Enhancement Layer Research Articles

Optimization of BaSnO3 as a compact layer for enhancement of DSSC performance using response surface methodology/Box–Behnken design

Optimization of BaSnO3 as a compact layer for enhancement of DSSC performance using response surface methodology/Box–Behnken design

SiamHSFT: A Siamese Network-Based Tracker with Hierarchical Sparse Fusion and Transformer for UAV Tracking.

Due to high maneuverability as well as hardware limitations of Unmanned Aerial Vehicle (UAV) platforms, tracking targets in UAV views often encounter challenges such as low resolution, fast motion, and background interference, which make it difficult to strike a compatibility between performance and efficiency. Based on the Siamese network framework, this paper proposes a novel UAV tracking algorithm, SiamHSFT, aiming to achieve a balance between tracking robustness and real-time computation. Firstly, by combining CBAM attention and downward information interaction in the feature enhancement module, the provided method merges high-level and low-level feature maps to prevent the loss of information when dealing with small targets. Secondly, it focuses on both long and short spatial intervals within the affinity in the interlaced sparse attention module, thereby enhancing the utilization of global context and prioritizing crucial information in feature extraction. Lastly, the Transformer's encoder is optimized with a modulation enhancement layer, which integrates triplet attention to enhance inter-layer dependencies and improve target discrimination. Experimental results demonstrate SiamHSFT's excellent performance across diverse datasets, including UAV123, UAV20L, UAV123@10fps, and DTB70. Notably, it performs better in fast motion and dynamic blurring scenarios. Meanwhile, it maintains an average tracking speed of 126.7 fps across all datasets, meeting real-time tracking requirements.

An attention-based dual-encoding network for fire flame detection using optical remote sensing

Automatic extraction of flame area plays an important role in forest fire detection, which can accurately understand the spatial distribution and development trend of forest fire, so as to effectively realize the protection of forest resources. However, due to the instability and spread of fires, and the complexity of the background, accurate early fire detection is extremely challenging. At the same time, the image pixel proportion of the flame area in early stage is much smaller than that in the background, which causes a serious class imbalance problem. With the fast development of deep learning, some achievements have been made in flame extraction, but there are still some deficiencies in the existing networks, such as limited feature representation, poor feature capturing ability on micro objects, insufficiency processing of local features, etc. This paper proposes an attention-based dual-encoding segmentation network, abbreviated as ADE-Net, for pixelwise early fire detection. To realize strong feature representation, a dual-encoding path, consisting of semantic units and spatial units, is introduced to extract richer features, and an attention fusion module (AFM) is introduced to fully integrate spatial and semantic information and achieve effective feature aggregation. In addition, faced with the class imbalance problem, a multi-attention fusion (MAF) module is introduced to obtain more discriminating features to make the segmentation network to focus on the key pixel areas. Furthermore, a feature enhancement module, named attention-guided enhancement (AGE) module, is proposed to enrich the feature representation of local feature maps. Finally, to realize better multi-scale global feature extraction and fusion, a global context fusion (GCF) module is proposed into the bottleneck layer for multi-scale feature enhancement. Experimental results show that the proposed ADE-Net has a good early fire detection ability from remote sensing images, and it has obtained a competitive advantage compared with advanced segmentation models.

Analysis of epoxy composites reinforced with jute, banana, and coconut fibers and enhanced with Rubik's layer: Tensile, bending, and impact performance evaluation

This research paper presents a comprehensive analysis of epoxy composites fortified with natural fibers such as jute, banana, and coconut, further augmented by the incorporation of Rubik's layer, aimed at evaluating their mechanical performance in terms of tensile, bending, and impact properties. As sustainable alternatives to traditional reinforcement materials, these natural fibers offer the advantage of low environmental impact, renewability, and biodegradability. The Rubik's layer, known for its three-dimensional interlocking structure, holds promise in enhancing composite properties due to its unique geometry and material characteristics. The study involves the fabrication of composite specimens through a systematic layering process, varying the composition of natural fibers and Rubik's layer. A comprehensive experimental campaign is conducted to assess the tensile strength, bending modulus, and impact resistance of the resultant composites. The results are systematically compared against those of pristine epoxy composites to ascertain the influence of the added reinforcements and enhancement layer. The findings reveal distinctive trends in mechanical behavior based on the type and proportion of natural fibers employed. Notably, the jute-reinforced composites exhibit commendable tensile and bending properties, while banana and coconut reinforcements contribute to improved impact resistance. The introduction of the Rubik's layer further refines these properties, with discernible variations based on its placement within the composite structure. This paper offers valuable insights into the multifaceted impact of natural fiber reinforcements and Rubik's layer incorporation on epoxy composites. The systematic evaluation of mechanical attributes provides a comprehensive understanding of the synergistic effects among these constituents. As the demand for sustainable and high-performance materials escalates, this research contributes to the growing body of knowledge on composite design, catering to diverse engineering applications that prioritize mechanical excellence and ecological responsibility.

Optimizing electromechanical performance of multilayered multiwalled carbon nanotube/silicone rubber composites via filler content distribution modulation

AbstractDielectric elastomers are widely used as electroactive polymer materials due to their high energy density, high strain, and low loss. However, the practical applications are limited sometimes by their low electromechanical strain ability due to relatively low dielectric permittivity for polymers. Herein, multiwalled carbon nanotube (MWCNT) filled silicone rubber (SR) composites with a five‐layered structure are prepared with the outer two layers of neat SR while the middle three layers are MWCNT filled SR, in which the former functions as insulating layers while the latter acts as the dielectric permittivity enhancement layers. Further, by differing the MWCNT content within the middle three layers, we find that as the concentration distribution increases from 1:1:1 to 1:2:1 and 1:3:1, both Young's modulus and dielectric permittivity gradually improve while dielectric loss remains extremely low even though the total MWCNT content reaches 1.6 wt%. With the combined effects of dielectric permittivity and modulus, the composite with evenly distributed MWCNT content (1:1:1) shows the highest actuation strain under a given electric field strength. Meanwhile, the electric breakdown strength of the composite 1:1:1 is also the highest, leading ultimately to a maximum actuation strain of 10.87% at the breakdown strength of 14.6 kV/mm.

Preparation of TiO2/SnO2 Electron Transport Layer for Performance Enhancement of All-Inorganic Perovskite Solar Cells Using Electron Beam Evaporation at Low Temperature.

SnO2 has attracted much attention due to its low-temperature synthesis (ca. 140 °C), high electron mobility, and low-cost manufacturing. However, lattice mismatch and oxygen vacancies at the SnO2/CsPbI3-xBrx interface generally lead to undesirable nonradiative recombination in optoelectronic devices. The traditional TiO2 used as the electron transport layer (ETL) for all-inorganic perovskite solar cells (PSCs) requires high-temperature sintering and crystallization, which are not suitable for the promising flexible PSCs and tandem solar cells, raising concerns about surface defects and device uniformity. To address these challenges, we present a bilayer ETL consisting of a SnO2 layer using electron beam evaporation and a TiO2 layer through the hydrothermal method, resulting in an enhanced performance of the perovskite solar cell. The bilayer device exhibits an improved power conversion efficiency of 11.48% compared to the single-layer device (8.09%). The average fill factor of the bilayer electron transport layer is approximately 15% higher compared to the single-layer electron transport layer. Through a systematic investigation of the use of ETL for CsPb3-xBrx PSCs on optical and electronic properties, we demonstrate that the SnO2/TiO2 is an efficient bilayer ETL for PSCs as it significantly enhances the charge extraction capability, suppresses carrier recombination at the ETL/perovskite interface, facilitates efficient photogenerated carrier separation and transport, and provides high current density and reduced hysteresis.

Optical properties and electron characteristics of noble-metal-dielectric oxide nanostructures with covered graphene layer

A comparative study of surface plasmon resonances (SPR) and optical properties of metal/dielectric/graphene multilayer films based on high conductive Ag and Cu metals is presented. For measurements of the generation of surface plasmon polaritons under the resonant condition, we involved the total internal reflection ellipsometry and direct spectroscopic ellipsometry for determining optical properties. SPR was studied in graphene/HfO2/Ag(Cu)/Cr/substrate nano-hetero-structures which contain an additional graphene surface layer for enhancement of their sensing performance. The plasmonic performance of each hybrid nano-hetero-structure is evaluated based on quality factors and propagation length of surface plasmon polaritons. The SPR in the graphene/HfO2/Ag(Cu)/Cr/substrate hybrid nano-hetero-structures demonstrate a strong correlation with the measured macroscopic optical characteristics such as the effective real dielectric function ε1(λ) and optical conductivity σ(λ) and extracted from them effective microscopic parameters: the plasma and relaxation frequencies of free electrons ωP and γ. Our results on graphene/HfO2/Ag(Cu)/Cr/substrate hybrid nano-hetero-structures indicate that the real part of the effective dielectric function ε1(λ) and optical conductivity σ(λ) generally follows effective medium approach and the stronger SPR occurs at higher values of ε1(λSPR), and the ratio of ωP2/γ and lower ones of σ (λSPR). Going forward, it appears that graphene/HfO2/Ag(Cu)/Cr/substrate hybrid nano-hetero-structure designs are more suitable for surface plasmon biomedical sensor applications because they could provide both tunability and low optical loss due to specific electronic properties of graphene.

Priors Guided Extreme Underwater Image Compression for Machine Vision and Human Vision

A low bit-rate compression is required for underwater images due to the limited bandwidth in underwater acoustic communication, which limits performances of both machine analysis and human perception in most underwater applications. Few existing compression methods consider the unique characteristics of underwater images such as color shift and haze effect to better fulfill requirements of various applications under low bit-rates. To address this problem, we propose a novel extreme underwater image compression framework, which can provide scalability to support machine vision and human vision with the assistance of underwater priors. Specifically, the base layer is composed of a feature extractor and a generator, where global structural edges and high-level features of regions with a significant impact on machine analysis are extracted and used for reconstructing a feature-matching image for analysis purpose. Considering the negative influence of underwater imaging processes on machine vision, in this article, a feature degradation removal module guided by underwater priors is proposed to alleviate feature-level degradation via taking analysis-friendly enhanced images as auxiliary information. As for the enhancement layer aiming for human vision, the residual between the original image and the reconstruction from base layer is compressed. A feature attention block and a background light recovery block are designed utilizing features extracted from enhanced images and the underwater before further recovering the original scene with a good perception quality under low bit-rates. Experimental results demonstrate the superiority of our framework in both machine vision tasks and perception quality compared with traditional compression methods and learned-based methods.

Measurement of the Compressive Strength of Concrete Using Modeling of Deep Hybrid Forest Regression

The paper proposes a deep hybrid forest regression-based modeling method for measuring the compressive strength (CS) of concrete. Then, the reduced feature vector is used as input to train multiple subforest models (SFM), the predicted values are selected from multiple subforests via the KNN (K-nearest neighbor) method to combine them to obtain the layer regression vector (LRV), and it is combined with the reduced feature vector to obtain the improved LRV, then the output of this layer is taken; second, the regression vector (RV) of the input layer enhancement layer is used as input to obtain the output of the second layer FM, and the steps are repeated until the output of the input layer FM is complete. Finally, the output of the FM of the first layer is obtained. Several SFMs are trained and the result is obtained. The final prognosis is obtained by arithmetically averaging the forecast results of the SFMs of this layer.

Liquid Viscosity Sensor Using a Surface Acoustic Wave Device for Medical Applications Including Blood and Plasma.

Blood viscosity is the defining health indicator for hyperviscosity syndrome patients. This paper introduces an alternative approach for the real-time monitoring of blood viscosity by employing a surface-horizontal surface acoustic wave (SH-SAW) device at room temperature. A novel bi-layer waveguide is constructed on top of the SAW device. This device enables the SAW sensing of liquid droplets utilizing a bi-layer waveguide, consisting of a zinc oxide (ZnO) enhancement layer and Parlyene C, that facilitates the promotion of the surface horizontal mode. The ZnO piezoelectric thin-film layer enhanced the local particle displacement and dielectric coupling while the Parylene C layer constrained the wave mode at the interface of the piezoelectric material and polymer material. The device was tested with a liquid drop on the SAW delay-line path. Both experimental and finite element analysis results demonstrated the benefits of the bi-layer waveguide. The simulation results confirmed that the displacement field of local particles increased 9 times from 1.261 nm to 11.353 nm with the Parylene C/ZnO bi-layer waveguide structure. The device demonstrated a sensitivity of 3.57 ± 0.3125 kHz shift per centipoise enabling the potential for high precision blood viscosity monitoring.

TransVCL: Attention-Enhanced Video Copy Localization Network with Flexible Supervision

Video copy localization aims to precisely localize all the copied segments within a pair of untrimmed videos in video retrieval applications. Previous methods typically start from frame-to-frame similarity matrix generated by cosine similarity between frame-level features of the input video pair, and then detect and refine the boundaries of copied segments on similarity matrix under temporal constraints. In this paper, we propose TransVCL: an attention-enhanced video copy localization network, which is optimized directly from initial frame-level features and trained end-to-end with three main components: a customized Transformer for feature enhancement, a correlation and softmax layer for similarity matrix generation, and a temporal alignment module for copied segments localization. In contrast to previous methods demanding the handcrafted similarity matrix, TransVCL incorporates long-range temporal information between feature sequence pair using self- and cross- attention layers. With the joint design and optimization of three components, the similarity matrix can be learned to present more discriminative copied patterns, leading to significant improvements over previous methods on segment-level labeled datasets (VCSL and VCDB). Besides the state-of-the-art performance in fully supervised setting, the attention architecture facilitates TransVCL to further exploit unlabeled or simply video-level labeled data. Additional experiments of supplementing video-level labeled datasets including SVD and FIVR reveal the high flexibility of TransVCL from full supervision to semi-supervision (with or without video-level annotation). Code is publicly available at https://github.com/transvcl/TransVCL.

Comprehensive Evaluation of Marine Ship Fires Risk Based on Fuzzy Broad Learning System

Ship fires exhibit the main characteristics of a high possibility of occurrence, large load, fast spreading, high difficulty in extinguishing, and serious losses. Therefore, once a fire occurs, it will cause huge loss in terms of economic and personnel safety. Firstly, a ship fire risk evaluation indicator system was constructed based on the causes and severity of the fires. Secondly, a comprehensive evaluation method for the fuzzy broad learning system (FBLS) was proposed. The fuzzy system was used to implement feature mapping on the input data, and the extracted fuzzy features were further input into the BLS enhancement layer. A fuzzy broad learning neural network structure was constructed by combining fuzzy features, feature nodes, and enhancement nodes. The method was applied to the field of risk assessment for the first time, and is a reference for subsequent studies. Finally, the risk levels of ship fires were classified and compared with evaluation methods such as fuzzy support vector machine (FSVM) and Fuzzy BP neural network (FBPNN) to demonstrate effectiveness and accuracy. The proposed FBLS method was used to predict actual cases, and the results showed consistency with the level determined by the accident investigation report published by the Maritime Bureau Administration.

Hybrid Strategies for Efficient Intra Prediction in Spatial SHVC

With multi-layer encoding and Inter-layer prediction, Spatial Scalable High Efficiency Video Coding (SSHVC) has extremely high coding complexity. It is very crucial to speed up its coding to promote widespread and cost-effective SSHVC applications. Specifically, we first reveal that the average RD cost of Inter-layer Reference (ILR) mode is different from that of Intra mode, but they both follow the Gaussian distribution. Based on this discovery, we apply the classic Gaussian Mixture Model and Expectation Maximization to determine whether ILR mode is the best mode thus skipping Intra mode. Second, when coding units (CUs) in enhancement layer use Intra mode, it indicates very simple texture is presented. We investigate their Directional Mode (DM) distribution, and divide all DMs into three classes, and then develop different methods with respect to classes to progressively predict the best DMs. Third, by jointly considering rate distortion costs, residual coefficients and neighboring CUs, we propose to employ the Conditional Random Fields model to early terminate depth selection. Experimental results demonstrate that the proposed algorithm can significantly improve coding speed with negligible coding efficiency losses.

MAAFEU-Net: A Novel Land Use Classification Model Based on Mixed Attention Module and Adjustable Feature Enhancement Layer in Remote Sensing Images

The classification of land use information is important for land resource management. With the purpose of extracting precise spatial information, we present a novel land use classification model based on a mixed attention module and adjustable feature enhancement layer (MAAFEU-net). Our unique design, the mixed attention module, allows the model to concentrate on target-specific discriminative features and capture class-related features within different land use types. In addition, an adjustable feature enhancement layer is proposed to further enhance the classification ability of similar types. We assess the performance of this model using the publicly available GID dataset and the self-built Gwadar dataset. Six semantic segmentation deep networks are used for comparison. The experimental results show that the F1 score of MAAFEU-net is 2.16% and 2.3% higher than the next model and that MIoU is 3.15% and 3.62% higher than the next model. The results of the ablation experiments show that the mixed attention module improves the MIoU by 5.83% and the addition of the adjustable feature enhancement layer can further improve it by 5.58%. Both structures effectively improve the accuracy of the overall land use classification. The validation results show that MAAFEU-net can obtain land use classification images with high precision.

Graded-Index Active Layer for Efficiency Enhancement in Polymer Solar Cell

In this paper, narrow-bandgap polymer acceptors combining a benzotriazole (BTz)-core fused-ring segment, named the PZT series, were used with a high-absorption-efficiency polymer (PBDB) compound with branched 2-butyl octyl, linear n-octyl, and methyl to be utilized as a graded-index (GI) active layer of the polymer solar cells (PSCs) to increase the photocurrent and enhance solar efficiency compared to the existing PBDB-T:PZT and PBDB-T:PZT-γ. In addition, a two-dimensional photonic crystal (2D-PhC) structure was utilized as a light-trapping anti-reflection coating (ARC) thin film based on indium tin oxide (ITO) to reduce incident light reflection and enhance its absorption. The dimensions of the cell layers were optimized to achieve the maximum power-conversion efficiency (PCE). Furthermore, the design and simulations were conducted from a 300 nm to 1200 nm wavelength range using a finite difference time-domain (FDTD) analysis. One of the most important results expected from the study was the design of a nano solar cell at (64 µm)2 with a PCE of 25.1%, a short-circuit current density (JSC) of 27.74 mA/cm2, and an open-circuit voltage (VOC) of 0.986 V.

Material Removal Rate Prediction Based on Broad Echo State Learning System for Magnetically Driven Internal Finishing

Material removal rate (MRR) modeling is crucial for process and quality control in abrasive finishing processes. In this paper, a novel broad echo state learning system (BESLS) is developed to predict MRR in the magnetically driven internal finishing process based on the force signal. This BESLS model employs reservoirs with echo state properties to replace the enhancement layer nodes of the conventional broad learning system. Three representative BESLS architectures are designed and experiments are conducted to validate the developed models. The effect of feature-fusion approaches on prediction accuracy is investigated. Results demonstrate that the prediction error of MRR is only 6.86% for the proposed BESLS model. The model has one reservoir with variable nodes (BESLS-III) and fuses extracted force features and process parameters as input. It also shows remarkable computational efficiency with a testing time of 0.134 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\rm s$</tex-math></inline-formula> , making it a potential candidate for online process control.

Light Extraction of Near-Infrared AlGaAs-Based LED Enhanced by Nanostructured Surface Morphology

To improve the light extraction efficiency of a planar AlGaAs-based light emitting diode (LED) (Device A), three novel LEDs with nanostructured surface morphologies are prepared using a surface texturing approach. We describe the fabrication of a nanostructured light extraction enhancement layer via the annealing of an evaporated Ag layer. Thermal annealing is used to induce the restructuring of a 15–25 nm layer of electron beam evaporated Ag into “nanoparticles”, which are used as an etch mask to transfer a nanopattern into the n-AlGaAs layer. Then, the Ag is removed, and the remaining nanostructured n-AlGaAs surface improves the extraction of light from the device. The novel LEDs have three different nanostructured thicknesses, namely 15 nm (Device B), 20 nm (Device C), and 25 nm (Device D). The morphologies of the Devices B–D are analyzed by an atomic force microscope and a scanning electron microscope. Compared to the planar LED (Device A), the light output powers of the Devices B–D increases by 112.6%, 91.4%, and 63.5%, respectively. The nanopatterns can mitigate the abrupt change of the refractive indexes between the air and the semiconductor to increase the LEDs’ light extraction efficiency. The surface texturing approach can be applied to commercial high-power LEDs.

Leveraging deep learning and big data to enhance computing curriculum for industry-relevant skills: A Norwegian case study

Computer science graduates face a massive gap between industry-relevant skills and those learned at school. Industry practitioners often counter a huge challenge when moving from academics to industry, requiring a completely different set of skills and knowledge. It is essential to fill the gap between the industry's required skills and those taught at varsities. In this study, we leverage deep learning and big data to propose a framework that maps the required skills with those acquired by computing graduates. Based on the mapping, we recommend enhancing the computing curriculum to match the industry-relevant skills. Our proposed framework consists of four layers: data, embedding, mapping, and a curriculum enhancement layer. Based on the recommendations from the mapping module, we made revisions and modifications to the computing curricula. Finally, we perform a case study of the Norwegian IT jobs market, where we make recommendations for data science and software engineering-related jobs. We argue that by using our proposed methodology and analysis, a significant enhancement in the computing curriculum is possible to help increase employability, student satisfaction, and smart decision-making.

Numerical Investigation of Electron/Hole Transport Layer for Enhancement of Ecofriendly Tin-Ge Based Perovskite Solar Cell

ABSTRACT The current study examines the influence of different hole transport layers (HTL) and electron transport layers (ETL) on an environmentally friendly CsSn0.5Ge0.5I3 based perovskite solar cell. The numerical analysis of a novel heterojunction structure of FTO/WS2/CsSn0.5Ge0.5I3/Zn3P2/Pt was done using SCAPS software. Initially, a suitable HTL (i.e. Zn3P2) and ETL (WS2) were chosen after analyzing various inorganic HTL and ETL materials. The optimized thickness values of the perovskite film and HTL layer were also measured. Different physical parameters of layers were also measured, such as defect concentration, radiative recombination, energy bandgap of the absorber layer, interface defect concentration, and series and shunt resistances. These analyses revealed that optimizing these parameters improves the electrical rendition of the Tin-Ge-based perovskite solar cell. The photovoltaic cell’s energy conversion efficiency (ECE) value increased to 26.22%, current density (Jsc) to 27.182 mA/cm2, and open-circuit voltage (Voc) to 1.116 V, and fill factor (FF) to 86.40%.

In-situ growth of PPy/MnOx radical quenching layer for durability enhancement of proton exchange membrane in PEMFCs

Proton exchange membrane fuel cells (PEMFCs), which exhibit low environmental impact and high power density, have attracted considerable interest as clean and efficient energy conversion technology. However, the oxidative degradation of the proton exchange membrane (PEM) by in-situ generated peroxide and hydroxyl free radicals commonly leads to performance losses in PEMFC. To alleviate the chemical attack on PEM, we report an antioxidant approach to growing a polypyrrole/manganese dioxide (PPy/MnOx) radical quenching layer on a highly proton conductive membrane surface. The resulting PEM displays improved durability in PEMFC compared with the pristine membrane, as evidenced by at least 150 h stable discharging performance in an H2/O2 PEMFC at a current density of 200 mA cm−2 at 80 °C and a much slower open circuit voltage (OCV) decay. Moreover, the ex-situ conductivity and in-situ fuel cell test indicate that the porous radical quenching layer has a tiny impact on the fuel cell performance. The resultant H2/O2 PEMFC single cell containing the chemically stable PEM exhibits a promisingly high power density of over 900 mW cm−2 at 80 °C with 100% RH.