Model Structure Research Articles

In-silico approach to characterize the structure and function of a hypothetical protein of Monkeypox virus exploring Chordopox-A20R domain-containing protein activity.

Background: Monkeypox has emerged as a noteworthy worldwide issue due to its daily escalating case count. This illness presents diverse symptoms,including skin manifestations, which have the potential to spread through contact. The transmission of this infectious agent is intricate and readily transfers between individuals.Methods: The hypothetical protein MPXV-SI-2022V502225_00135 strain of monkeypox underwent structural and functional analysis using NCBI-CD Search, Pfam, and InterProScan. Quality assessment utilized PROCHECK, QMEAN, Verify3D, and ERRAT, followed by protein-ligand docking, visualization, and a 100-nanosecond simulation on Schrodinger Maestro.Results: Different physicochemical properties were estimated, indicating a stable molecular weight (49147.14) and theoretical pI (5.62) with functional annotation tools predicting the target protein to contain the domain of Chordopox_A20R domain. In secondary structure analysis, the helix coil was found to be predominant. The three-dimensional (3D) structure of the protein was obtained using a template protein (PDB ID:6zyc.1), which became more stable after YASARA energy minimization and was validated by quality assessment tools like PROCHECK, QMEAN, Verify3D, and ERRAT. Protein-ligand docking was conducted using PyRx 9.0 software to examine the binding and interactions between a ligand and a hypothetical protein, focusing on various amino acids. The model structure, active site, and binding site were visualized using the CASTp server, FTsite, and PyMOL. A 100 nanosecond simulation was performed with ligand CID_16124688 to evaluate the efficiency of this protein.Conclusion: The analysis revealed significant binding interactions and enhanced stability, aiding in drug or vaccine design for effective antiviral treatment and patient management.

Structure tensor-based Gaussian kernel edge-adaptive depth map refinement with triangular point view in images

<span lang="EN-US">Image reconstruction is the process of restoring the image resolution. In 3D image reconstruction, the objects in different viewpoints are processed with the triangular point view (TPV) method to estimate object geometry structure for 3D model. This work proposes a depth refinement methodology in preserving the geometric structure of objects using the structure tensor method with a Gaussian filter by transforming a series of 2D input images into a 3D model. The computation of depth map errors can be found by comparing the masked area/patch with the distribution of the original image's greyscale levels using the error pixel-based patch extraction algorithm. The presence of errors in the depth estimation could seriously deteriorate the quality of the 3D effect. The depth maps were iteratively refined based on histogram bins number to improve the accuracy of initial depth maps reconstructed from rigid objects. The existing datasets such as the dataset tanks and unit (DTU) and Middlebury datasets, were used to build the model out of the object scene structure. The results of this work have demonstrated that the proposed patch analysis outperformed the existing state of the art models depth refinement methods in terms of accuracy.</span>

Exploring malaria parasite surface proteins to devise highly immunogenic multi-epitope subunit vaccine for Plasmodium falciparum

BackgroundMalaria has remained a major health concern for decades among people living in tropical and sub-tropical countries. Plasmodium falciparum is one of the critical species that cause severe malaria and is responsible for major mortality. Moreover, the parasite has generated resistance against all WHO recommended drugs and therapies. Therefore, there is an urgent need for preventive measures in the form of reliable vaccines to achieve the target of a malaria-free world. Surface proteins are the preferable choice for subunit vaccine development because they are rapidly detected and engaged by host immune cells and vaccination-induced antibodies. Additionally, abundant surface or membrane proteins may contribute to the opsonization of pathogens by vaccine-induced antibodies. ResultsIn our study, we have listed all those surface proteins from the literature that could be functionally important and essential for infection and immune evasion of the malaria parasite. Eight Plasmodium surface and membrane proteins from the pre-erythrocyte and erythrocyte stages were shortlisted. Thirty-seven epitopes (B-cell, CTL, and HTL epitopes) from these proteins were predicted using immune-informatic tools and joined with suitable peptide linkers to design a vaccine construct. A TLR-4 agonist peptide adjuvant was added at the N-terminus of the multi-epitope series, followed by the PADRE sequence and EAAAK linker. The TLR-4 receptor was docked with the construct’s anticipated model structure. The complex of vaccine and TLR-4, with the lowest energy −1514, was found to be stable under simulated physiological settings. ConclusionThis study has provided a novel multi-epitope construct that may be exploited further for the development of an efficient vaccine for malaria.

Analytical solution and spectral structure of the two-photon anisotropic Rabi-Stark model

Abstract Since the realization of the strong coupling between light and matter in experimental setups, the quantum Rabi model and its generalized models describing the interaction between the boson field and the two-level system have attracted extensive interest again. The study of anisotropic generalized Rabi models enables us to better understand the novel physical properties of the interaction between light and matter in the ultra-strong and deep-strong coupling regions. In this work, the two-photon anisotropic Rabi-Stark model (tpARSM) is analytically solved by using the Bogoliubov operator approach and the $su(1,1)$ Lie algebra. We derive the G-function, whose zeros give the regular spectrum of the system. By studying the pole structure of the G-function and the coefficients in the function, exceptional solutions, including the first-order quantum phase transition points, doubly degenerate exceptional solutions and nondegenerate exceptional solutions, are obtained. By discussing the spectral structure, we give the conditions for the first-order quantum phase transition of tpARSM. Furthermore, we find that the property that all of the lowest doubly degenerate crossing points in the two-photon Rabi-Stark model have the same energy only holds for the special case of the tpARSM in which the anisotropy parameter is equal to 1. Finally, from the perspective of first-order quantum phase transitions, concise conditions for the ground state energy level to collapse to or escape from the collapse point for the tpARSM are presented. A good understanding of the tpARSM will lay a good foundation for studying the extended two-photon systems involving multiple levels and multiple bosonic modes, and even the relevant open quantum systems.

Mechanism-based organization of neural networks to emulate systems biology and pharmacology models.

Deep learning neural networks are often described as black boxes, as it is difficult to trace model outputs back to model inputs due to a lack of clarity over the internal mechanisms. This is even true for those neural networks designed to emulate mechanistic models, which simply learn a mapping between the inputs and outputs of mechanistic models, ignoring the underlying processes. Using a mechanistic model studying the pharmacological interaction between opioids and naloxone as a proof-of-concept example, we demonstrated that by reorganizing the neural networks' layers to mimic the structure of the mechanistic model, it is possible to achieve better training rates and prediction accuracy relative to the previously proposed black-box neural networks, while maintaining the interpretability of the mechanistic simulations. Our framework can be used to emulate mechanistic models in a large parameter space and offers an example on the utility of increasing the interpretability of deep learning networks.

Learning Media "ARASIK" in Understanding the Meaning of Nouns for SDLB Deaf Students at SLB Negeri Bogor

Deaf children experience speech and language difficulties due to hearing loss. Children with hearing loss experience delays and communication difficulties due to delays in speech and language development. The main problem in language acquisition for deaf children is that they have difficulty understanding the meaning of words. The problem is that children can read, but they do not understand what they read. The title of this article is ``The learning media "ARASIK" in understanding the meaning of nouns in SDLB Deaf students at SLB Negeri Bogor" The theoretical foundations used in this study are: (1) understanding the meaning of words, as stated by Nurbeiti Jamalus that the meaning of a word is the relationship between the sound (language) of the word spoken or written with the object concerned; (2) Augmented Realitiy learning media promoted by scientists, that AR can visualize abstract concepts for understanding and the structure of an object model allows AR as a more effective media in accordance with the objectives of learning media. This research uses a descriptive-qualitative approach, with data collection techniques through observation, interviews and documentation studies. The data analysis technique used refers to Miles and Huberman (1994) which includes three activities, namely: (1) data reduction, (2) data presentation, and (3) conclusion drawing from the application of "ARASIK" media. Based on the results of the study, it can be concluded that the "ARASIK" media can help facilitate SDLB Deaf students in understanding the meaning of nouns.

Analysis of Factors Affecting Profitability in Automotive and Component Sub-Sector Companies on the Indonesia Stock Exchange 2018 – 2022

The purpose of this study is to determine the factors that affect profitability in automotive and component sub-sector companies on the Indonesia Stock Exchange in 2018-2022. The dependent variable in this study is profitability while the independent variables in this study are liquidity, solvency and model structure. The population in this study is automotive and component sub-sector companies listed on the Indonesia Stock Exchange with a total population of 15 companies. This study uses purposive sampling technique with a sample size of 9 companies. The data used in this study are secondary data. The data analysis technique used is multiple linear regression analysis whose calculations use IBM SPSS 24 software. The results showed that liquidity, solvency and model structure had a positive and significant effect on profitability in automotive and component companies on the Indonesia Stock Exchange.

Numerical Simulation Study Considering Discontinuous Longitudinal Joints in Soft Soil under Symmetric Loading

In shield tunneling, the joint is one of the most vulnerable parts of the segmental lining. Opening of the joint reduces the overall stiffness of the ring, leading to structural damage and issues such as water leakage. Currently, the Winkler method is commonly used to calculate structural deformation, simplifying the interaction between segments and soil as radial and tangential Winkler springs. However, when introducing connection springs or reduction factors to simulate the joint stiffness of segments, the challenge lies in determining the reduction coefficient and the stiffness of the springs. Currently, the hyperstatic reflection method cannot simulate the discontinuity effect at the connection of the tunnel segments, while the state space method overlooks the nonlinear interaction between the tunnel and the soil. Therefore, this paper proposes a numerical simulation method considering the interaction between the tunnel and the soil, which is subjected to compression rather than tension, and the discontinuity of the joints between the segments. The model structure and external load are symmetrical, resulting in symmetrical calculation results. This method is based on the soft soil layers and shield tunnel structures of the Shanghai Metro, and the applicability of the model is verified through deformation calculations using three-dimensional laser scanning point clouds of sections from the Shanghai Metro Line 5. When the subgrade reaction coefficient is 5000 kN/m3, the model can effectively simulate the deformation of operational tunnels. By adjusting the bending stiffness of individual connection springs, we investigate the influence of bending stiffness reduction on the bending moment, radial displacement, and rotational displacement of the ring. The results indicate that a decrease in joint bending stiffness significantly affects the mechanical response of the ring, and the extent and degree of this influence are correlated with the joint position and the magnitude of joint bending stiffness.

Modeling Population Growth under Climate Stressors Using Age-structured Matrix Models.

Climate resilience, a focus of many recent studies, has been examined from ecological, physiological, and evolutionary perspectives. However, sampling biases towards adults, males, and certain species have made establishing the link between environmental change and population-level change problematic. Here we used data from four laboratory studies, in which we administered pre- and post-natal stressors, such as suboptimal incubation temperature, heat stress, and food restriction, to zebra finches and quantified hatching success, post-hatch survival, and reproductive success, to parameterize age-structured population dynamics models with the goal of estimating the effect of the stressors on relative population growth rates. Using the same model structure, we tested the hypothesis that early life stages influence population growth rate more than later life stages. Our models suggested that stressful events during embryonic development, such as suboptimal incubation temperatures and reduced gas exchange for the embryos, have a greater total impact on population growth than post-hatch stressors, such as heat stress and food restriction. However, among life history traits, differences in hatching success and sex ratio of offspring in response to stressors changed population growth rates more than differences in any other demographic rate estimates. These results suggest that when predicting population resilience against climate change, it is critical to account for effects of climate change on all life stages, including early stages of life, and to incorporate individuals' physiology and stress tolerance that likely influence future stress responses, reproduction, and survival.

Total cross section of the process e++e−→Σ0+Σ¯0 in the vicinity of charmonium ψ(3770) including the D -meson loop and three-gluon contributions

For the study of the structure of baryons it is necessary to investigate the production of a baryon pair in e+e− annihilation. The baryon-antibaryon pair production at the electron-positron linear collider makes it possible to investigate in detail the basic structure of the Standard Model. The creation of baryon-antibaryon pairs in electron-positron annihilation provides an increasingly powerful tool at higher c.m. energies. We present phenomenological results for Σ0Σ¯0 production in e+e− interaction at the BESIII and Colliders. In the present work, we investigate a hyperon pair produced in the reaction e+e−→Σ0Σ¯0. We calculate the total cross section of the process e+e−→Σ0Σ¯0 taking into account the contributions of the D-meson loop and three gluon loops as well as the interference of all diagrams to the Born approximation. For these contributions large relative phases are generated with respect to the pure electromagnetic mechanism. For the large momentum transferred region we obtain as a byproduct a fit of the electromagnetic form factor of the Σ hyperon. Published by the American Physical Society 2024

Decentralized Online Order Fulfillment in Omni-Channel Retailers

We consider an order fulfillment problem of an omni-channel retailer that ships online orders from its distribution center (DC) and brick-and-mortar stores. Stores use their local information, not observed by the retailer, that can lead them to accept or reject fulfillment requests of items in an online order. We investigate the problem of sequencing requests to stores and inventory rationing decisions at the DC to minimize expected costs under uncertain store acceptance behavior and when items are indistinguishable in terms of shipping. First, under the scenario that stores are used only when the DC has insufficient inventory, we propose a Markov Decision Process formulation and analyze the performance of myopic policies that are preferable because of their interpretability. We show that the performance rate of a myopic approach that orders stores by cost only depends on the number of items in an order, which is small in practice. We also determine conditions for the range of acceptance probabilities for the myopic policy to be optimal for small-sized orders. Using optimality conditions for a special case of the problem, we develop an adaptive variant of the myopic policy, and propose a new degree-based strategy that balances shipping costs and acceptance probabilities. Numerical testing suggests that the best-performing sequencing policy is within 1% of optimality on average. Moreover, using two years of data from a large omni-channel retailer in North America, we observe that adaptive policies, albeit more complex, are beneficial in reducing costs and split deliveries if acceptance rates can be estimated accurately. Second, we determine when the retailer should ship from stores or ration the inventory at the DC. We show that for single-item orders, the optimal policy has a threshold structure, where, remarkably, the highest priority region is also subject to rationing. We then consider the novel multi-unit-single-item rationing problem, and leverage the structure of the single-unit model to develop a heuristic. We numerically establish the efficacy of rationing models and our heuristic.

The Impact of Industrial Characteristics on the Capital Structure

This paper investigates the relationship between industrial characteristics and capital structure. The author selected three industries with totally different features as examples and discussed how their particular industrial functions can make a significant difference in leverage ratio. These industrial characteristics are only related to the industry, such as business model and financial statements structure, regardless of the firms size, business performance, and profitability, which can be calculated and measured. Using high-tech-driven, asset-intensive, and labor-intensive industries as samples to analyze their influences on firms leverage ratios. Their industry characteristics can explain the difference in leverage, as asset-intensive companies have the highest average level of debt while labor-intensive has the lowest one. However, the industries cannot account for all diversities in capital structure, and there are difficulties in discovering the perfect capital structure that can meet all requirements and has the lowest cost under current literature. It is necessary to ascertain all factors that will affect the capital structure and evaluate the extent of their influences in future research.

Simultaneous Determination of Four Catechins in Black Tea via NIR Spectroscopy and Feature Wavelength Selection: A Novel Approach

As a non-destructive, fast, and cost-effective technique, near-infrared (NIR) spectroscopy has been widely used to determine the content of bioactive components in tea. However, due to the similar chemical structures of various catechins in black tea, the NIR spectra of black tea severely overlap in certain bands, causing nonlinear relationships and reducing analytical accuracy. In addition, the number of NIR spectral wavelengths is much larger than that of the modeled samples, and the small-sample learning problem is rather typical. These issues make the use of NIRS to simultaneously determine black tea catechins challenging. To address the above problems, this study innovatively proposed a wavelength selection algorithm based on feature interval combination sensitivity segmentation (FIC-SS). This algorithm extracts wavelengths at both coarse-grained and fine-grained levels, achieving higher accuracy and stability in feature wavelength extraction. On this basis, the study built four simultaneous prediction models for catechins based on extreme learning machines (ELMs), utilizing their powerful nonlinear learning ability and simple model structure to achieve simultaneous and accurate prediction of catechins. The experimental results showed that for the full spectrum, the ELM model has better prediction performance than the partial least squares model for epicatechin (EC), epicatechin gallate (ECG), epigallocatechin (EGC), and epigallocatechin gallate (EGCG). For the feature wavelengths, our proposed FIC-SS-ELM model enjoys higher prediction performance than ELM models based on other wavelength selection algorithms; it can simultaneously and accurately predict the content of EC (Rp2 = 0.91, RMSEP = 0.019), ECG (Rp2 = 0.96, RMSEP = 0.11), EGC (Rp2 = 0.97, RMSEP = 0.15), and EGCG (Rp2 = 0.97, RMSEP = 0.35) in black tea. The results of this study provide a new method for the quantitative determination of the bioactive components of black tea.

#2898 Exposure response model describing hematologic changes with chronic treatment of CKD anemia with vadadustat

Abstract Background and Aims Vadadustat (VADA) is an oral hypoxia-inducible factor (HIF) prolyl hydroxylase inhibitor, a class of drugs that stabilize HIF and stimulate endogenous erythropoietin production, increasing iron mobilization and red blood cell production. VADA is approved in 36 countries globally and is indicated in the European Union for the treatment of symptomatic anaemia associated with chronic kidney disease (CKD) in adults on chronic maintenance dialysis and is an alternative to treatment with erythropoiesis-stimulating agents (ESAs). The aim of this work was to develop a predictive, semi-mechanistic model to understand the effects of VADA and erythropoiesis-stimulating agents (ESAs) on hemoglobin response and to evaluate the impact of intrinsic and extrinsic patient characteristics on that response for non-dialysis dependent (NDD) and dialysis-dependent (DD) patient populations. Method A predictive semi-mechanistic pharmacokinetic/pharmacodynamic (PK/PD) model for VADA and ESA treatment was developed using nonlinear mixed effects methods. The model describes changes in reticulocyte count (RETICs), mature erythrocytes (RBCs) and hemoglobin (Hb) as a function of drug exposure and subject-specific characteristics. The dataset was based on data from 7 Phase 1 to Phase 3 studies (Table 1; N = 894 for VADA; N = 560 for ESA modeling) in healthy volunteers and subjects with NDD- or DD-CKD who were either ESA-naïve or ESA experienced but not receiving treatment at screening. Prior population PK modeling of VADA provided estimated drug exposures for VADA-treated subjects, while dose normalized to standard units (IU/kg/wk) was used as the exposure metric for subjects on ESA. Each of these exposure metrics could vary with time, as the dose was adjusted according to observed Hb response. This work evaluated alternative model structures, as well as covariate effects affecting Hb individual response. Results A predictive semi-mechanistic pharmacokinetic/pharmacodynamic (PK/PD) model for VADA and ESA treatment was developed using nonlinear mixed effects methods. The model describes changes in reticulocyte count (RETICs), mature erythrocytes (RBCs) and hemoglobin (Hb) as a function of drug exposure and subject-specific characteristics. The dataset was based on data from 7 Phase 1 to Phase 3 studies (Table 1; N = 894 for VADA; N = 560 for ESA modeling) in healthy volunteers and subjects with NDD- or DD-CKD who were either ESA-naïve or ESA experienced but not receiving treatment at screening. Prior population PK modeling of VADA provided estimated drug exposures for VADA-treated subjects, while dose normalized to standard units (IU/kg/wk) was used as the exposure metric for subjects on ESA. Each of these exposure metrics could vary with time, as the dose was adjusted according to observed Hb response. This work evaluated alternative model structures, as well as covariate effects affecting Hb individual response. A similar model structure was found to describe early changes in RETICs and longer-term changes in Hb for both VADA and ESAs. In each case, the magnitude of response increases with increased drug exposure up to a maximum value (Emax), and the Emax values were similar between VADA and ESAs. Subject intrinsic predictors of response included eGFR, subject age, BMI, and serum albumin, while extrinsic factors affecting response included geographic region, limits on acceptable Hb values (which also differ by geographic region) and the presence of previous ESA treatment. Interestingly, Hb responses were also correlated with changes in serum hepcidin, a key regulator of iron homeostasis, following both VADA and ESA treatment. Differences between the response to VADA and ESA were also described, including differences in temporal changes in RETICs and Hb. Conclusion This model showed an exposure-response relationship between VADA or ESA treatment and changes in RETICs and Hb for ESA naïve or ESA-experienced CKD subjects. The model will be used to inform dosage recommendations for VADA based on patient characteristics.

Citrus Pest Identification Model Based on Improved ShuffleNet

To address the current issues of complex structures and low accuracies in citrus pest identification models, a lightweight pest identification model was proposed. First, a parameterized linear rectification function was introduced to avoid neuronal death. Second, the model’s attention to pest characteristics was improved by incorporating an improved mixed attention mechanism. Subsequently, the network structure of the original model was adjusted to reduce architectural complexity. Finally, by employing transfer learning, an SCHNet model was developed. The experimental results indicated that the proposed model achieved an accuracy rate of 94.48% with a compact size of 3.84 MB. Compared to the original ShuffleNet V2 network, the SCHNet model showed a 3.12% accuracy improvement while reducing the model size by 22.7%. The SCHNet model exhibited an excellent classification performance for citrus pest identification, enabling the accurate identification of citrus pests.

Intelligent identification of rice leaf disease based on YOLO V5-EFFICIENT

Rice leaf diseases is a threat to sustainable rice production. Many methods via machine learning or artificial intelligence have been used to detect rice leaf diseases. However, these methods may fail to identify them or are slow in recognition. Therefore, a YOLO V5-IMPROVEMENT model is proposed to overcome these issues. Based on YOLO V5s, the improved K-Means is utilized to generate initial anchor sizes which more fit in the experimental dataset. An attention mechanism is added to let the feature extraction layer focus more on Regions of Interest (ROIs). This improvement enhances the efficiency of feature information extraction from objects of different scales. To better detect occluded targets, the loss function is improved to strengthen the regression effect of the predicted bounding boxes. Main branch gradient flow BottleNeck Block module of Cross Stage Partial (CSP) in the Neck is improved. The Spatial Pyramid Pooling-Fast (SPPF) is replaced with the S-SPPF module to optimize the model structure and ensure real-time performance. An ablation study was conducted and the proposed YOLO V5-EFFICIENT was compared with other models. Compared with YOLO V5, the detection result of YOLO V5-EFFICIENT increased by 9.90% in terms of mAP. Compared with other approaches, the improved model can better balance detection accuracy and speed when recognizing fine features of lesions. And it is capable of handling rice leaf disease detection tasks with numerous small targets. It is suggested that YOLO V5-EFFICIENT is of high accuracy and robustness.

Use of Risk Management to Support Business Sustainability in the Automotive Industry

Today’s companies operate in a dynamic, constantly evolving, and highly competitive environment. The globalization of markets has significantly changed the economy, where companies operate within increasingly complex supply chains. The ever-increasing expectations of customers and company stakeholders, as well as the need to incorporate a comprehensive approach to the life cycle of manufactured products in corporate strategies, expose companies to a whole range of risks. The research was based on the need of organizations operating in the (automotive) industry to manage the dynamics of the business environment. This was accomplished using an appropriate model that, through its universality, would help to ensure the effective risk management in a holistic approach, protecting their performance and meeting the needs of the relevant stakeholders. The main idea of the research was to create and implement a dynamic model of risk management in the environment of a production organization based on the use of available methods such as SWOT, PESTLE, brainstorming, affinity diagrams, risk matrix, SIPOC diagram, risk, and the results of questionnaire surveys. The research was conducted in two directions: (1) designing the structure of the dynamic risk management model for the strategic management process; and (2) verifying the effectiveness of the proposed model in specific cases and evaluating the technical and economic benefits. To support the dynamics of the model, three basic management tools have been proposed: process review, internal audit, and management review, enriched with features that support the concept of risk-based thinking.

Robust Control of Motion in Presence of Uncertain Parameters and Control Constraints

The paper describes a novel, simple servo drive position controller, using only knowledge about the structure of the nonlinear model and the constraints met by individual components of the model. The desired behaviour of the position and velocity signals is obtained by imposing a time-varying constraint on the signal aggregating information about position and velocity tracking errors. The method allows you to determine the maximum control (servo drive current) necessary to achieve the control goal under the existing initial conditions and the selected reference trajectory. The control is constrained and consists in appropriate reaction when the trajectory approaches the barrier, the shape of which is responsible for the imposed properties of the transient and quasisteady state tracking error. In addition to the derivation of the control, a discussion of its possible variants and basic properties is presented. Control with time-varying constraints has been introduced, which allows the control objectives to be met with limited conservatism of the imposed constraints. The influence of technical factors related to actual speed and position measurements was discussed and the operation of the real drive on a laboratory stand was presented.

VoteDroid: a new ensemble voting classifier for malware detection based on fine-tuned deep learning models

AbstractIn this work, VoteDroid a novel fine-tuned deep learning models-based ensemble voting classifier has been proposed for detecting malicious behavior in Android applications. To this end, we proposed adopting the random search optimization algorithm for deciding the structure of the models used as voter classifiers in the ensemble classifier. We specified the potential components that can be used in each model and left the random search algorithm taking a decision about the structure of the model including the number of each component that should be used and its location in the structure. This optimization method has been used to build three different deep learning models namely CNN-ANN, pure CNN, and pure ANN. After selecting the best structure for each DL model, the selected three models have been trained and tested using the constructed image dataset. Afterward, we suggested hybridizing the fine-tuned three deep-learning models to form one ensemble voting classifier with two different working modes namely MMR (Malware Minority Rule) and LMR (Label Majority Rule). To our knowledge, this is the first time that an ensemble classifier has been fine-tuned and hybridized in this way for malware detection. The results showed that the proposed models were promising, where the classification accuracy exceeded 97% in all experiments.

Advances in Deep Learning Recognition of Landslides Based on Remote Sensing Images

Against the backdrop of global warming and increased rainfall, the hazards and potential risks of landslides are increasing. The rapid generation of a landslide inventory is of great significance for landslide disaster prevention and reduction. Deep learning has been widely applied in landslide identification due to its advantages in terms of its deeper model structure, high efficiency, and high accuracy. This article first provides an overview of deep learning technology and its basic principles, as well as the current status of landslide remote sensing databases. Then, classic landslide deep learning recognition models such as AlexNet, ResNet, YOLO, Mask R-CNN, U-Net, Transformer, EfficientNet, DeeplabV3+ and PSPNet were introduced, and the advantages and limitations of each model were extensively analyzed. Finally, the current constraints of deep learning in landslide identification were summarized, and the development direction of deep learning in landslide identification was analyzed. The purpose of this article is to promote the in-depth development of landslide identification research in order to provide academic references for the prevention and mitigation of landslide disasters and post-disaster rescue work. The research results indicate that deep learning methods have the characteristics of high efficiency and accuracy in automatic landslide recognition, and more attention should be paid to the development of emerging deep learning models in landslide recognition in the future.