Ordered Network Structure Research Articles

Facile in-situ synthesis of MnO2-ITO NWs composite for electrochemical supercapacitors

MnO2 is a promising material for pseudocapacitor applications due to its high specific capacity and low cost, while MnO2 electrodes suffer from their low electrical and ionic conductivities. Herein, a facile and low-cost method is adopted to synthesize MnO2 - tin-doped indium oxide nanowires (ITO NWs) composite with highly ordered network structures for electrochemical supercapacitors. Such network structure can effectively decrease the ion diffusion and charge transport resistance in the electrode. The specific capacitance of bare ITO NWs is only 2.83 F g−1, thus the contribution of the matrix material to capacitance can be ignored, and the optimized MnO2 possesses a high specific capacitor of 508.54 F g−1 at the scan rate of 5 mV s−1. It is anticipated that the synthesized MnO2-ITO NWs composite will find wide applications in supercapacitors (SCs) and other devices in virtue of their outstanding characters of good conductivity, convenient synthesis.

Recent Advances in the Study of Wheat Protein and Other Food Components Affecting the Gluten Network and the Properties of Noodles.

Upon hydrating and mixing wheat flour, wheat protein forms a network that strongly affects the structure and physicochemical properties of dough, thus affecting the properties of noodles. Different approaches have been taken to alter the gluten network structure in order to control the dough properties. In the current review, we summarize the structure and function of wheat protein, including glutenin and gliadin, and describe food components that may affect noodle quality by interacting with wheat protein. In fact, the ratio of glutenin to gliadin is closely related to the viscosity of dough, and disulfide bonds also contribute to the gluten network formation. Meanwhile, wheat protein coexists with starch and sugar in wheat dough, and thus the nature of starch may highly influence gluten formation as well. Salts, alkali, enzymes and powdered plant food can be added during dough processing to regulate the extensional properties of wheat noodles, obtaining noodles of high quality, with improved sensory and storage properties. This review describes specific methods to reinforce the wheat protein network and provides a reference for improving noodle quality.

Co-MOFs as Emerging Pulse Modulators for Femtosecond Ultrafast Fiber Laser.

The metal organic framework (MOF) has attracted more and more attention due to its unique morphology, functional linkers, and orderly network structure. Zeolitio imidazolata frameworks (ZIFs), which are formed by bivalent transition metals (Zn, Co, etc.) and nitrogen-containing heterocyclic imidazole or purine organic ligands, are a very attractive subclass of MOFs. ZIF-67, obtained by the nucleation growth of dimethylimidazole and Co 2p, has been developed as a precursor for porous nanostructured cobalt-based metal oxides. During material preparation we add rGO because it can be used as a basic element to construct macroscopic three-dimensional carbon structural materials, which self-assemble into a 3D network structure with ZIF-67 through simple van der Waals forces or hydrogen bonds, and some samples contain specific functional groups that are added to the precursor. In this paper, we employ liquid-phase synthesis to generate rGO-ZIF-67 and calcine it at the temperature of 350 °C to obtain rGO-Co3O4. Then we fabricate rGO-Co3O4 and rGO-ZIF-67 modulators based on microfibers and test their nonlinear optical absorption in 1.5 μm range. The modulation depths of rGO-Co3O4 and rGO-ZIF-67 are measured as 10.41% and 6.61%, respectively. By using microfiber-based rGO-Co3O4 modulator, we have obtained a conventional soliton and a soliton molecule in Er3+-doped fiber lasers. The conventional soliton has a pulse width of 793.4 fs and a spectral width of 3.3 at 1558.9 nm, respectively. The obtained soliton molecule has a spectral modulation period of 1.65 nm and temporal separation of 4.94 ps at 1563.2 nm. By employing a microfiber-based rGO-ZIF-67 modulator, we obtain conventional solitons with a spectral width of 1.9 nm at the central wavelength of 1529.8 nm. Our research may expand the MOF-based materials for ultrafast photonics, blazing a new path for fiber laser, optical communications, and optoelectronics, etc.

Effects of rice bran feruloyl oligosaccharides on gel properties and microstructure of grass carp surimi

Effects of feruloyl oligosaccharides (FOs) from rice bran on the gel properties, microstructure, and sensory properties of grass crap surimi gel were investigated. The results showed that FOs decreased the whiteness of surimi gel, and improved the water-holding capacity and breaking force of surimi gel. According to the texture analysis, the hardness and chewiness of surimi gel significantly increased by adding 0.3% FOs, but had no significant effect on the springiness and cohesiveness. The changes in AFM images indicated that FOs made myofibrillar protein aggregated and uniformly distributed. The SEM micrograph revealed that the 0.3% FOs group had the most compact and ordered network structure. Additionally, sensory characteristics suggested that FOs reduced off-odor from freshwater fish and remained fish delicious taste. This study provides a new prospect for the potential commercial application of FOs as a health gel enhancer in surimi products.

Synthesis and evaluation of water-soluble fracturing fluid thickener based on hydrophobic association

• Hydrophobically associative polymers. • Cross-linked fracturing fluid has excellent performance. • The residue content is low, and the damage to the reservoir is small. A cyclic quaternary ammonium salt type hydrophobic monomer VIM-16 was synthesized by 1-vinylimidazole and 1-bromohexadecane, and the hydrophobically associative polymer PAAV was prepared with AM and AMPS. It was cross-linked with 0.3% zirconium acetylacetonate to form a viscoelastic fracturing fluid. The rheological properties of it were found to have good thickening and shear resistance properties. Using 0.2% gel breaker, the gel was completely broken. No residue, it was a low damage fracturing fluid. Scanning electron microscopy was used to observe the microscopic morphology, and the morphology after cross-linking to form the jelly showed a uniform, regular and ordered network structure.

Exposure and health: A progress update by evaluation and scientometric analysis.

Several hands are now working worldwide to reduce exposure to air pollution, especially in developing nations. Future steps should be determined and classified as possible research solutions and gaps from the massive bulk of research output. Therefore, a scientometric approach has been applied using VOSviewer to show an accurate picture and trend in the mentioned area “Air pollution exposure and health,“ and its signify issues. According to the proposed study, complete 26,859 documents were retrieved from the database (ISI Web of Science) related to air pollution exposure and health effects during 2018–2022. The mapping analysis is been conducted on the country’s collaboration, co-authorship, institutional collaboration, and co-occurrence of keywords. The data collected shows the information about published articles (upward trend) over the years. Based on the citations and publication database, countries like China and the USA play a prominent role in air pollution exposure and health-related research. The study clearly defines the 3 domains of research and 4 major themes that have been currently focused. The case studies related to pollution and its impact on climate and health, studies involving chemical characteristics and management practices, also Hazardous health effects, theme like association of air pollutants, chemical composition and characterization of aerosols, health impacts due to exposure and modelling and analytical approach have been the most researched topics in the past 5 years. The developing and developed countries might potentially change the research network and work structure in order to obtain advancement in the field of Air pollution and enhance measures on exposure and health. The following research attempts to provide insights to the researchers and health sectors by straightening out developments up to date and raveling the research gaps that are needed to be addressed regarding Air pollution health and exposure.

An Improved Apple Object Detection Method Based on Lightweight YOLOv4 in Complex Backgrounds

Convolutional neural networks have recently experienced successful development in the field of computer vision. In precision agriculture, apple picking robots use computer vision methods to detect apples in orchards. However, existing object detection algorithms often face problems such as leaf shading, complex illumination environments, and small, dense recognition targets, resulting in low apple detection rates and inaccurate localization. In view of these problems, we designed an apple detection model based on lightweight YOLOv4—called Improved YOLOv4—from the perspective of industrial application. First, to improve the detection accuracy while reducing the amount of computation, the GhostNet feature extraction network with a Coordinate Attention module is implemented in YOLOv4, and depth-wise separable convolution is introduced to reconstruct the neck and YOLO head structures. Then, a Coordinate Attention module is added to the feature pyramid network (FPN) structure in order to enhance the feature extraction ability for medium and small targets. In the last 15% of epochs in training, the mosaic data augmentation strategy is turned off in order to further improve the detection performance. Finally, a long-range target screening strategy is proposed for standardized dense planting apple orchards with dwarf rootstock, removing apples in non-target rows and improving detection performance and recognition speed. On the constructed apple data set, compared with YOLOv4, the mAP of Improved YOLOv4 was increased by 3.45% (to 95.72%). The weight size of Improved YOLOv4 is only 37.9 MB, 15.53% of that of YOLOv4, and the detection speed is improved by 5.7 FPS. Two detection methods of similar size—YOLOX-s and EfficientNetB0-YOLOv3—were compared with Improved YOLOv4. Improved YOLOv4 outperformed these two algorithms by 1.82% and 2.33% mAP, respectively, on the total test set and performed optimally under all illumination conditions. The presented results indicate that Improved YOLOv4 has excellent detection accuracy and good robustness, and the proposed long-range target screening strategy has an important reference value for solving the problem of accurate and rapid identification of various fruits in standard orchards.

Variation in Hydrogel Formation and Network Structure for Telo-, Atelo- and Methacrylated Collagens.

As the most abundant protein in the extracellular matrix, collagen has become widely studied in the fields of tissue engineering and regenerative medicine. Of the various collagen types, collagen type I is the most commonly utilised in laboratory studies. In tissues, collagen type I forms into fibrils that provide an extended fibrillar network. In tissue engineering and regenerative medicine, little emphasis has been placed on the nature of the network that is formed. Various factors could affect the network structure, including the method used to extract collagen from native tissue, since this may remove the telopeptides, and the nature and extent of any chemical modifications and crosslinking moieties. The structure of any fibril network affects cellular proliferation and differentiation, as well as the overall modulus of hydrogels. In this study, the network-forming properties of two distinct forms of collagen (telo- and atelo-collagen) and their methacrylated derivatives were compared. The presence of the telopeptides facilitated fibril formation in the unmodified samples, but this benefit was substantially reduced by subsequent methacrylation, leading to a loss in the native self-assembly potential. Furthermore, the impact of the methacrylation of the collagen, which enables rapid crosslinking and makes it suitable for use in 3D printing, was investigated. The crosslinking of the methacrylated samples (both telo- and atelo-) was seen to improve the fibril-like network compared to the non-crosslinked samples. This contrasted with the samples of methacrylated gelatin, which showed little, if any, fibrillar or ordered network structure, regardless of whether they were crosslinked.

CeO2-NiO/N,O-rich porous carbon derived from covalent-organic framework for enhanced Li-storage

Heteroatom-doped porous carbon is crucial to improve energy storage performance of transition metal oxide (TMO)/carbon nanocomposites. However, their traditional template synthesis, and chemical or thermal activation methods are cumbersome and inefficient. Crystalline covalent-organic framework (COF) has customizable structure and abundant heteroatoms. Its abundant heteroatoms and ordered network structure make it to be promising precursors to prepare TMO/carbon nanocomposites. Herein, a new N,O-rich COFDHNDA-BTH with ribbon morphology was synthesized by amine-aldehyde condensation reaction. Using COFDHNDA-BTH as precursors, CeO2-doped NiO heterostructures/N,O-rich porous carbon (CeO2-NiO/NC) nanocomposites were synthesized and successfully applied for enhanced Li-storage. The N,O-rich COFDHNDA-BTH as precursors can not only avoid the cumbersome procedures and low efficiency of traditional template method but also provide more uniformly distributed active sites to anchor CeO2-NiO and hierarchical pores. Thanks to larger lattice space provided by doping of large radius cerium for Li+ insertion/de-insertion and uniformly distributed small CeO2-NiO nanoparticles with a diameter of 18 nm, the obtained 1/5CeO2-NiO/NC exhibits excellent Li-storage performance with a capacity of 852 mAh g−1 after 500 cycles at 1000 mA g−1. The simple yet efficient strategy provides a new guide to prepare CeO2-doped TMO heterostructures/NC nanocomposites for enhanced Li-storage.

A Pruning Method for Deep Convolutional Network Based on Heat Map Generation Metrics.

With the development of deep learning, researchers design deep network structures in order to extract rich high-level semantic information. Nowadays, most popular algorithms are designed based on the complexity of visible image features. However, compared with visible image features, infrared image features are more homogeneous, and the application of deep networks is prone to extracting redundant features. Therefore, it is important to prune the network layers where redundant features are extracted. Therefore, this paper proposes a pruning method for deep convolutional network based on heat map generation metrics. The ‘network layer performance evaluation metrics’ are obtained from the number of pixel activations in the heat map. The network layer with the lowest ‘network layer performance evaluation metrics’ is pruned. To address the problem that the simultaneous deletion of multiple structures may result in incorrect pruning, the Alternating training and self-pruning strategy is proposed. Using a cyclic process of pruning each model once and retraining the pruned model to reduce the incorrect pruning of network layers. The experimental results show that proposed method in this paper improved the performance of CSPDarknet, Darknet and Resnet.

Micro-terminal regulation in nanoreactors for the construction of tantalum pentoxide single-crystal ordered networks with promoting enhanced hydrogen evolution performance

• Single-crystal ordered networks of Ta 2 O 5 was constructed by micro-terminal regulation. • Single-crystal ordered networks reduce carrier recombination rate at grain boundaries. • The SCON-Ta 2 O 5 exhibits a considerably improved photocatalytic H 2 evolution activity. The ordered macroporous structure of photocatalytic semiconductors can enable smooth mass transfer, high hydrogen release efficiency and multiple reaction site interfaces. Remote electronic communications and structural continuity are necessary to achieve these goals. The single-crystal ordered network structures are ideal candidates to meet the above requirements. However, fabricating such continuous single-crystal structures is very challenging due to the rapid formation of grain boundaries. In this study, highly ordered poly(methyl methacrylate) (PMMA) was chosen as hosts to build a nanoreactor. A micro-terminal was developed in nanoreactors to generate the suitable growth environment for single-crystal ordered networks of Ta 2 O 5 (SCON-Ta 2 O 5 ). By regulation of the nanoreactor space, the effect of mass transfer channel and carrier migration distance on the photocatalytic performance of SCON-Ta 2 O 5 was systematically investigated. A substantially improved photocatalytic hydrogen performance was realized on SCON-Ta 2 O 5 . Thus, SCON-Ta 2 O 5 has a great potential in other applications and this general synthetic strategy could extend the possibility of macroporous single-crystal growth to other functional semiconductors.

Effect of low-frequency alternating magnetic field on the rheological properties, water distribution and microstructure of low-salt pork batters

The effects of different intensities of low-frequency alternating magnetic fields (LF-AMF) modification on gel characteristics, rheology, water distribution, secondary structure and microstructure were investigated. The results showed that application of LF-AMF exhibited a significant improvement of the water-holding capacity, gel strength, color, textural properties and acceptability of low-salt pork batter gels (P < 0.05). When the LF-AMF intensity reached 0.6 mT, the low-salt pork batters had the highest WHC, L*, gel strength, hardness, springiness, gumminess and chewiness and acceptability (P < 0.05). During the temperature (sample heated from 20 to 80 °C) and frequency (0–10 Hz) sweep, the storage modulus G′ first increased and then decreased with increasing of LF-AMF intensity. Low-field nuclear magnetic resonance (LF-NMR) showed that LF-AMF at an intensity of 0.6 mT shortened the T2 relaxation time of pork batter gel and increased the proportion of immobilized water. Fourier transform infrared spectroscopy (FTIR) showed that LF-AMF treatment significantly induced an increase of β-sheet structure and reduction of α-helix content in pork batter gels (P < 0.05). Scanning electron microscopy (SEM) results suggested that LF-AMF contributed to the formation of pork batter gels with a more uniform and orderly network structure.

DEVELOPMENT OF STATISTICALLY AVERAGED MODELS OF DEFORMATION OF MATERIALS WITH RANDOM NETWORK STRUCTURE OF DIFFERENTLY ORIENTED FIBERS

The paper describes the developed statistically averaged models of deformation of materials with a random network structure of differently oriented fibers. New methods of stress-strain analysis and micromacromechanical models of material deformation in the volume of bodies made of material with a network structure taking into account structural and physical nonlinearities have been created. These models are based on the micromechanics of network structures at the level of statistical sets of their chains. The novelty of approaches, models, methods and results is the creation of theoretical foundations for the analysis of the deformation of non-traditional network materials. Nonlinear mathematical models of material deformation in the form of a chaotic network structure of one-dimensional fragments are proposed, which are constructed involving fundamentally new approaches to the description of physical and mechanical properties at the micro level of statistical sets of fiber chains and spatial homogenization of their macroproperties. Compared to traditional models, they more adequately model the features of material deformation in the form of spatial chaotic and ordered network structures, as they do not involve a number of additional non-physical hypotheses. This creates fundamentally new opportunities not only for analyzing the properties of such materials, but also when creating new ones with specified properties. Using the created methods, models and research tools, the basis for solving a number of model and applied problems has been created. The nature of deformation of non-traditional materials with a network structure of one-dimensional elements is determined. The macro-properties of these materials are established on the basis of the developed micromechanical models, variational formulations and averaging methods. Keywords: stress-strain state, network structures, contact interaction, finite element method, contact pressure, machine parts, variational formulation

Ultrathin Two-Dimensional Metal–Organic Framework Nanosheets with Activated Ligand-Cluster Units for Enhanced SERS

Ultrathin two-dimensional (2D) metal-organic framework (MOF) nanosheets (MOFNs) comprise an emerging family of attractive materials with excellent potential for use in different catalytic, electrochemical, and sensing applications owing to their striking features such as ultrathin thickness, a large surface area, and highly ordered network structures. However, to the best of our knowledge, the ligand-cluster units activated through exfoliation into the MOFNs have rarely been realized, which is indeed crucial for surface-enhanced Raman scattering (SERS) analysis. Herein, we emphasize that the activated ligand-cluster units are based on the accessible coordination sites at the exposed cluster nodes accompanied by a complete excitation of the ligand-cluster units under incident photons, which make MOFNs highly effective SERS substrates, significantly outperforming their bulk counterparts. The SERS enhancement of MOFNs is further illustrated by an efficient integration of the inherent ligand-cluster charge-transfer (LCCT) transitions in MOFNs into interfacial charge-transfer processes through an "L"-type charge-transfer (CT) pathway, as further evidenced by an ultrahigh degree (0.98) of CT contributed to the SERS enhancement. This study provides an efficient strategy of exfoliating MOFs into ultrathin nanosheets for the design of highly efficient MOF-based SERS substrates.

Effects of non‐thermal plasma treating wheat kernel on the physicochemical properties of wheat flour and the quality of fresh wet noodles

AbstractThe effects of non‐thermal plasma (NTP) on the physicochemical properties of wheat flour and the quality of fresh wet noodles (FWN) were investigated. The results showed that NTP effectively decreased the total plate count (TPC), yeast and mould count (YMC) and Bacillus spp. in wheat flour. Wet gluten contents and the stability time reached the maximum when treated for 20 s. The viscosity of starch increased significantly after treatment due to the increased of damaged starch. The contents of secondary structure were altered to some extent, which was because that the ordered network structure of gluten protein broken. Furthermore, compared with the control, texture properties of FWN were enhanced significantly at 20 s, and the darkening rate of FWN was greatly inhibited due to the low polyphenol oxidase (PPO) activity. Consequently, the most suitable treatment was 500 W for 20 s, providing a basis for the application of NTP in flour products.

Variation in Hydrogel Formation and Network Structure For Telo-, Atelo- and Methacrylated Collagens

As the most abundant protein in the extracellular matrix, collagen has become widely studied in the fields of tissue engineering and regenerative medicine. Of the various collagen types, collagen type I remains the most commonly utilised in laboratory studies. In tissues, collagen type I forms into fibrils that provide an extended fibrillar network. In tissue engineering and regenerative medicine, little emphasis has been placed on the nature of the network that is being formed. Various factors could affect the network structure, including the method used to extract collagen form the native tissue, since this may remove the telopeptides, and the nature and extent of any chemical modifications and crosslinking moieties. The structure of any fibril network impacts cellular proliferation and differentiation, as well as the overall modulus of hydrogels. In this study, the network forming properties of two distinct forms of collagen (telo- and atelo- collagen), and their methacrylated derivatives were compared. The presence of the telopeptides facilitated fibril formation for unmodified samples, but this benefit was substantially reduced by subsequent methacrylation, leading to a loss in the native self-assembly potential. Furthermore, the impact of methacrylation of the collagen which enables rapid crosslinking and makes it suitable for use in 3D printing was investigated. The crosslinking of the methacrylated samples (both telo- and atelo-) was seen to improve the fibril-like network compared to non-crosslinked samples. This contrasted with samples of methacrylated gelatin which showed little, if any, fibrillar or ordered network structure whether or not they were crosslinked.

Effects of magnetic nanometer combined with radio frequency or microwave thawing on physicochemical properties of myofibrillary protein in sea bass

This work was aimed to explore the effects of different thawing strategies on the properties of sea bass myofibrillar protein (MP) and organization structure. Results revealed that magnetic nanometer combined with radio frequency thawing (RT-Mag) and magnetic nanometer combined with microwave thawing (MT-Mag) increased the α-helical content and decreased β-sheet content, while RT-Mag had minimal effect on the secondary protein structure. Low-field nuclear magnetic resonance and SEM analysis revealed that RT-Mag and radio frequency thawing (RT) reduced the mobility and loss of immobilized and non-mobile water, had the most compact and ordered network structure. Decreases in the Tmax and enthalpies were observed in the thawing treatments expect for RT-Mag during the thawing process. The appearance of polymerized protein band of SDS-PAGE indicated that RT-Mag and MT-Mag occurred a mild oxidation. In addition, the changes of particle size indicated that MP pretreated by RT-Mag and MT-Mag had less aggregation and degradation. The UV second derivative showed that the effect of RT-Mag treatment was closer to that of FS, and the improvement effect of protein aggregation and oxidation was better. Therefore, RT-Mag of New thawing method can be used as an alternative method to improve MP performance and meat quality.

Pollen transport networks reveal highly diverse and temporally stable plant-pollinator interactions in an Appalachian floral community.

Floral visitation alone has been typically used to characterize plant–pollinator interaction networks even though it ignores differences in the quality of floral visits (e.g. transport of pollen) and thus may overestimate the number and functional importance of pollinating interactions. However, how network structural properties differ between floral visitation and pollen transport networks is not well understood. Furthermore, the strength and frequency of plant–pollinator interactions may vary across fine temporal scales (within a single season) further limiting our predictive understanding of the drivers and consequences of plant–pollinator network structure. Thus, evaluating the structure of pollen transport networks and how they change within a flowering season may help increase our predictive understanding of the ecological consequences of plant–pollinator network structure. Here we compare plant–pollinator network structure using floral visitation and pollen transport data and evaluate within-season variation in pollen transport network structure in a diverse plant–pollinator community. Our results show that pollen transport networks provide a more accurate representation of the diversity of plant–pollinator interactions in a community but that floral visitation and pollen transport networks do not differ in overall network structure. Pollen transport network structure was relatively stable throughout the flowering season despite changes in plant and pollinator species composition. Overall, our study highlights the need to improve our understanding of the drivers of plant–pollinator network structure in order to more fully understand the process that govern the assembly of these interactions in nature.

Modified graphene oxide composite aerogels for enhanced adsorption behavior to heavy metal ions

Exploiting adsorbents with high adsorption activity, good durability and low cost is still the core focus of water pollution treatment. In this study, sodium alginate (SA), graphene oxide (GO), and β-cyclodextrin (βCD) were used as raw materials to frame a composite aerogel with an orderly 3D network structure by a sol-gel and freeze-drying method. The incorporation of (graphene oxide)-β-cyclodextrin (GO-βCD) could make SA molecules have higher cohesion and create more active sites for adsorbates. The temperate ratio of GO-βCD and SA to be integrated was also discussed in this work. When GO-βCD was 4 wt% (i.e., SA/GO-βCD-4), the compress performance of the composite aerogel could be 37.97% higher than the original pure SA aerogel, and the saturated adsorption capacity for Cu2+ and Cd2+ reached up 148.49 and 174.85 mg/g. It shows that SA/GO-βCD-4 composite aerogels have excellent adsorption properties for metal ions. The test data was fitted to reveal the adsorption mechanism. The adsorption kinetics of the pseudo-second-order kinetic model and Langmuir isotherm models were identified to coincide with the adsorption behavior of the modified aerogel. Comprehensively, the synthesis of the samples could pave a new way for versatile adsorbents.

Modeling Hot-Mix asphalt dynamic modulus using deep residual neural Networks: Parametric and sensitivity analysis study

The dynamic modulus (E*) of hot-mix asphalt mixtures is one of the most tedious and time-consuming laboratory testing material properties. It requires costly, advanced equipment and skills that are not easily accessible in the majority of laboratories yet. Thus, many studies have been dedicated to developing E* predictive models. Unfortunately, it is a complex task due to the many input variables and their non-linear effect on the E*. This study applies a deep residual neural networks (DRNNs) technique for the first time to the problem to enhance the E* prediction capabilities. The proposed DRNNs architecture utilizes residual connections (i.e., shortcuts) that bypass some layers in the deep network structure in order to alleviate the problem of training with high accuracy. An intensive laboratory database is employed in the DRNNs model development considering all influential input parameters such as; mixture gradation, volumetric properties, binder characteristics, and testing conditions parameters. Moreover, a brute force enumeration is integrated in the model to reduce the number of needed input variables and identify the best combinations of them. Then, the proposed DRNNs performance, with the best combination of inputs, is evaluated using representative performance indicators and compared with the well-known E* predictive models, namely; Witczak 1-37A, Witczak 1-40D, and Hirsch models. Finally, a variance-based global sensitivity (VB-GS) analysis is conducted with the Monte Carlo simulation aid to highlight each input variable effect on the E* magnitude in real practice while removing the potential distortion of results due to the input variables correlations. Performance evaluation indicators reveal that the DRNNs model outperforms other E* prediction ones. Furthermore, VB-GS analysis shows that, among all feasible inputs, binder stiffness characteristics and testing temperature are the most significant ones.