GLORIA

GEOMAR Library Ocean Research Information Access

X

Your email was sent successfully. Check your inbox.

An error occurred while sending the email. Please try again.

Proceed reservation?

Export
Filter
  • MDPI AG  (276)
  • 1
    Online Resource
    Online Resource
    Deep Fusion Prediction Method for Nonstationary Time Series Based on Feature Augmentation and Extraction
    MDPI AG ; 2023
    In:  Applied Sciences Vol. 13, No. 8 ( 2023-04-19), p. 5088-
    Details
    In: Applied Sciences, MDPI AG, Vol. 13, No. 8 ( 2023-04-19), p. 5088-
    Abstract: Deep learning effectively identifies and predicts modes but faces performance reduction under few-shot learning conditions. In this paper, a time series prediction framework for small samples is proposed, including a data augmentation algorithm, time series trend decomposition, multi-model prediction, and error-based fusion. First, data samples are augmented by retaining and extracting time series features. Second, the expanded data are decomposed based on data trends, and then, multiple deep models are used for prediction. Third, the models’ predictive outputs are combined with an error estimate from the intersection of covariances. Finally, the method is verified using natural systems and classic small-scale simulation datasets. The results show that the proposed method can improve the prediction accuracy of small sample sets with data augmentation and multi-model fusion.
    Type of Medium: Online Resource
    ISSN: 2076-3417
    URL: Article
    DOI: 10.3390/app13085088
    Language: English
    Publisher: MDPI AG
    Publication Date: 2023
    detail.hit.zdb_id: 2704225-X
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 2
    Online Resource
    Online Resource
    Transcriptome Sequencing Reveal That Rno-Rsf1_0012 Participates in Levodopa-Induced Dyskinesia in Parkinson’s Disease Rats via Binding to Rno-mir-298-5p
    MDPI AG ; 2022
    In:  Brain Sciences Vol. 12, No. 9 ( 2022-09-07), p. 1206-
    Details
    In: Brain Sciences, MDPI AG, Vol. 12, No. 9 ( 2022-09-07), p. 1206-
    Abstract: Levodopa-induced dyskinesia (LID) is a common complication of chronic dopamine replacement therapy in the treatment of Parkinson’s disease (PD), and a noble cause of disability in advanced PD patients. Circular RNA (circRNA) is a novel type of non-coding RNA with a covalently closed-loop structure, which can regulate gene expression and participate in many biological processes. However, the biological roles of circRNAs in LID are not completely known. In the present study, we established typical LID rat models by unilateral lesions of the medial forebrain bundle and repeated levodopa therapy. High-throughput next-generation sequencing was used to screen circRNAs differentially expressed in the brain of LID and non-LID (NLID) rats, and key circRNAs were selected according to bioinformatics analyses. Regarding fold change ≥2 and p 〈 0.05 as the cutoff value, there were a total of 99 differential circRNAs, including 39 up-regulated and 60 down-regulated circRNAs between the NLID and LID groups. The expression of rno-Rsf1_0012 was significantly increased in the striatum of LID rats and competitively bound rno-mir-298-5p. The high expression of target genes PCP and TBP in LID rats also supports the conclusion that rno-Rsf1_0012 may be related to the occurrence of LID.
    Type of Medium: Online Resource
    ISSN: 2076-3425
    URL: Article
    DOI: 10.3390/brainsci12091206
    Language: English
    Publisher: MDPI AG
    Publication Date: 2022
    detail.hit.zdb_id: 2651993-8
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 3
    Online Resource
    Online Resource
    Nonstationary Time Series Prediction Based on Deep Echo State Network Tuned by Bayesian Optimization
    MDPI AG ; 2023
    In:  Mathematics Vol. 11, No. 6 ( 2023-03-20), p. 1503-
    Details
    In: Mathematics, MDPI AG, Vol. 11, No. 6 ( 2023-03-20), p. 1503-
    Abstract: The predictions from time series data can help us sense development trends and make scientific decisions in advance. The commonly used forecasting methods with backpropagation consume a lot of computational resources. The deep echo state network (DeepESN) is an advanced prediction method with a deep neural network structure and training algorithm without backpropagation. In this paper, a Bayesian optimization algorithm (BOA) is proposed to optimize DeepESN to address the problem of increasing parameter scale. Firstly, the DeepESN was studied and constructed as the basic prediction model for the time series data. Secondly, the BOA was reconstructed, based on the DeepESN, for optimal parameter searching. The algorithm is proposed within the framework of the DeepESN. Thirdly, an experiment was conducted to verify the DeepESN with a BOA within three datasets: simulation data generated from computer programs, a real humidity dataset collected from Beijing, and a power load dataset obtained from America. Compared with the models of BP (backpropagation), LSTM (long short-term memory), GRU (gated recurrent unit), and ESN (echo state network), DeepESN obtained optimal results, which were 0.0719, 18.6707, and 764.5281 using RMSE evaluation. While getting better accuracy, the BOA optimization time was only 323.4 s, 563.2 s, and 9854 s for the three datasets. It is more efficient than grid search and grey wolf optimizer.
    Type of Medium: Online Resource
    ISSN: 2227-7390
    URL: Article
    DOI: 10.3390/math11061503
    Language: English
    Publisher: MDPI AG
    Publication Date: 2023
    detail.hit.zdb_id: 2704244-3
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 4
    Online Resource
    Online Resource
    Rutaecarpine Ameliorates Murine N-Methyl-N’-Nitro-N-Nitrosoguanidine-Induced Chronic Atrophic Gastritis by Sonic Hedgehog Pathway
    MDPI AG ; 2023
    In:  Molecules Vol. 28, No. 17 ( 2023-08-28), p. 6294-
    Details
    In: Molecules, MDPI AG, Vol. 28, No. 17 ( 2023-08-28), p. 6294-
    Abstract: CAG is a burdensome and progressive disease. Numerous studies have shown the effectiveness of RUT in digestive system diseases. The therapeutic effects of RUT on MNNG-induced CAG and the potential mechanisms were probed. MNNG administration was employed to establish a CAG model. The HE and ELISA methods were applied to detect the treatment effects. WB, qRT-PCR, immunohistochemistry, TUNEL, and GES-1 cell flow cytometry approaches were employed to probe the mechanisms. The CAG model was successfully established. The ELISA and HE staining data showed that the RUT treatment effects on CAG rats were reflected by the amelioration of histological damage. The qRT-PCR and WB analyses indicated that the protective effect of RUT is related to the upregulation of the SHH pathway and downregulation of the downstream of apoptosis to improve gastric cellular survival. Our data suggest that RUT induces a gastroprotective effect by upregulating the SHH signaling pathway and stimulating anti-apoptosis downstream.
    Type of Medium: Online Resource
    ISSN: 1420-3049
    URL: Article
    DOI: 10.3390/molecules28176294
    Language: English
    Publisher: MDPI AG
    Publication Date: 2023
    detail.hit.zdb_id: 2008644-1
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 5
    Online Resource
    Online Resource
    RHΔgra17Δnpt1 Strain of Toxoplasma gondii Elicits Protective Immunity Against Acute, Chronic and Congenital Toxoplasmosis in Mice
    MDPI AG ; 2020
    In:  Microorganisms Vol. 8, No. 3 ( 2020-03-01), p. 352-
    Details
    In: Microorganisms, MDPI AG, Vol. 8, No. 3 ( 2020-03-01), p. 352-
    Abstract: In the present study, a dense granule protein 17 (gra17) and novel putative transporter (npt1) double deletion mutant of Toxoplasma gondii RH strain was engineered. The protective efficacy of vaccination using RHΔgra17Δnpt1 tachyzoites against acute, chronic, and congenital toxoplasmosis was studied in a mouse model. Immunization using RHΔgra17Δnpt1 induced a strong humoral and cellular response, as indicated by the increased levels of anti-T. gondii specific IgG, interleukin 2 (IL-2), IL-10, IL-12, and interferon-gamma (IFN-γ). Vaccinated mice were protected against a lethal challenge dose (103 tachyzoites) of wild-type homologous (RH) strain and heterologous (PYS and TgC7) strains, as well as against 100 tissue cysts or oocysts of Pru strain. Vaccination also conferred protection against chronic infection with 10 tissue cysts or oocysts of Pru strain, where the numbers of brain cysts in the vaccinated mice were significantly reduced compared to those detected in the control (unvaccinated + infected) mice. In addition, vaccination protected against congenital infection with 10 T. gondii Pru oocysts (administered orally on day 5 of gestation) as shown by the increased litter size, survival rate and the bodyweight of pups born to vaccinated dams compared to those born to unvaccinated + infected dams. The brain cyst burden of vaccinated dams was significantly lower than that of unvaccinated dams infected with oocysts. Our data show that T. gondii RHΔgra17Δnpt1 mutant strain can protect mice against acute, chronic, and congenital toxoplasmosis by balancing inflammatory response with immunogenicity.
    Type of Medium: Online Resource
    ISSN: 2076-2607
    URL: Article
    DOI: 10.3390/microorganisms8030352
    Language: English
    Publisher: MDPI AG
    Publication Date: 2020
    detail.hit.zdb_id: 2720891-6
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 6
    Online Resource
    Online Resource
    Olfactory Gene Families in Scopula subpunctaria and Candidates for Type-II Sex Pheromone Detection
    MDPI AG ; 2022
    In:  International Journal of Molecular Sciences Vol. 23, No. 24 ( 2022-12-12), p. 15775-
    Details
    In: International Journal of Molecular Sciences, MDPI AG, Vol. 23, No. 24 ( 2022-12-12), p. 15775-
    Abstract: Scopula subpunctaria, an abundant pest in tea gardens, produce type-II sex pheromone components, which are critical for its communicative and reproductive abilities; however, genes encoding the proteins involved in the detection of type-II sex pheromone components have rarely been documented in moths. In the present study, we sequenced the transcriptomes of the male and female S. subpunctaria antennae. A total of 150 candidate olfaction genes, comprising 58 odorant receptors (SsubORs), 26 ionotropic receptors (SsubIRs), 24 chemosensory proteins (SsubCSPs), 40 odorant-binding proteins (SsubOBPs), and 2 sensory neuron membrane proteins (SsubSNMPs) were identified in S. subpunctaria. Phylogenetic analysis, qPCR, and mRNA abundance analysis results suggested that SsubOR46 may be the Orco (non-traditional odorant receptor, a subfamily of ORs) of S. subpunctaria. SsubOR9, SsubOR53, and SsubOR55 belonged to the pheromone receptor (PR) clades which have a higher expression in male antennae. Interestingly, SsubOR44 was uniquely expressed in the antennae, with a higher expression in males than in females. SsubOBP25, SsubOBP27, and SsubOBP28 were clustered into the moth pheromone-binding protein (PBP) sub-family, and they were uniquely expressed in the antennae, with a higher expression in males than in females. SsubOBP19, a member of the GOBP2 group, was the most abundant OBP in the antennae. These findings indicate that these olfactory genes, comprising five candidate PRs, three candidate PBPs, and one candidate GOBP2, may be involved in type II sex pheromone detection. As well as these genes, most of the remaining SsubORs, and all of the SsubIRs, showed a considerably higher expression in the female antennae than in the male antennae. Many of these, including SsubOR40, SsubOR42, SsubOR43, and SsubIR26, were more abundant in female antennae. These olfactory and ionotropic receptors may be related to the detection of host plant volatiles. The results of this present study provide a basis for exploring the olfaction mechanisms in S. subpunctaria, with a focus on the genes involved in type II sex pheromones. The evolutionary analyses in our study provide new insights into the differentiation and evolution of lepidopteran PRs.
    Type of Medium: Online Resource
    ISSN: 1422-0067
    URL: Article
    DOI: 10.3390/ijms232415775
    Language: English
    Publisher: MDPI AG
    Publication Date: 2022
    detail.hit.zdb_id: 2019364-6
    SSG: 12
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 7
    Online Resource
    Online Resource
    Hybrid Deep Learning Predictor for Smart Agriculture Sensing Based on Empirical Mode Decomposition and Gated Recurrent Unit Group Model
    MDPI AG ; 2020
    In:  Sensors Vol. 20, No. 5 ( 2020-02-29), p. 1334-
    Details
    In: Sensors, MDPI AG, Vol. 20, No. 5 ( 2020-02-29), p. 1334-
    Abstract: Smart agricultural sensing has enabled great advantages in practical applications recently, making it one of the most important and valuable systems. For outdoor plantation farms, the prediction of climate data, such as temperature, wind speed, and humidity, enables the planning and control of agricultural production to improve the yield and quality of crops. However, it is not easy to accurately predict climate trends because the sensing data are complex, nonlinear, and contain multiple components. This study proposes a hybrid deep learning predictor, in which an empirical mode decomposition (EMD) method is used to decompose the climate data into fixed component groups with different frequency characteristics, then a gated recurrent unit (GRU) network is trained for each group as the sub-predictor, and finally the results from the GRU are added to obtain the prediction result. Experiments based on climate data from an agricultural Internet of Things (IoT) system verify the development of the proposed model. The prediction results show that the proposed predictor can obtain more accurate predictions of temperature, wind speed, and humidity data to meet the needs of precision agricultural production.
    Type of Medium: Online Resource
    ISSN: 1424-8220
    URL: Article
    DOI: 10.3390/s20051334
    Language: English
    Publisher: MDPI AG
    Publication Date: 2020
    detail.hit.zdb_id: 2052857-7
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 8
    Online Resource
    Online Resource
    Spatio-Temporal Prediction for the Monitoring-Blind Area of Industrial Atmosphere Based on the Fusion Network
    MDPI AG ; 2019
    In:  International Journal of Environmental Research and Public Health Vol. 16, No. 20 ( 2019-10-09), p. 3788-
    Details
    In: International Journal of Environmental Research and Public Health, MDPI AG, Vol. 16, No. 20 ( 2019-10-09), p. 3788-
    Abstract: The monitoring-blind area exists in the industrial park because of private interest and limited administrative power. As the atmospheric quality in the blind area impacts the environment management seriously, the prediction and inference of the blind area is explored in this paper. Firstly, the fusion network framework was designed for the solution of “Circumjacent Monitoring-Blind Area Inference”. In the fusion network, the nonlinear autoregressive network was set up for the time series prediction of circumjacent points, and the full connection layer was built for the nonlinear relation fitting of multiple points. Secondly, the physical structure and learning method was studied for the sub-elements in the fusion network. Thirdly, the spatio-temporal prediction algorithm was proposed based on the network for the blind area monitoring problem. Finally, the experiment was conducted with the practical monitoring data in an industrial park in Hebei Province, China. The results show that the solution is feasible for the blind area analysis in the view of spatial and temporal dimensions.
    Type of Medium: Online Resource
    ISSN: 1660-4601
    URL: Article
    DOI: 10.3390/ijerph16203788
    Language: English
    Publisher: MDPI AG
    Publication Date: 2019
    detail.hit.zdb_id: 2175195-X
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 9
    Online Resource
    Online Resource
    Sugar-Sweetened Beverages Intake, Abdominal Obesity, and Inflammation among US Adults without and with Prediabetes—An NHANES Study
    MDPI AG ; 2022
    In:  International Journal of Environmental Research and Public Health Vol. 20, No. 1 ( 2022-12-30), p. 681-
    Details
    In: International Journal of Environmental Research and Public Health, MDPI AG, Vol. 20, No. 1 ( 2022-12-30), p. 681-
    Abstract: Excessive sugar-sweetened beverages (SSB) consumption and abdominal obesity have been independently linked to numerous disorders, including diabetes and elevated C-reactive protein (CRP). This study aimed to explore the association between SSB intake, abdominal obesity, and inflammation in normal and prediabetic adults. Sugar intake from SSBs was calculated from 24-h dietary recalls and further classified into non-, medium-, and high-intake. The status of non- and prediabetes was identified based on hemoglobin A1c level. All analyses were performed under a survey module with appropriate sampling weights to control for the complex survey design. A total of 5250 eligible adults without diabetes were selected from the 2007–2010 NHANES. A 1.31-fold increased risk of developing prediabetes was observed in people who consumed high sugar from SSBs when compared to non-SSB consumers. Among individuals with prediabetes, adults who consumed a high amount of sugar from SSB had a 1.57-fold higher risk to increase CRP when compared to non-SSB consumers, even after adjusting for abdominal obesity. Furthermore, the association between the high amount of sugar intake from SSBs and elevated CRP was strengthened by abdominal obesity in prediabetes (p for interaction term = 0.030). Our findings highlight that a positive association between sugar intake from SSBs and CRP levels was only observed in US adults with prediabetes. Abdominal obesity may strengthen this effect in prediabetic adults with a high amount of sugar intake from SSBs.
    Type of Medium: Online Resource
    ISSN: 1660-4601
    URL: Article
    DOI: 10.3390/ijerph20010681
    Language: English
    Publisher: MDPI AG
    Publication Date: 2022
    detail.hit.zdb_id: 2175195-X
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
  • 10
    Online Resource
    Online Resource
    BMAE-Net: A Data-Driven Weather Prediction Network for Smart Agriculture
    MDPI AG ; 2023
    In:  Agronomy Vol. 13, No. 3 ( 2023-02-22), p. 625-
    Details
    In: Agronomy, MDPI AG, Vol. 13, No. 3 ( 2023-02-22), p. 625-
    Abstract: Weather is an essential component of natural resources that affects agricultural production and plays a decisive role in deciding the type of agricultural production, planting structure, crop quality, etc. In field agriculture, medium- and long-term predictions of temperature and humidity are vital for guiding agricultural activities and improving crop yield and quality. However, existing intelligent models still have difficulties dealing with big weather data in predicting applications, such as striking a balance between prediction accuracy and learning efficiency. Therefore, a multi-head attention encoder-decoder neural network optimized via Bayesian inference strategy (BMAE-Net) is proposed herein to predict weather time series changes accurately. Firstly, we incorporate Bayesian inference into the gated recurrent unit to construct a Bayesian-gated recurrent units (Bayesian-GRU) module. Then, a multi-head attention mechanism is introduced to design the network structure of each Bayesian layer, improving the prediction applicability to time-length changes. Subsequently, an encoder-decoder framework with Bayesian hyperparameter optimization is designed to infer intrinsic relationships among big time-series data for high prediction accuracy. For example, the R-evaluation metrics for temperature prediction in the three locations are 0.9, 0.804, and 0.892, respectively, while the RMSE is reduced to 2.899, 3.011, and 1.476, as seen in Case 1 of the temperature data. Extensive experiments subsequently demonstrated that the proposed BMAE-Net has overperformed on three location weather datasets, which provides an effective solution for prediction applications in the smart agriculture system.
    Type of Medium: Online Resource
    ISSN: 2073-4395
    URL: Article
    DOI: 10.3390/agronomy13030625
    Language: English
    Publisher: MDPI AG
    Publication Date: 2023
    detail.hit.zdb_id: 2607043-1
    SSG: 23
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
    Online Resource
Close ⊗
This website uses cookies and the analysis tool Matomo. More information can be found here...