Wyniki wyszukiwania

1

Prediction of protein secondary structure by neural networks: encoding short and long range patterns of amino acid packing

100%

Vieth M., Kolinski A., Skolnick J., Sikorski A.

Acta Biochimica Polonica

|

1992

|

tom 39

|

nr 4

À complex, cascaded neural network designed to predict the secondary structure of globular proteins has been developed. Information about the local buried-unburied pattern and the average tendency of the particular types of amino acids to be buried inside the globule were used. Nonspecific information about long distance contact maps was also employed. These modifications result in a noticeable improvement (3 - 9%) of prediction accuracy. The best result for the average success ratio for the testing set of nonhomologous proteins was 68.3% (with corresponding Matthews' coefficients, C

2

Novelty based feedback regulation in artificial neural networks

88%

Rychwalska A., Jablonski P., Zochowski M., Nowak A.

Acta Neurobiologiae Experimentalis

|

2005

|

tom 65

|

nr 4

3

Identifikacija tekhnicheskikh resursov v proekte proizvodstva sel'skokhozjajjstvennojj produkcii s ispol'zovaniem nejjronnykh setejj

88%

Tymochko V., Padjuka R.

Motrol. Motoryzacja i Energetyka Rolnictwa

|

2014

|

tom 16

|

nr 4

4

Attractors as the cortical contribution to memory computations

88%

Treves A.

Acta Neurobiologiae Experimentalis

|

2005

|

tom 65

|

nr 5

5

Artykuł dostępny w postaci pełnego tekstu - kliknij by otworzyć plik

Neural network simulation in running of acetic acid synthesis unit while start-up

88%

Porkuian O., Samojlova Z.

Teka Komisji Motoryzacji i Energetyki Rolnictwa

|

2013

|

tom 13

|

nr 3

6

Prediction of signal peptides in protein sequences by neural networks

88%

Plewczynski D., Slabinski L., Ginalski K., Rychlewski L.

Acta Biochimica Polonica

|

2008

|

tom 55

|

nr 2

261-267

We present here a neural network-based method for detection of signal peptides (abbreviation used: SP) in proteins. The method is trained on sequences of known signal peptides extracted from the Swiss-Prot protein database and is able to work separately on prokaryotic and eukaryotic proteins. A query protein is dissected into overlapping short sequence fragments, and then each fragment is analyzed with respect to the probability of it being a signal peptide and containing a cleavage site. While the accuracy of the method is comparable to that of other existing prediction tools, it provides a significantly higher speed and portability. The accuracy of cleavage site prediction reaches 73% on heterogeneous source data that contains both prokaryotic and eukaryotic sequences while the accuracy of discrimination between signal peptides and non-signal peptides is above 93% for any source dataset. As a consequence, the method can be easily applied to genome-wide datasets. The software can be downloaded freely from http://rpsp.bioinfo. pl/RPSP.tar.gz.

7

Physical properties - formed during spray drying - of materials with the properties of an agglomerate

88%

Zbicinski I., Kwapinska M.

Acta Agrophysica

|

2003

|

tom 02

|

nr 2[96]

8

Using of neural network to precipitation nowcasting based on weather radar data

75%

Osrodka K., Jurczyk A., Szturc J.

Wiadomości Instututu Meteorologii i Gospodarki Wodnej

|

2004

|

tom 27

|

nr 2

3-15

9

Energy-efficient modes for management of biotechnical objects based on natural disturbances prediction

75%

Lysenko V., Golovinskyi B., Reshetiuk V., Shcherbatiuk V., Shtepa V.

Annals of Warsaw University of Life Sciences - SGGW. Agriculture

|

2015

|

nr 65 Agric.Forest Eng.

Nowadays overwhelming majority of biotechnical objects in agriculture, such as poultry houses, greenhouses etc., function under the mode of stabilization of technological parameters (air temperature, humidity etc.). This approach leads to excess consumption of energy resources (electrical energy, natural gas). Intelligent control based on using different strategies (not only stabilization), prediction and consideration of natural disturbances on biotechnical objects, physiological features of biological objects (poultry, plants etc.) allows to reduce energy consumption. The paper presents specific knowledge concerning promising areas of control systems of biotechnical objects, methodological bases for specialized algorithmic-mathematical software construction based on the methods of game theory and statistical solutions, neural networks (including genetic algorithm), filtering the noise components of information signals.

10

Application of neural networks for the prediction of total phosphorus concentrations in surface waters

75%

Mozejko J., Gniot R.

Polish Journal of Environmental Studies

|

2008

|

tom 17

|

nr 3

363-368

This paper describes the application of artificial neural networks (ANNs) for the time series modeling of total phosphorous concentrations in the Odra River. Data from the monitoring site Police in the lower part of the Odra were used for training, validating and testing the models. Two models are proposed to prove the satisfactory forecast of phosphorus concentrations: a simpler one with a single input variable and a more complex one with 14 input variables. Both ANN models show a high ability to predict from the new data set. On the basis of sensitivity analysis the relationships between phosphorus concentrations and other water quality variables were established.

11

Erythropoietin affects GABAergic transmission in hippocampal neurons in vitro

75%

Wojtowicz T., Mozrzymas J. W.

Cellular and Molecular Biology Letters

|

2008

|

tom 13

|

nr 4

649-655

Erythropoietin is a potent regulator of erythropoiesis. It acts via the specific membrane receptor (EpoR). Erythropoietin is also known to be present in the central nervous system, and its concentration and the expression of EpoR change during development, which raises the possibility that this modulator might be involved in the regulation of neuronal functions in the developing brain. The GABAergic system undergoes profound changes during development and is particularly susceptible to modulation by endogenous factors. Therefore, we decided to investigate the impact of Epo on GABAergic transmission in hippocampal neurons developing in vitro. An analysis of miniature IPSCs (mIPSCs) revealed that a long-term treatment with Epo (48 or 72 h) resulted in a major acceleration of the decaying phase of these currents while the amplitude and current frequency remained unchanged. Interestingly, this effect was restricted to the youngest considered age group (6-8 DIV), indicating that Epomediated modulation of mIPSCs depends on the developmental stage of the neurons. We conclude that Epo may exert a modulatory action on GABAergic transmission in developing neural networks.

12

Criteria for selecting attributes for the prognostic neural model based on limited data set

75%

Janaszak M., Majorczyk M., Mankowski D. R., Trajer J.

Annals of Warsaw University of Life Sciences - SGGW. Agriculture

|

2007

|

nr 51 Agric.Forest Eng.

99-104

13

Normirovanie mekhanicheskojj obrabotki vosstanovlennykh detalejj sel'skokhozjajjstvennojj tekhniki

75%

Rogovskijj L., Zazimko O., Kjurchev S., Boltjanskaja N.

Motrol. Motoryzacja i Energetyka Rolnictwa

|

2014

|

tom 16

|

nr 3

14

Feedforward neural networks and the forecasting of multi-sectional demand for telecom services: a comparative study of effectiveness for hourly data

75%

Kaczmarczyk P.

Acta Scientiarum Polonorum. Oeconomia

|

2020

|

tom 19

|

nr 3

15

Application of neural networks to mathematical modeling of sedimentation processes

75%

Kowalski W. P., Kolodziejczyk K., Zacharz T.

Archiwum Ochrony Środowiska

|

2002

|

tom 28

|

nr 2

16

Optimization of HPLC separations of flavonoids with the use of artificial neural networks

75%

Bucinski A., Baczek T.

Polish Journal of Food and Nutrition Sciences

|

2002

|

tom 11/52

|

nr 4

The high-performance liquid chromatography (HPLC) procedure based on gradient elution technique was used to separate flavonoids in leaves of Taxus baccata var. elegantissima and Metasequoia glyptostroboides. Optimization of chromatographic separations was supported by artificial neural networks. The best gradient conditions acquired to separate analyzed compounds were established and then used in experiments. Predictive errors were additionally calculated. Satisfactory correlation between predicted and experimental retention data was obtained.

17

The use of neural networks in studying the outflow from drainage pipelines

75%

Reinhard T., Reinhard A.

Journal of Water and Land Development

|

2005

|

nr 09

18

The identification of parameters of a linear and a non-linear model of a kinematic measurement-control network

63%

Mrowczynska M.

Acta Scientiarum Polonorum. Geodesia et Descriptio Terrarum

|

2014

|

tom 13

|

nr 1-2

Engineering geodesy deals with a wide range of problems. There is also a part that deals with measuring displacements and deformations of engineering objects. Correct geodetic monitoring requires identifying the movement of points representing an engineering object in order to determine displacement values, taking into account the time function. The paper presents the results of research on kinematic models of geodetic networks in the aspect of using them for describing the state of vertical displacements of engineering objects located on expansive soil. The paper presents two functional models of an observation system: one in the form of a second rank polynomial and the other in the form of an exponential function. The selected kinematic models of measurement-control geodetic networks were estimated with classic methods and neural networks.

19

Neural model for localization of the injection pump damaged elements

63%

Klimkiewicz M.

Annals of Warsaw University of Life Sciences - SGGW. Agriculture

|

2007

|

nr 51 Agric.Forest Eng.

79-83

20

Neural modeling of plant tissue cultures: a review

63%

Zielinska S., Kepczynska E.

BioTechnologia. Journal of Biotechnology Computational Biology and Bionanotechnology

|

2013

|

tom 94

|

nr 3

Ograniczanie wyników

Prediction of protein secondary structure by neural networks: encoding short and long range patterns of amino acid packing

Novelty based feedback regulation in artificial neural networks

Identifikacija tekhnicheskikh resursov v proekte proizvodstva sel'skokhozjajjstvennojj produkcii s ispol'zovaniem nejjronnykh setejj

Attractors as the cortical contribution to memory computations

Neural network simulation in running of acetic acid synthesis unit while start-up

Prediction of signal peptides in protein sequences by neural networks

Physical properties - formed during spray drying - of materials with the properties of an agglomerate

Using of neural network to precipitation nowcasting based on weather radar data

Energy-efficient modes for management of biotechnical objects based on natural disturbances prediction

Application of neural networks for the prediction of total phosphorus concentrations in surface waters

Erythropoietin affects GABAergic transmission in hippocampal neurons in vitro

Criteria for selecting attributes for the prognostic neural model based on limited data set

Normirovanie mekhanicheskojj obrabotki vosstanovlennykh detalejj sel'skokhozjajjstvennojj tekhniki

Feedforward neural networks and the forecasting of multi-sectional demand for telecom services: a comparative study of effectiveness for hourly data

Application of neural networks to mathematical modeling of sedimentation processes

Optimization of HPLC separations of flavonoids with the use of artificial neural networks

The use of neural networks in studying the outflow from drainage pipelines

The identification of parameters of a linear and a non-linear model of a kinematic measurement-control network

Neural model for localization of the injection pump damaged elements

Neural modeling of plant tissue cultures: a review