Finding Relevant Variables in PAC Model with Membership Queries

1999 ◽  
pp. 313-322 ◽  
Author(s):  
David Guijarro ◽  
Jun Tarui ◽  
Tatsuie Tsukiji
Keyword(s):  
Membership Queries ◽  
Relevant Variables ◽  
Pac Model

scholarly journals On the Learnability of Possibilistic Theories

2020 ◽  
Author(s):  
Cosimo Persia ◽  
Ana Ozaki
Keyword(s):  
Large Class ◽  
Polynomial Time ◽  
Classical Logic ◽  
Learning Model ◽  
Membership Queries ◽  
Exact Model ◽  
Exact Learning ◽  
Probably Approximately Correct ◽  
Horn Theories ◽  
Pac Model

We investigate learnability of possibilistic theories from entailments in light of Angluin’s exact learning model. We consider cases in which only membership, only equivalence, and both kinds of queries can be posed by the learner. We then show that, for a large class of problems, polynomial time learnability results for classical logic can be transferred to the respective possibilistic extension. In particular, it follows from our results that the possibilistic extension of propositional Horn theories is exactly learnable in polynomial time. As polynomial time learnability in the exact model is transferable to the classical probably approximately correct (PAC) model extended with membership queries, our work also establishes such results in this model.

A novel approach to white liquor control in a continuous digester using the Box-Jenkins methodology to predict chip bulk density

TAPPI Journal ◽  
2015 ◽  
Vol 14 (6) ◽  
pp. 395-402
Author(s):  
FLÁVIO MARCELO CORREIA ◽  
JOSÉ VICENTE HALLAK D’ANGELO ◽  
SUELI APARECIDA MINGOTI
Keyword(s):  
Bulk Density ◽  
Moving Average ◽  
Pulp Mill ◽  
Statistical Decision ◽  
White Liquor ◽  
Novel Approach ◽  
Cooking Process ◽  
Eucalyptus Kraft Pulp ◽  
Relevant Variables ◽  
Kraft Cooking

Alkali charge is one of the most relevant variables in the continuous kraft cooking process. The white liquor mass flow rate can be determined by analyzing the chip bulk density fed to the process. At the mills, the total time for this analysis usually is greater than the residence time in the digester. This can lead to an increasing error in the mass of white liquor added relative to the specified alkali charge. This paper proposes a new approach using the Box-Jenkins methodology to develop a dynamic model for predicting chip bulk density. Industrial data were gathered on 1948 observations over a period of 12 months from a Kamyr continuous digester at a bleached eucalyptus kraft pulp mill in Brazil. Autoregressive integrated moving average (ARIMA) models were evaluated according to different statistical decision criteria, leading to the choice of ARIMA (2,0,2) as the best forecasting model, which was validated against a new dataset gathered during 2 months of operations. A combination of predictors has shown more accurate results compared to those obtained by laboratory analysis, allowing a reduction of around 25% of the chip bulk density error to the alkali addition amount.

Metal Contamination of Stream Waters under the Impact of Tanneries

2006 ◽  
Vol 33 (2) ◽  
pp. 55 ◽  
Author(s):  
MARIA LUCIA KOLOWSKI RODRIGUES ◽  
MILTON LUIZ LAQUINTINIE FORMOSO
Keyword(s):  
Water Quality ◽  
Water Discharge ◽  
Solid Material ◽  
Total Variance ◽  
Oxygen Conductivity ◽  
Contamination Degree ◽  
Iron Aluminum ◽  
Relevant Variables ◽  
Stream Waters ◽  
The Impact

This study evaluated the contamination of water samples from Cadeia and Feitoria rivers (Rio Grande do Sul State, Brazil), affected by tannery activities. From July 1999 to April 2000, four sampling campaigns were performed at ten sites in order to evaluate selected metals and ancillary physicochemical variables. Sample preservation and analyses followed recommendations of the Standard Methods. Factor analysis was used to obtain statistical indexes representing the contamination degree of waters evaluated. The information was summarized in two principal components. The first, which accounted for 50% of the total variance, was associated to a tannery contribution and generated a contamination index. Total, Suspended and Dissolved Solids, Dissolved Oxygen, Conductivity, Chromium, Manganese, Copper, Nickel, Sodium, Calcium, Potassium, and Magnesium were the well-correlated variables with this first component. The water quality decreased from headwaters up to mouth along both streams, but the most contaminated sites were located at the lower reach of Feitoria river (Ivoti and Lindolfo Collor cities), where tanneries are concentrated. After the entrainment of Feitoria waters (São Sebastião do Caí municipality), Cadeia river also presented an increased contamination degree. The application of statistical randomization tests highlighted these same sites as significantly distinct from the others. Water contamination also showed association to flow variations, and a poorer water quality was observed during the dry period (January). The second component, in which Iron, Aluminum, and Suspended Solids were the relevant variables, was loaded with 15% of the total variance. It was linked to natural events, since higher factor scores in this component were obtained during a period of increased water discharge (October), which caused resuspension and entrainment of solid material to the rivers bed. As a final result of the study, sampling stations were classified according to the contamination degree, and graphically represented on a basin map, which synthesized the environmental diagnosis.

Voting and Popularity

2019 ◽  
pp. 852-879 ◽  
Author(s):  
Gebhard Kirchgässner
Keyword(s):  
Economic Development ◽  
Self Interest ◽  
Relevant Variables ◽  
Time Periods ◽  
Real Growth ◽  
Voting Intentions

For about 45 years, vote and popularity functions have been estimated for many countries, indicating that both voting intentions and actual votes are influenced by economic development. The economy is, of course, not the only and probably not always the most important factor, but there is no doubt anymore that it is an important factor. The most relevant variables are still unemployment and/or real growth, and inflation. The estimated coefficients vary considerably between countries and time periods. In studies done, retrospective sociotropic voting dominates. However, the evidence is not so univocal; rather, it tells that voting has egotropic as well as sociotropic aspects, and it is prospective as well as retrospective. It is still open what roles self-interest and altruism play in voting.

scholarly journals Albumin in patients with liver disease shows an altered conformation

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Margret Paar ◽  
Vera H. Fengler ◽  
Daniel J. Rosenberg ◽  
Angelika Krebs ◽  
Rudolf E. Stauber ◽  
...  
Keyword(s):  
Fatty Acids ◽  
Liver Disease ◽  
Chronic Liver Disease ◽  
Chronic Liver ◽  
X Ray Scattering ◽  
Pathological Conditions ◽  
Healthy Donors ◽  
Relevant Variables ◽  
End Stage

AbstractHuman serum albumin (HSA) constitutes the primary transporter of fatty acids, bilirubin, and other plasma compounds. The binding, transport, and release of its cargos strongly depend on albumin conformation, which is affected by bound ligands induced by physiological and pathological conditions. HSA is both highly oxidized and heavily loaded with fatty acids and bilirubin in chronic liver disease. By employing small-angle X-ray scattering we show that HSA from the plasma of chronic liver disease patients undergoes a distinct opening compared to healthy donors. The extent of HSA opening correlates with clinically relevant variables, such as the model of end-stage liver disease score, bilirubin, and fatty acid levels. Although the mild oxidation of HSA in vitro does not alter overall structure, the alteration of patients’ HSA correlates with its redox state. This study connects clinical data with structural visualization of albumin dynamicity in solution and underlines the functional importance of albumin’s inherent flexibility.

scholarly journals Bioprospecting of Sechium spp. varieties for the selection of characters with pharmacological activity

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
María Isabel Iñiguez-Luna ◽  
Jorge Cadena-Iñiguez ◽  
Ramón Marcos Soto-Hernández ◽  
Francisco Javier Morales-Flores ◽  
Moisés Cortes-Cruz ◽  
...  
Keyword(s):  
Cell Lines ◽  
Proliferative Activity ◽  
Meta Analysis ◽  
Pearson Correlation ◽  
Statistical Significance ◽  
Economic Value ◽  
Principal Component ◽  
Malignant Cell ◽  
Length Polymorphisms ◽  
Relevant Variables

AbstractBioprospecting identifies new sources of compounds with actual or potential economic value that come from biodiversity. An analysis was performed regarding bioprospecting purposes in ten genotypes of Sechium spp., through a meta-analysis of 20 information sources considering different variables: five morphological, 19 biochemical, anti-proliferative activity of extracts on five malignant cell lines, and 188 polymorphic bands of amplified fragment length polymorphisms, were used in order to identify the most relevant variables for the design of genetic interbreeding. Significant relationships between morphological and biochemical characters and anti-proliferative activity in cell lines were obtained, with five principal components for principal component analysis (SAS/ETS); variables were identified with a statistical significance (< 0.7 and Pearson values ≥ 0.7), with 80.81% of the accumulation of genetic variation and 110 genetic bands. Thirty-nine (39) variables were recovered using NTSYSpc software where 30 showed a Pearson correlation (> 0.5) and nine variables (< 0.05), Finally, using a cladistics analysis approach highlighted 65 genetic bands, in addition to color of the fruit, presence of thorns, bitter flavor, piriform and oblong shape, and also content of chlorophylls a and b, presence of cucurbitacins, and the IC50 effect of chayote extracts on the four cell lines.

scholarly journals Potential of standard perinatal data for measuring maternal integrity in childbirth

2020 ◽  
Vol 30 (Supplement_5) ◽  
Author(s):  
C Miani ◽  
S Batram-Zantvoort ◽  
O Razum
Keyword(s):  
Real Life ◽  
Healthcare Setting ◽  
Demographic Variables ◽  
Care Providers ◽  
Birth Process ◽  
Standard Data ◽  
Obstetric Violence ◽  
Relevant Variables ◽  
Perinatal Data ◽  
Birth Centres

Abstract Background Measuring the phenomenon of violation of maternal integrity in childbirth (e.g. obstetric violence) relies in part on the completeness of maternity care providers' data. The population coverage and linkage possibilities that they provide make for a great untapped potential. Although violation of integrity is a complex phenomenon best measured with dedicated instruments, standard data provide details about the birth and care received. Relevant variables include justifications of medical procedures (e.g. episiotomy) and characteristics of the birth process (e.g. length of labour). Demographic variables can be used for intersectional analyses to track potential discrimination -a dimension of violation of integrity in childbirth. Methods Using a baseline questionnaire and perinatal data obtained from hospitals, birth centres and midwifes in the BaBi study (Germany), we compared the completeness of integrity-relevant variables across providers and depending on the demographic and clinical characteristics of the women. We investigated potential for analysis from an intersectional perspective. Results Our analyses included 908 births, of which 32 outside hospital. There were 634 vaginal birth vs. 274 caesarean sections. We found poor reporting on demographic variables, in particular with regard to the 'region of origin' variable (correct origin recorded for half of the migrants). There was better reporting by midwives than by hospitals for “soft indicators”, such as the position of the women during birth (100% vs. 87.6%). Conclusions Putting more emphasis on completeness of standardised data could increase their potential for research. Healthcare setting, organisational culture and working conditions might determine what is judged important in terms of reporting; therefore, targeted education may improve this process. Next, we will interview care providers to understand data collection constraints and priorities and potential reporting bias in real-life settings.

scholarly journals Fault Detection of Diesel Engine Air and after-Treatment Systems with High-Dimensional Data: A Novel Fault-Relevant Feature Selection Method

Processes ◽  
2021 ◽  
Vol 9 (2) ◽  
pp. 259
Author(s):  
Qilan Ran ◽  
Yedong Song ◽  
Wenli Du ◽  
Wei Du ◽  
Xin Peng
Keyword(s):  
Genetic Algorithm ◽  
Diesel Engine ◽  
Fault Detection ◽  
Correlation Analysis ◽  
Canonical Correlation Analysis ◽  
Diesel Engines ◽  
Canonical Correlation ◽  
High Dimensional Data ◽  
High Dimensional ◽  
Relevant Variables

In order to reduce pollutants of the emission from diesel vehicles, complex after-treatment technologies have been proposed, which make the fault detection of diesel engines become increasingly difficult. Thus, this paper proposes a canonical correlation analysis detection method based on fault-relevant variables selected by an elitist genetic algorithm to realize high-dimensional data-driven faults detection of diesel engines. The method proposed establishes a fault detection model by the actual operation data to overcome the limitations of the traditional methods, merely based on benchmark. Moreover, the canonical correlation analysis is used to extract the strong correlation between variables, which constructs the residual vector to realize the fault detection of the diesel engine air and after-treatment system. In particular, the elitist genetic algorithm is used to optimize the fault-relevant variables to reduce detection redundancy, eliminate additional noise interference, and improve the detection rate of the specific fault. The experiments are carried out by implementing the practical state data of a diesel engine, which show the feasibility and efficiency of the proposed approach.

Attribute-efficient learning of Boolean functions from Post closed classes

2020 ◽  
Vol 30 (5) ◽  
pp. 285-301
Author(s):  
Anastasiya V. Bistrigova
Keyword(s):  
Boolean Functions ◽  
Membership Queries ◽  
Efficient Learning

AbstractWe consider exact attribute-efficient learning of functions from Post closed classes using membership queries and obtain bounds on learning complexity.

Sign in / Sign up

Export Citation Format

Share Document