Journal articles on the topic 'Residual Pairwise Network'
To see the other types of publications on this topic, follow the link: Residual Pairwise Network.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 17 journal articles for your research on the topic 'Residual Pairwise Network.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
He, Zhi, and Dan He. "Spatial-Adaptive Siamese Residual Network for Multi-/Hyperspectral Classification." Remote Sensing 12, no. 10 (May 20, 2020): 1640. http://dx.doi.org/10.3390/rs12101640.
Full textAbstract:
Deep learning methods have been successfully applied for multispectral and hyperspectral images classification due to their ability to extract hierarchical abstract features. However, the performance of these methods relies heavily on large-scale training samples. In this paper, we propose a three-dimensional spatial-adaptive Siamese residual network (3D-SaSiResNet) that requires fewer samples and still enhances the performance. The proposed method consists of two main steps: construction of 3D spatial-adaptive patches and Siamese residual network for multiband images classification. In the first step, the spectral dimension of the original multiband images is reduced by a stacked autoencoder and superpixels of each band are obtained by the simple linear iterative clustering (SLIC) method. Superpixels of the original multiband image can be finally generated by majority voting. Subsequently, the 3D spatial-adaptive patch of each pixel is extracted from the original multiband image by reference to the previously generated superpixels. In the second step, a Siamese network composed of two 3D residual networks is designed to extract discriminative features for classification and we train the 3D-SaSiResNet by pairwise inputting the training samples into the networks. The testing samples are then fed into the trained 3D-SaSiResNet and the learned features of the testing samples are classified by the nearest neighbor classifier. Experimental results on three multiband image datasets show the feasibility of the proposed method in enhancing classification performance even with limited training samples.
2
Li, Zhong, Yuele Lin, Arne Elofsson, and Yuhua Yao. "Protein Contact Map Prediction Based on ResNet and DenseNet." BioMed Research International 2020 (April 6, 2020): 1–12. http://dx.doi.org/10.1155/2020/7584968.
Full textAbstract:
Residue-residue contact prediction has become an increasingly important tool for modeling the three-dimensional structure of a protein when no homologous structure is available. Ultradeep residual neural network (ResNet) has become the most popular method for making contact predictions because it captures the contextual information between residues. In this paper, we propose a novel deep neural network framework for contact prediction which combines ResNet and DenseNet. This framework uses 1D ResNet to process sequential features, and besides PSSM, SS3, and solvent accessibility, we have introduced a new feature, position-specific frequency matrix (PSFM), as an input. Using ResNet’s residual module and identity mapping, it can effectively process sequential features after which the outer concatenation function is used for sequential and pairwise features. Prediction accuracy is improved following a final processing step using the dense connection of DenseNet. The prediction accuracy of the protein contact map shows that our method is more effective than other popular methods due to the new network architecture and the added feature input.
3
Domonkos, Peter, José A. Guijarro, Victor Venema, Manola Brunet, and Javier Sigró. "Efficiency of Time Series Homogenization: Method Comparison with 12 Monthly Temperature Test Datasets." Journal of Climate 34, no. 8 (April 2021): 2877–91. http://dx.doi.org/10.1175/jcli-d-20-0611.1.
Full textAbstract:
AbstractThe aim of time series homogenization is to remove nonclimatic effects, such as changes in station location, instrumentation, observation practices, and so on, from observed data. Statistical homogenization usually reduces the nonclimatic effects but does not remove them completely. In the Spanish “MULTITEST” project, the efficiencies of automatic homogenization methods were tested on large benchmark datasets of a wide range of statistical properties. In this study, test results for nine versions, based on five homogenization methods—the adapted Caussinus-Mestre algorithm for the homogenization of networks of climatic time series (ACMANT), “Climatol,” multiple analysis of series for homogenization (MASH), the pairwise homogenization algorithm (PHA), and “RHtests”—are presented and evaluated. The tests were executed with 12 synthetic/surrogate monthly temperature test datasets containing 100–500 networks with 5–40 time series in each. Residual centered root-mean-square errors and residual trend biases were calculated both for individual station series and for network mean series. The results show that a larger fraction of the nonclimatic biases can be removed from station series than from network-mean series. The largest error reduction is found for the long-term linear trends of individual time series in datasets with a high signal-to-noise ratio (SNR), where the mean residual error is only 14%–36% of the raw data error. When the SNR is low, most of the results still indicate error reductions, although with smaller ratios than for large SNR. In general, ACMANT gave the most accurate homogenization results. In the accuracy of individual time series ACMANT is closely followed by Climatol, and for the accurate calculation of mean climatic trends over large geographical regions both PHA and ACMANT are recommended.
4
Rogge, Ségolène, Ionut Schiopu, and Adrian Munteanu. "Depth Estimation for Light-Field Images Using Stereo Matching and Convolutional Neural Networks." Sensors 20, no. 21 (October 30, 2020): 6188. http://dx.doi.org/10.3390/s20216188.
Full textAbstract:
The paper presents a novel depth-estimation method for light-field (LF) images based on innovative multi-stereo matching and machine-learning techniques. In the first stage, a novel block-based stereo matching algorithm is employed to compute the initial estimation. The proposed algorithm is specifically designed to operate on any pair of sub-aperture images (SAIs) in the LF image and to compute the pair’s corresponding disparity map. For the central SAI, a disparity fusion technique is proposed to compute the initial disparity map based on all available pairwise disparities. In the second stage, a novel pixel-wise deep-learning (DL)-based method for residual error prediction is employed to further refine the disparity estimation. A novel neural network architecture is proposed based on a new structure of layers. The proposed DL-based method is employed to predict the residual error of the initial estimation and to refine the final disparity map. The experimental results demonstrate the superiority of the proposed framework and reveal that the proposed method achieves an average improvement of 15.65% in root mean squared error (RMSE), 43.62% in mean absolute error (MAE), and 5.03% in structural similarity index (SSIM) over machine-learning-based state-of-the-art methods.
5
Adewopo, Julius B., and Alexandra Felix Locher. "Network-Based Resource-Proximity Analysis of Primary Wood Processing Mills in Arkansas." Southern Journal of Applied Forestry 35, no. 3 (August 1, 2011): 109–14. http://dx.doi.org/10.1093/sjaf/35.3.109.
Full textAbstract:
Abstract Primary wood processing mills in Arkansas play a vital role in both the state and the national economy, as evidenced by Arkansas' high national ranking in lumber productivity. Log acquisition from forestlands is invariably constrained by suitability of terrain and road networks; hence, an accurate assessment of the sufficiency of timberlands in servicing mills based on the existing road network and cost-effective log-truck travel time is essential for planning for the future. Many different analyses were carried out on an ArcInfo 9.3.1 workstation to delineate cost-effective sawmill service areas (SSA), timber supply areas (TSA), agricultural lands, and the overlaps that exist between these land patches. Zonal area summation of the land patches was analyzed with a two-sample paired t-test. Results indicated that there were significant pairwise differences (P < 0.0001) in the extent of SSA and TSA, SSA and SSA within TSA, SSA without agricultural lands and SSA within TSA, agricultural lands with SSA, and agricultural lands without SSA. This study indicated that a significant portion (10%) of agricultural lands must be used for optimal stocking of the delineated cost-effective SSA. Furthermore, this study revealed the suitable areas in Arkansas where there are clusters of residual timberlands that can serve as a raw material supply base for new mills.
6
Nolte, Wietje, Rosemarie Weikard, Ronald M. Brunner, Elke Albrecht, Harald M. Hammon, Antonio Reverter, and Christa Kühn. "Identification and Annotation of Potential Function of Regulatory Antisense Long Non-Coding RNAs Related to Feed Efficiency in Bos taurus Bulls." International Journal of Molecular Sciences 21, no. 9 (May 6, 2020): 3292. http://dx.doi.org/10.3390/ijms21093292.
Full textAbstract:
Long non-coding RNAs (lncRNAs) can influence transcriptional and translational processes in mammalian cells and are associated with various developmental, physiological and phenotypic conditions. However, they remain poorly understood and annotated in livestock species. We combined phenotypic, metabolomics and liver transcriptomic data of bulls divergent for residual feed intake (RFI) and fat accretion. Based on a project-specific transcriptome annotation for the bovine reference genome ARS-UCD.1.2 and multiple-tissue total RNA sequencing data, we predicted 3590 loci to be lncRNAs. To identify lncRNAs with potential regulatory influence on phenotype and gene expression, we applied the regulatory impact factor algorithm on a functionally prioritized set of loci (n = 4666). Applying the algorithm of partial correlation and information theory, significant and independent pairwise correlations were calculated and co-expression networks were established, including plasma metabolites correlated with lncRNAs. The network hub lncRNAs were assessed for potential cis-actions and subjected to biological pathway enrichment analyses. Our results reveal a prevalence of antisense lncRNAs positively correlated with adjacent protein-coding genes and suggest their participation in mitochondrial function, acute phase response signalling, TCA-cycle, fatty acid β-oxidation and presumably gluconeogenesis. These antisense lncRNAs indicate a stabilizing function for their cis-correlated genes and a putative regulatory role in gene expression.
7
Yang, Liang, Chuan Wang, Junhua Gu, Xiaochun Cao, and Bingxin Niu. "Why Do Attributes Propagate in Graph Convolutional Neural Networks?" Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 5 (May 18, 2021): 4590–98. http://dx.doi.org/10.1609/aaai.v35i5.16588.
Full textAbstract:
Many efforts have been paid to enhance Graph Convolutional Network from the perspective of propagation under the philosophy that ``Propagation is the essence of the GCNNs". Unfortunately, its adverse effect is over-smoothing, which makes the performance dramatically drop. To prevent the over-smoothing, many variants are presented. However, the perspective of propagation can't provide an intuitive and unified interpretation to their effect on prevent over-smoothing. In this paper, we aim at providing a novel explanation to the question of "Why do attributes propagate in GCNNs?''. which not only gives the essence of the oversmoothing, but also illustrates why the GCN extensions, including multi-scale GCN and GCN with initial residual, can improve the performance. To this end, an intuitive Graph Representation Learning (GRL) framework is presented. GRL simply constrains the node representation similar with the original attribute, and encourages the connected nodes possess similar representations (pairwise constraint). Based on the proposed GRL, exiting GCN and its extensions can be proved as different numerical optimization algorithms, such as gradient descent, of our proposed GRL framework. Inspired by the superiority of conjugate gradient descent compared to common gradient descent, a novel Graph Conjugate Convolutional (GCC) network is presented to approximate the solution to GRL with fast convergence. Specifically, GCC adopts the obtained information of the last layer, which can be represented as the difference between the input and output of the last layer, as the input to the next layer. Extensive experiments demonstrate the superior performance of GCC.
8
Comba, Allegra, Andrea Baldi, Massimo Carossa, Riccardo Michelotto Tempesta, Eric Garino, Xhuliano Llubani, Davide Rozzi, Julius Mikonis, Gaetano Paolone, and Nicola Scotti. "Post-Fatigue Fracture Resistance of Lithium Disilicate and Polymer-Infiltrated Ceramic Network Indirect Restorations over Endodontically-Treated Molars with Different Preparation Designs: An In-Vitro Study." Polymers 14, no. 23 (November 23, 2022): 5084. http://dx.doi.org/10.3390/polym14235084.
Full textAbstract:
The aim of the present study was to evaluate the fatigue to cyclic and static resistance of indirect restorations with different preparation designs made either of lithium disilicate (LS) or polymer-infiltrated ceramic network (PICN). Eighty-four (n = 84) molars were chosen, endodontically treated, and prepared with standardized MOD cavities. The molars were randomly divided into 6 study groups (n = 14) taking into account the “preparation design’’ (occlusal veneer with 1.2 mm occlusal thickness; overlay with 1.6 mm occlusal thickness; adhesive crown with 2 mm occlusal thickness) and the “CAD/CAM material’’ (E-max CAD, Ivoclar vivadent; Vita Enamic, Vita). A fatigue test was conducted with a chewing simulator set at 50 N for 1,500,000 cycles. Fracture resistance was assessed using a universal testing machine with a 6 mm diameter steel sphere applied to the specimens at a constant speed of 1 mm/min. A SEM analysis before the fracture test was performed to visually analyze the tooth-restoration margins. A statistical analysis was performed with a two-way ANOVA and a post-hoc pairwise comparison was performed using the Tukey test. The two-way ANOVA test showed that both the preparation design factor (p = 0.0429) and the CAD/CAM material factor (p = 0.0002) had a significant influence on the fracture resistance of the adhesive indirect restorations. The interaction between the two variables did not show any significance (p = 0.8218). The occlusal veneer had a lower fracture resistance than the adhesive crown (p = 0.042) but not lower than the overlay preparation (p = 0.095). LS was more resistant than PICN (p = 0.002). In conclusion, in the case of endodontically treated teeth, overlay preparation seems to be a valid alternative to the traditional full crown preparation, while occlusal veneers should be avoided in restoring non-vital molars with a high loss of residual tooth structure. LS material is more resistant compared to PICN.
9
Luu, Dai Chu Nguyen, Rizvan Mamet, Carrie C. Zornosa, Joyce C. Niland, Thomas A. D'Amico, Gregory Peter Kalemkerian, Marianna Koczywas, Katherine Pisters, Michael S. Rabin, and Gregory Alan Otterson. "Retrospective analysis of the impact of age on overall survival in patients with non-small cell lung cancer." Journal of Clinical Oncology 30, no. 15_suppl (May 20, 2012): e18018-e18018. http://dx.doi.org/10.1200/jco.2012.30.15_suppl.e18018.
Full textAbstract:
e18018 Background: Clinical trials have failed to demonstrate that age is a significant prognostic indicator among patients treated for non-small cell lung cancer (NSCLC). Clinical trials do not necessarily represent real-world experience, however. We sought to analyze the impact of age on survival in patients in the National Comprehensive Cancer Network (NCCN) NSCLC Outcomes Database. Methods: We performed a retrospective analysis of 6,834 NSCLC patients from the NCCN NSCLC Database representing 8 NCCN institutions. Of this population, 4,943 patients were eligible for our analysis. Exclusion criteria included the following: alive patients with < 180 days of follow-up, patients with incomplete staging, and patients with a prior cancer diagnosis. The study population was separated into five age quintiles with equal number of patients in each group. Variables included institution, smoking status, gender, race, Charlson comorbidity score, ECOG performance status (PS), histology, stage, and receipt of resection, drug and radiation therapy. Multivariable Cox model was performed for the effect of age on survival after adjusting for the above variables. Model assumptions were evaluated via graphs and residual tests. Results: Across the five quintiles (< 54, 54-60, 61-66, 67-72 and ≥ 73) there was a trend towards lower stage and higher Charlson score with increasing quintile. In addition, there was an increased proportion of patients with squamous cancer in the older age group. In the adjusted Cox model, there was a statistically significant longer survival in each of four younger quintiles compared to the reference group of ≥ 73 years of age (p=0.01). The adjusted hazard ratio of death for patients < 54 was .82 (95% CI = .72 to .94), for patients 54-60 was .86 (95% CI = .76 to .97), for patients 61-66 was .84 (95% CI = .74 to .95), and for patients 67-72 was .84 (95% CI = .74 to .95). There were no statistically significant pairwise interactions among age, smoking status and stage. Conclusions: Even after adjusting for institution, comorbidity scores, smoking status, race, gender, ECOG PS, histology, stage and treatment, NSCLC patients who were ≥ 73 years of age had a worse survival when compared to younger age groups.
10
Gilson, M., A. Tauste Campo, X. Chen, A. Thiele, and G. Deco. "Nonparametric test for connectivity detection in multivariate autoregressive networks and application to multiunit activity data." Network Neuroscience 1, no. 4 (December 2017): 357–80. http://dx.doi.org/10.1162/netn_a_00019.
Full textAbstract:
Directed connectivity inference has become a cornerstone in neuroscience to analyze multivariate data from neuroimaging and electrophysiological techniques. Here we propose a nonparametric significance method to test the nonzero values of multivariate autoregressive model to infer interactions in recurrent networks. We use random permutations or circular shifts of the original time series to generate the null-hypothesis distributions. The underlying network model is the same as used in multivariate Granger causality, but our test relies on the autoregressive coefficients instead of error residuals. By means of numerical simulation over multiple network configurations, we show that this method achieves a good control of false positives (type 1 error) and detects existing pairwise connections more accurately than using the standard parametric test for the ratio of error residuals. In practice, our method aims to detect temporal interactions in real neuronal networks with nodes possibly exhibiting redundant activity. As a proof of concept, we apply our method to multiunit activity (MUA) recorded from Utah electrode arrays in a monkey and examine detected interactions between 25 channels. We show that during stimulus presentation our method detects a large number of interactions that cannot be solely explained by the increase in the MUA level.
11
Nagi, Anmol Sharan, Devinder Kumar, Daniel Sola, and K. Andrea Scott. "RUF: Effective Sea Ice Floe Segmentation Using End-To-End RES-UNET-CRF with Dual Loss." Remote Sensing 13, no. 13 (June 24, 2021): 2460. http://dx.doi.org/10.3390/rs13132460.
Full textAbstract:
Sea ice observations through satellite imaging have led to advancements in environmental research, ship navigation, and ice hazard forecasting in cold regions. Machine learning and, recently, deep learning techniques are being explored by various researchers to process vast amounts of Synthetic Aperture Radar (SAR) data for detecting potential hazards in navigational routes. Detection of hazards such as sea ice floes in Marginal Ice Zones (MIZs) is quite challenging as the floes are often embedded in a multiscale ice cover composed of ice filaments and eddies in addition to floes. This study proposes a segmentation model tailored for detecting ice floes in SAR images. The model exploits the advantages of both convolutional neural networks and convolutional conditional random field (Conv-CRF) in a combined manner. The residual UNET (RES-UNET) computes expressive features to generate coarse segmentation maps while the Conv-CRF exploits the spatial co-occurrence pairwise potentials along with the RES-UNET unary/segmentation maps to generate final predictions. The whole pipeline is trained end-to-end using a dual loss function. This dual loss function is composed of a weighted average of binary cross entropy and soft dice loss. The comparison of experimental results with the conventional segmentation networks such as UNET, DeepLabV3, and FCN-8 demonstrates the effectiveness of the proposed architecture.
12
Jing, Xiaoyang, and Jinbo Xu. "Improved protein model quality assessment by integrating sequential and pairwise features using deep learning." Bioinformatics, December 16, 2020. http://dx.doi.org/10.1093/bioinformatics/btaa1037.
Full textAbstract:
Abstract Motivation Accurately estimating protein model quality in the absence of experimental structure is not only important for model evaluation and selection but also useful for model refinement. Progress has been steadily made by introducing new features and algorithms (especially deep neural networks), but the accuracy of quality assessment (QA) is still not very satisfactory, especially local QA on hard protein targets. Results We propose a new single-model-based QA method ResNetQA for both local and global quality assessment. Our method predicts model quality by integrating sequential and pairwise features using a deep neural network composed of both 1D and 2D convolutional residual neural networks (ResNet). The 2D ResNet module extracts useful information from pairwise features such as model-derived distance maps, co-evolution information, and predicted distance potential from sequences. The 1D ResNet is used to predict local (global) model quality from sequential features and pooled pairwise information generated by 2D ResNet. Tested on the CASP12 and CASP13 datasets, our experimental results show that our method greatly outperforms existing state-of-the-art methods. Our ablation studies indicate that the 2D ResNet module and pairwise features play an important role in improving model quality assessment. Availability and implementation https://github.com/AndersJing/ResNetQA. Contact jinboxu@gmail.com Supplementary information Supplementary data are available at Bioinformatics online.
13
Chen, Chen, Yuxue Wang, Jin Rao, Weixiang Tang, Weiwei Wu, Yuanhai Li, Guanghong Xu, and Weiwei Zhong. "Propofol Versus Sevoflurane General Anaesthesia for Selective Impairment of Attention Networks After Gynaecological Surgery in Middle-Aged Women: A Randomised Controlled Trial." Frontiers in Psychiatry 13 (July 14, 2022). http://dx.doi.org/10.3389/fpsyt.2022.917766.
Full textAbstract:
PurposeAttention is an essential component of cognitive function that may be impaired after surgery with anaesthesia. Propofol intravenous anaesthesia and sevoflurane inhalational anaesthesia are frequently used in gynaecological surgery. However, which type of anaesthetic has fewer cognitive effects postoperatively remains unclear. We compared the differences in attention network impairment after surgery in women receiving propofol versus sevoflurane general anaesthesia.Patients and MethodsEighty-three patients with gynaecological diseases who were 40–60 years of age were involved in the study. All patients underwent elective gynaecological surgery under either total intravenous anaesthesia or sevoflurane inhalational anaesthesia, depending on randomisation. The efficiencies of the three attention networks were captured using the attention network test preoperatively and on the 1st and 5th postoperative days.ResultsBoth groups of patients showed differences in impairments on the 1st and 5th postoperative days. Pairwise comparisons indicated that the alerting and orienting networks of patients in the propofol group were impaired to a greater extent than those of patients in the sevoflurane group on the 1st postoperative day, while the executive control network was impaired to a lesser extent. On the 5th postoperative day, the alerting networks of both groups recovered to the baseline level. Patients in the propofol group still showed impairment of the orienting network, while patients in the sevoflurane group recovered to baseline. For the executive control network, patients in the sevoflurane group still exhibited more severe impairment than those in the propofol group.ConclusionIn middle-aged women, propofol impaired orienting and alerting networks more than sevoflurane, while sevoflurane showed more residual impairment of the executive control network.
14
Villegas-Morcillo, Amelia, Victoria Sanchez, and Angel M. Gomez. "FoldHSphere: deep hyperspherical embeddings for protein fold recognition." BMC Bioinformatics 22, no. 1 (October 12, 2021). http://dx.doi.org/10.1186/s12859-021-04419-7.
Full textAbstract:
Abstract Background Current state-of-the-art deep learning approaches for protein fold recognition learn protein embeddings that improve prediction performance at the fold level. However, there still exists aperformance gap at the fold level and the (relatively easier) family level, suggesting that it might be possible to learn an embedding space that better represents the protein folds. Results In this paper, we propose the FoldHSphere method to learn a better fold embedding space through a two-stage training procedure. We first obtain prototype vectors for each fold class that are maximally separated in hyperspherical space. We then train a neural network by minimizing the angular large margin cosine loss to learn protein embeddings clustered around the corresponding hyperspherical fold prototypes. Our network architectures, ResCNN-GRU and ResCNN-BGRU, process the input protein sequences by applying several residual-convolutional blocks followed by a gated recurrent unit-based recurrent layer. Evaluation results on the LINDAHL dataset indicate that the use of our hyperspherical embeddings effectively bridges the performance gap at the family and fold levels. Furthermore, our FoldHSpherePro ensemble method yields an accuracy of 81.3% at the fold level, outperforming all the state-of-the-art methods. Conclusions Our methodology is efficient in learning discriminative and fold-representative embeddings for the protein domains. The proposed hyperspherical embeddings are effective at identifying the protein fold class by pairwise comparison, even when amino acid sequence similarities are low.
15
Liu, Zhuanzhuan, Ye Xu, Yudi Li, Shihong Xu, Yiji Li, Ling Xiao, Xiaoguang Chen, Cheng He, and Kuiyang Zheng. "Transcriptome analysis of Aedes albopictus midguts infected by dengue virus identifies a gene network module highly associated with temperature." Parasites & Vectors 15, no. 1 (May 19, 2022). http://dx.doi.org/10.1186/s13071-022-05282-y.
Full textAbstract:
Abstract Background Dengue is prevalent worldwide and is transmitted by Aedes mosquitoes. Temperature is a strong driver of dengue transmission. However, little is known about the underlying mechanisms. Methods Aedes albopictus mosquitoes exposed or not exposed to dengue virus serotype 2 (DENV-2) were reared at 23 °C, 28 °C and 32 °C, and midguts and residual tissues were evaluated at 7 days after infection. RNA sequencing of midgut pools from the control group, midgut breakthrough group and midgut nonbreakthrough group at different temperatures was performed. The transcriptomic profiles were analyzed using the R package, followed by weighted gene correlation network analysis (WGCNA) and Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis to identify the important molecular mechanisms regulated by temperature. Results The midgut infection rate and midgut breakthrough rate at 28 °C and 32 °C were significantly higher than those at 23 °C, which indicates that high temperature facilitates DENV-2 breakthrough in the Ae. albopictus midgut. Transcriptome sequencing was performed to investigate the antiviral mechanism in the midgut. The midgut gene expression datasets clustered with respect to temperature, blood-feeding and midgut breakthrough. Over 1500 differentially expressed genes were identified by pairwise comparisons of midguts at different temperatures. To assess key molecules regulated by temperature, we used WGCNA, which identified 28 modules of coexpressed genes; the ME3 module correlated with temperature. KEGG analysis indicated that RNA degradation, Toll and immunodeficiency factor signaling and other pathways are regulated by temperature. Conclusions Temperature affects the infection and breakthrough of Ae. albopictus midguts invaded by DENV-2, and Ae. albopictus midgut transcriptomes change with temperature. The candidate genes and key pathways regulated by temperature provide targets for the prevention and control of dengue. Graphical abstract
16
Winter, Philip M., Christoph Burger, Sebastian Lehner, Johannes Kofler, Thomas I. Maindl, and Christoph M. Schäfer. "Residual neural networks for the prediction of planetary collision outcomes." Monthly Notices of the Royal Astronomical Society, October 14, 2022. http://dx.doi.org/10.1093/mnras/stac2933.
Full textAbstract:
Abstract Fast and accurate treatment of collisions in the context of modern N-body planet formation simulations remains a challenging task due to inherently complex collision processes. We aim to tackle this problem with machine learning (ML), in particular via residual neural networks. Our model is motivated by the underlying physical processes of the data-generating process and allows for flexible prediction of post-collision states. We demonstrate that our model outperforms commonly used collision handling methods such as perfect inelastic merging and feed-forward neural networks in both prediction accuracy and out-of-distribution generalization. Our model outperforms the current state of the art in 20/24 experiments. We provide a dataset that consists of 10164 Smooth Particle Hydrodynamics (SPH) simulations of pairwise planetary collisions. The dataset is specifically suited for ML research to improve computational aspects for collision treatment and for studying planetary collisions in general. We formulate the ML task as a multi-task regression problem, allowing simple, yet efficient training of ML models for collision treatment in an end-to-end manner. Our models can be easily integrated into existing N-body frameworks and can be used within our chosen parameter space of initial conditions, i.e. where similar-sized collisions during late-stage terrestrial planet formation typically occur.
17
Prema, Dr R., G. Manikanta, and G. Venkat. "PROTOCOL TO OPTIMIZE NETWORK LIFETIME USING WSN." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 07, no. 04 (April 14, 2023). http://dx.doi.org/10.55041/ijsrem18924.
Full textAbstract:
This paper investigates the problem of energy consumption in wireless sensor networks. Wireless sensor nodes deployed in harsh environment where the conditions change drastically suffer from sudden changes in link quality and node status. The end-to-end delay of each sensor node varies due to the variation of link quality and node status. On the other hand, the sensor nodes are supplied with limited energy and it is a great concern to extend the network lifetime. To cope with those problems, this paper proposes a novel and simple routing metric, predicted remaining deliveries (PRD), combining parameters, including the residual energy, link quality, end-to-end delay, and distance together to achieve better network performance. PRD assigns weights to individual links as well as end-to-end delay, so as to reflect the node status in the long run of the network. Large-scale simulation results demonstrate that PRD performs better than the widely used ETX metric as well as other two metrics devised recently in terms of energy consumption and end-to-end delay, while guaranteeing packet delivery ratio. Key words:- Wireless Sensor Network (WSN), EESAA, Pairwis, Clustering, Sleep, Awake.