transparency and interpretability, SHapley Additive exPlanations (SHAP) values were assessed and depicted as beeswarm plots. Results Two hundred thirty-nine patients (214 males; mean age 56 ± 11 years) were enrolled in the study. There were 371 perfusion defects (321 in the training and validation sets; 50 in the testing set). Based on the reference standard, 168 perfusion defects had hibernating myocardium (139 in the training and validation sets; 29 in the testing set). On cross-validation, six ML algorithms with Log Loss <0.688 had AUC >0.800. On validation, 10 ML algorithms had a Log Loss value <0.672, among which six had AUC >0.800. On model evaluation of the selected models on the unseen testing set, nine ML models had AUC >0.800 with Gradient Boosting Random Forest (xgboost) [GB RF (xgboost)] achieving the highest AUC of 0.860 and could detect the presence of hibernating myocardium in 21/29 (72.4%) perfusion defects with a precision of 87.5% (21/24), specificity 85.7% (18/21), CA 78.0% (39/50) and F1 Score 0.792. Four models depicted a clear pattern of model interpretability based on the beeswarm SHAP plots. These were GB RF (xgboost), GB (scikit-learn), GB (xgboost), and Random Forest. Conclusion Our study demonstrates the potential of ML in detecting hibernating myocardium using radiomics features extracted from perfusion defects on rest MPI images. This proof-of-concept underscores the notion that radiomics features capture nuanced information beyond what is perceptible to the human eye, offering promising avenues for improved myocardial viability assessment.

Path loss modelling of mmwave outdoor propagation for 5G mobile systems at 28, 38, 60, and 73 GHz in four Nigerian cities

Millimetre-waves (mmWaves), a critical part of 5G, have not been extensively studied in the sub-Saharan tropical environment. This study was conducted to model the outdoor propagation path loss of mmWaves in four Nigerian cities at 28, 38, 60, and 73 GHz for 5G mobile systems: Abuja, Lagos, Ibadan, and Port Harcourt. The study utilised simulation data from a Composite Raytracing-Image-Method propagation model in MATLAB 2023a with OpenStreetMap 3D building maps to formulate the Close-In free-space Reference Distance (CI), Floating Intercept (FI), and Alpha–Beta-Gamma (ABG) large-scale path loss models. This model considered the specific atmospheric conditions, terrain, building materials and structures, and geographical layouts of each site. The study found that the path loss exponent ranged from 2.712 to 3.819 in line-of-sight scenarios, with shadow fading standard deviation (σCI) ranging from 11.778 to 37.199. In non-line-of-sight scenarios, the path loss exponent ranged from 3.375 to 5.033, with σCI ranging from 12.441 to 44.181 across the four frequencies studied. The ABG model consistently provided the most accurate predictions compared to CI and FI, particularly the mean absolute error and root mean square error values. However, performance varied across cities, frequencies, and scenarios, with Port Harcourt exhibiting the highest path loss values across all frequencies and scenarios, followed by Lagos. Furthermore, the omnidirectional large-scale path loss increases marginally as the frequency increases, except at 60 GHz, which had a higher path loss per distance than 73 GHz. Finally, the findings showed that the propagation characteristics of mmWaves for 5G networks in sub-Saharan tropical environments, such as Nigeria, exhibit significant variability based on factors such as atmospheric conditions, terrain, building materials, and geographical layouts. The formulated path loss models can be used to predict the coverage area and signal quality of millimetre-wave communication systems at these frequencies and locations.

PERBANDINGAN OPTIMIZER, BATCH SIZE DAN EPOCH PADA METODE CONVOLUTION NEURAL NETWORK

Buffalo meat and beef are two types of red meat that are widely consumed by the public. The demand for meat increases every year. However, not all types of meat can be eaten by Indonesians, such as pork, so the price of pork in Indonesia is lower than the price of beef and buffalo. In general, the texture and colour of pork, beef and buffalo are almost the same. In the introduction of meat, it is only done directly from the colour, texture, and fibre of the type of meat. However, meat circulating in the community is often mixed between beef, buffalo meat and pork. Distinguishing beef, buffalo and pork must first recognise the characteristics of each type of meat, because there are limitations to the human sense of sight in distinguishing between them. In the use of technology with the help of digital images to determine the most optimal optimizer, batch size and epoch in meat classification, using the Convolutional Neural Network (CNN) method with NasNetmobil Architecture. The data set used is 3000 images divided into three classes, with a division of 2400 training data images, 300 testing data images, 300 validation data images. The results showed that the Adam optimiser, batch size 62 and epoch 20 produced an accuracy of 99.00% and a loss value of 0.0243. Keywords: Convolutional Neural Network, Buffalo and Beef Classification,

Unveiling the structural, optical, electrical, and ferromagnetic properties of Ca2+ doped mixed spinel ferrites for switching field high-frequency device applications

In this paper, the calcium-doped nickel-zinc nano-ferrites [Ni0.5Zn0.5CaxFe2-xO4; x = 0.00, 0.10, and 0.30] were prepared using the chemical co-precipitation synthesis route and studied for switching field high-frequency device applications. The structural analysis has been completed by analyzing X-ray diffraction (XRD) patterns. The Rietveld refined XRD patterns confirmed the formation of cubic spinel structure of Ca2+ substituted nickel-zinc ferrites. The detection of metal-oxygen bonds present at A and B lattice sites has been unveiled by Fourier transform infrared (FTIR) spectroscopy. The morphological studies obtained through FESEM (Field emission scanning electron microscopy) analysis showed a reduction in the particle size from 70 nm to 53 nm when the concentration of Ca2+ ions in Ni-Zn ferrites was increased. Energy dispersive spectra (EDS) confirmed the presence of elements present in the prepared composition. The structure of a cubic spinel-shaped unit cell has been verified from three active prominent Raman modes (A1g, A2g, and T2g). Diffuse-reflectance spectroscopy (DRS) exhibits the increment in the bandgap values (from 1.55 eV to 1.63 eV) which helps fabricate highly efficient photovoltaic devices. The ferroelectric measurements yielded a rise in polarization values from 1.461 μC/cm2 to 18.228 μC/cm2 for 10 % Ca2+ ion substitution. The tangent loss values declined from 24 to 3 in Ni-Zn ferrites upon substituting Ca2+ ions. The Vibrating sample Magnetometer (VSM) technique found the increment in the saturation magnetization (Ms) values from 34.724 emu/g to 54.662 emu/g on substituting up to 30 % Ca2+ ions in Ni-Zn ferrites. These obtained results support the material in switching field distribution for high-frequency applications. The results exhibited that the prepared samples can be applicable for switching devices, filters, and microwave absorption devices. The results revealed the maximum frequency between 12 and 18 GHz which is useful for Ku band absorption.

Predictor Variables of Intraoperative Blood Loss during Cleft Palate Surgery

Study design: Cross-sectional study Objectives: To determine the predictor variables associated with blood loss during cleft palate surgery. Method: This was carried out for 12 months. Pre-operative records of each participant were taken including the age, sex, BMI, haematocrit, haemoglobin concentration, the length of the cleft defect and the width. Blood loss was determined using colorimetric method of measurement. The blood loss was calculated using the appropriate formula. Multiple regression analysis was done to determine the predictors of increased blood loss. Statistical analysis was carried out with IBM SPSS version 23.0 (2015) with statistical significance assessed at a p-value of ≤ 0.05, and a 95% confidence interval. Result: A total of 39 participants were recruited for this study, with a median age of 24 (IQR: 21–48) months. The mean length of the defects was 32.1±2.6 mm while the mean duration of surgery was 118.1±38.1 mm. The median value of the intra-operative blood loss was 40.2(IQR: 26.7–60.5). The duration of surgery and the age of the patient were the only statistically significant variables in regression analysis (p&lt;0.0001). Conclusion: Predictor variables of increased intra-operative blood loss were the duration of surgery and the age of the patient.

Development of a Web-based Tomato Plant Disease Detection and Diagnosis System using Transfer Learning Techniques

A significant obstacle to agricultural productivity that jeopardizes the availability of food is crop diseases and farmer livelihoods by reducing crop yields. Traditional visual assessment methods for disease diagnosis are effective but complex, often requiring expert observers. Recent advancements in deep learning indicate the potential for increasing accuracy and automating disease identification. Developing accessible diagnostic tools, such as web applications leveraging CNNs, can provide farmers with efficient and accurate disease identification, especially in regions with limited access to advanced diagnostic technologies. The main goal is to develop a productive system that can recognize tomato plant diseases. The model was trained on a collection of images of healthy and damaged tomato leaves from PlantVillage using transfer learning techniques. The images from the dataset were cleansed by resizing them from 256 × 256 to 224 × 224 to match the dimensions used in pre-trained models using min-max normalization. An evaluation of VGG16, VGG19, and DenseNet121 models based on performance accuracy and loss value for 7 categories of tomatoes guided the selection of the most effective model for practical application. VGG16 achieved 84.54% accuracy, VGG19 achieved 84.62%, and DenseNet121 achieved 98.28%, making DenseNet121 the chosen model due to its highest performance accuracy. The web application development based on the DenseNet121 architecture was integrated using the Django web framework, which is built on Python. This enables real-time disease diagnosis for uploaded images of tomato leaves. The proposed system allows early detection and diagnosis of tomato plant diseases, helping to mitigate crop losses. This supports sustainable farming practices and increases agricultural productivity.

A CNN based model for heart disease detection

Cardiovascular diseases (CVDs) pose a formidable global health challenge, claiming millions of lives annually. Despite advancements in healthcare, heart disease remains a leading cause of mortality, especially in developing nations. Early detection of cardiac abnormalities through predictive models is crucial for effective intervention. This research leverages machine learning (ML) and artificial intelligence (AI), focusing on deep learning, to enhance diagnostic capabilities. Unlike previous studies, this work introduced caffeine as a potential risk factor often overlooked in datasets. The study utilized Magnetic Resonance Imaging (MRI) datasets from Enugu State University Teaching Hospital and Kaggle, comprising 90,500 samples, with specific attention to high caffeine intake cases. Data preprocessing involved resizing, normalization, color adjustments, and augmentation to optimize model training. A Convolutional Neural Network (CNN) architecture with four convolutional layers was employed for classification. The CNN model achieved a remarkable accuracy of 94% and low loss values, and demonstrated proficiency in categorizing heart MRI data. Ten-fold cross-validation reaffirmed the model's high success rate with an average accuracy of 94.13% and minimal loss function. Comparative analysis showcased the effectiveness of the developed CNN model, outperforming several existing models in heart disease classification.

Multi-heterogeneous interfaces boost dielectric polarization in PBA-derived Co/MnO@NC ternary composites for electromagnetic wave absorption

The elaborate construction of multi-component composites has been deemed as a promising strategy to enhance dielectric polarization response capability in the preparation of highly efficient microwave absorbers. However, the rational design and integration of homogeneous composites with diverse components continues to pose a great challenge. Herein, we propose a straightforward self-assembly-carbonization strategy for fabricating Co/MnO@NC ternary composites derived from CoMn-Prussian Blue Analogous precursors, featuring enriched heterogeneous interfaces and balanced magneto-electric coupling synergy. The ternary composites effectively introduce diverse dissipation mechanisms, including interfacial polarization behavior originated from the constructed heterogeneous interfaces, dipole polarization relaxation triggered by atomic defects, and optimized magnetic loss ability from well-dispersed metallic Co species. Benefiting from these advantages, the Co/MnO@NC composites demonstrate superior electromagnetic wave absorption performances, with a minimum reflection loss value of −61.37 dB at the thickness of 3.5 mm and effective frequency absorption bandwidth of 6.32 GHz, covering the full Ku-band. Furthermore, power loss density and radar cross-section simulations validate that the Co/MnO@NC ternary composites possess exceptional microwave signal attenuation abilities, with a maximum radar cross-section reduction value of up to 27.98 dBm2 at 0°. Such outstanding absorption properties exceed those of most currently reported ternary composites and exhibit significant potential to replace conventional ferromagnetic-based absorbers. This work offers a straightforward strategy to fabricate ternary composites with excellent electromagnetic wave attenuation properties and sheds novel insights into the dissipation mechanisms.

An intelligent bone age assessment model incorporating multilayer superimposed texture enhancement and the China-05 attention mechanism

In the process of intelligent bone age assessment for Chinese ethnicity, generalized convolutional network models are not well targeted in extracting specific features in medical skeletal images and lack specificity in training and predicting skeletal developmental features in different ethnicities. This study aims to propose a hybrid improved deep residual network model, ZH05-DL-ResNet50, focusing on intelligent bone age assessment for Chinese ethnicity. In the process of building the ZH05-DL-ResNet50 model. First, multiple overlapping texture enhancement layers are introduced through combinatorial optimization, which can better characterize the global features of hand bone radiographs while using less texture information, reducing the interference of redundant information and freeing up computational power; second, the China-05′s spatial focusing mechanism is designed so that the model can intelligently focus on the region of interest, efficiently locate and automatically learn key image information; Finally, the model can be used for intelligent bone age assessment of Chinese ethnicity by constructing a 50-layer residual depth network, the superposition enhancement layer and the focusing mechanism are fused to form the ZH05-DL-ResNet50 model, which mitigates the problem of gradient disappearance and explosion caused by the increase of network depth, and reduces the information loss and depletion of the multi-layer texture superposition features in the focus region of interest. The training was performed using the Chinese ethnographic dataset provided and created by Tsinghua Changgeng Hospital, where 10 % of the radiographs were used as the test set and the rest as the training and validation sets. The overall performance of the models was estimated by comparing the average accuracy and loss values of different models, and the overall performance between model training and model design was evaluated using the data distribution (Distribution) and histogram of bias weight distribution (Histogram). The results showed that the average accuracy of the bone age estimation model was 98.1 % and the average error on the test set was 0.312 years. Evaluation of the model visualization and accuracy comparison showed that the model performed well and was more appropriate and accurate than other bone age estimation models. Therefore, the first intelligent bone age assessment model for Chinese ethnicity, ZH05-DL-ResNet50, was created, which differs from the untargeted nature of other intelligent bone age assessment models, and is used to train and predict hand bone radiographs more appropriately and accurately for Chinese ethnicity.

The Environmental Footprint of Available Food Waste in Young Households: A Diary Case Study of Schleswig-Holstein (Germany)

As households contribute significantly to food waste, it can be assumed that they bear considerable responsibility for the environmental footprint of it. In Germany, household food waste comprises over half of all food loss and waste, with a notable share attributable to young people. To explore their environmental footprint, data from fifty young households in Schleswig-Holstein, northern Germany, is analyzed using the Food Loss and Waste Value Calculator with an integrated life cycle assessment. We evaluate the environmental footprint of animal and plant food waste across five categories: climate change, water scarcity footprint, soil quality index, phosphorus and nitrogen eutrophication. Surprisingly, animal food waste, though representing only 18% of the total volume of all available food waste in our study, exhibits a more substantial impact in all categories except water scarcity. Specifically, animal food waste is found to be an important factor in soil degradation. Our results generally indicate an inverse relationship between the volume of animal-based and plant-based food waste in young households and its environmental footprint. However, the case study highlights a troubling connection between plant food waste and significant water scarcity issues in European agriculture.

Ingeniously construction of industrial carbon fiber/nickel-iron layered double hydroxide heterostructure composite for high-efficient microwave absorption in aircraft

To enhance the survivability of military aircraft in electromagnetic warfare, carbon fiber/nickel-iron layered double hydroxide (CF/NiFe-LDH) composites with heterogeneous structure were constructed starting from the raw industrial carbon fiber (CF) by electrostatic self-assembly. By reasonably adjusting the mass ratio of CF and NiFe-LDH, the voids formed by LDH arrays stacked on the fiber surface are utilized to promote reflection and scattering of electromagnetic wave (EMW), optimizing impedance matching, as well as synergize dielectric-magnetic dual loss mechanism. Moreover, interfacial polarization effect induced by the abundant heterogeneous interfaces significantly enhance the ability of EMW dissipation. The optimized CF/NiFe-LDH heterostructure composite exhibits the minimum reflection loss (RLmin) value of −52.48 dB at mere 1.77 mm thickness and an expansive maximum effective bandwidth (EABmax) of 7.29 GHz at 2.14 mm. In addition, the computer simulation technology (CST) revealed that the radar scattering cross section (RCS) reduction of composites reaches up to 26.92 dBm2 at an incidence angle of 90°, demonstrating their excellent radar attenuation capability. Tremendously, the heterogeneous composites achieve an SRL1 value of 524.8, which is appreciably better than most of the EMW absorbing materials. The wondrous characteristics including lightweight, ultra-thin, high-efficient microwave absorbing ability of CF/NiFe-LDH heterostructure composites display potential application in fighter aircraft.

Chirped apodized fiber Bragg gratings inverse design via deep learning

Overcoming inverse design problems in fiber Bragg gratings (FBGs) can be challenging due to the significant nonlinearity of the problem and the intricate relationship between structural properties and optical characteristics. Here, we present a novel artificial intelligence-based approach that effectively addresses these challenges. We introduce a methodology centered on applying deep learning (DL) to estimate the reflective spectrum of FBGs. The results highlight DL’s exceptional capability in designing chirped apodized FBGs, with our model demonstrating significantly enhanced computational efficiency relative to traditional numerical simulations. Notably, our DL-based approach exhibits the remarkable ability to tackle the inverse design challenges of FBGs, thereby eliminating the reliance on trial-and-error or empirical methodologies. The predictive losses for both the forward and inverse models are impressively minimal, with low loss values of 2.2 × 10-2 and 1.6 × 10-2, respectively. The FBG configurations derived via DL are ideally suited for optical communications, heralding significant advancements in all-optical signal processing.

TRANSFORMER NETWORKS TO CLASSIFY WEEDS AND CROPS IN HIGH-RESOLUTION AERIAL IMAGES FROM NORTH-EAST SERBIA

The intricate backgrounds present in crop and field images, coupled with the minimal contrast between weed-infested areas and the background, can lead to considerable ambiguity. This, in turn, poses a significant challenge to the resilience and precision of crop identification models. Identifying and mapping weeds are pivotal stages in weed control, essential for maintaining crop health. A multitude of research efforts underscore the significance of leveraging remote sensing technologies and sophisticated machine learning algorithms to enhance weed management strategies. Deep learning techniques have demonstrated impressive effectiveness in a range of agricultural remote sensing applications, including plant classification and disease detection. High-resolution imagery was collected using a UAV equipped with a high-resolution camera, which was strategically deployed over weed, sunflower, tobacco and maize fields to collect data. The VIT models achieved commendable levels of accuracy, with test accuracies of 92.97% and 90.98% in their respective evaluations. According to the experimental results, transformers not only excel in crop classification accuracy, but also achieve higher accuracy with a smaller sample size. Swin-B16 achieved an accuracy of 91.65% on both the training and test datasets. Compared to the other two ViT models, the loss value is significantly lower by half, at 0.6450.

Regulating the phase composition and microstructure of Fe3Si/SiC nanofiber composites to enhance electromagnetic wave absorption

The rational introduction of multi-components to fabricate electromagnetic wave absorbing (EMA) materials with synergistic conductive/dielectric/magnetic losses promises lightweighting and excellent EMA performance, but it remains a challenge. In this work, multicomponent Fe3Si/SiC nanofibre composites with network structure were constructed by electrostatic spinning method and in-situ carbothermal reduction strategy. Design of microstructures and multicomponent modulation by controlling the carbothermal reduction temperature. As a result, the presence of a large number of non-homogeneous interfaces, three-dimensional (3D) conductive network structures and defect structures in Fe3Si/SiC nanofibre composites induces a combination of multiple loss mechanisms that significantly improve the EMA performance. When the filling amount of Fe3Si/SiC in the paraffin transmission matrix is 20 wt%, the maximum effective absorption bandwidth (EABmax) of the fabricated material reaches 5.84 GHz with a thin thickness of 2.02 mm. Moreover, the minimum reflection loss (RLmin) value at 10.96 GHz is as low as −67.57 dB. Meanwhile, the radar cross-section (RCS) simulation verifies that the F-4 peak RCS is reduced to −30.37 dB in the range of −60°<θ < 60°. It indicates that the Fe3Si/SiC nanofiber composites have a good radar-wave dissipation capability in practical applications. In summary, the comprehensive performance of lightweight multicomponent Fe3Si/SiC nanofiber composites can meet the new application requirements and is expected to become an emerging multifunctional wave-absorbing material suitable for harsh environments.

Microwave absorption performance of La1.5Sr0.5NiO4/SrFe12O19 composites with thin matching thickness

The global focus on electromagnetic interference and pollution is undeniable. To counter these challenges, high-performance microwave-absorbing materials (MAMs), typically composed of dielectric and magnetic components, offer effective solutions by ensuring favorable impedance matching. Leveraging these MAMs has proven beneficial across various sectors, including 5G technology, information security, energy harvesting, diminished radar cross-section, and advancements in military applications. We successfully synthesized composites of La1.5Sr0.5NiO4 (LSNO) and SrFe12O19 (SrM) composites through ball milling and heat treatment. With the escalation of SrM weight percentage in the composites, noticeable alteration in structural, morphological, and static magnetic characteristics was ensured.Moreover, the amalgamation of these components bolstered the EM properties, consequently yielding exceptional microwave absorption capabilities in the composites. The composites with 40, 60, and 80 wt% of SrM (named S4, S6, and S8) exhibited excellent microwave absorption performance with an absorption rate of over 99.9 % for a thin thickness. The S4 and S8 composites attained reflection loss (RL) values of −34.75 dB and −36.93 dB, with 2.0 and 1.6 mm thicknesses, respectively. Meanwhile, the S6 composite achieved an RL value of −44.24 dB with a thickness of 1.9 mm. These composites' outstanding microwave absorption performance can be attributed to their significant magnetic loss, remarkable dielectric loss, and synergistic effects.

Modeling of Grid Tied PV Inverter to Improve its Performance During Unbalanced Load and Unbalance Fault

Integrating solar through inverter brings about various challenges in the microgrids and the inverter itself. This paper aims to the study of problems in the operation of inverter during unbalance load and unbalance fault condition along with the possible control measures to mitigate those problems to ensure the safe and reliable operation of the inverter. A grid connected PV inverter is modeled using hysteresis band controller and implementing the MPPT of the PV system with the buck boost converter. During unbalance load and unbalance fault condition, the negative and zero sequence components of current exists. All the zero-sequence component of current is delivered by the grid. The negative sequence component of current also flows through the inverter resulting in high value of current and loss of stability. Also, the voltage across the dc link capacitor increases during fault. The high value of current flowing through the inverter and high voltage across dc link capacitor may damages the inverter and capacitor respectively. An inverter dual current controller is introduced replacing the hysteresis band control such that the negative sequence component of current flowing through the inverter is almost mitigated from 600A to 10A and positive sequence current is also reduced relatively to a tolerable value 150A from 550A. The total current flowing through the inverter is limited to 200A from 950A and voltage across dc link capacitor is limited to 700V from 1050V during LG fault at the inverter side thus ensuring safe operation of the inverter during voltage dip condition. A further study can be done on limiting the positive sequence component of current to a rated value and improving the performance while operating in islanded mode.

Using a Convolutional Neural Network for Early Infectious Disease Detection During Public Health Emergencies

Proactively detecting infectious illnesses aids in delivering superior therapy and improves preventing and managing such diseases. This work proposed a Convolutional Neural Network for early Infectious Disease Detection during Public Health Emergencies (CNN-IDD-PHE). The objective is to mitigate the significant damages that Public Health Emergencies (PHE) inflicted on individuals' well-being, everyday routines, and the whole national economy. Statistics on Tuberculosis (TB) cases in a city were gathered from July 2020 to 2022. The Structural Equation Model (SEM) is designed to ascertain the correlation between latent and observed variables by identifying the appropriate indicators and estimating the parameters. A prediction model using Convolutional Neural Network (CNN) has been developed. The strategy's efficacy is validated by assessing the loss value and accuracy of the detection model during both the training and testing phases. Hence, using CNN in Deep Learning (DL) for early warning systems performs better in predicting and alerting Public Health (PH) situations. This advancement is of great importance in enhancing the capabilities of early warning systems.