Pitting corpus-based classification models against each other: a case study for predicting constructional choice in written Estonian

2017 ◽  
Vol 0 (0) ◽  
Author(s):  
Jane Klavan
Keyword(s):  
Statistical Modelling ◽  
Model Fit ◽  
Discriminative Learning ◽  
Classification Models ◽  
Statistical Classification ◽  
Multivariate Statistical ◽  
Lexical Choice ◽  
Modelling Techniques ◽  
The Moment

AbstractIn the context of constructional alternatives, we may assume that speakers’ choice between alternative forms is influenced by a multitude of factors. At the moment, multivariate statistical classification modelling seems to be the best tool available to capture this knowledge quantitatively. There is a vast array of techniques available. In this paper, two distinct modelling techniques are applied – logistic regression and naïve discriminative learning – to predict the choice between two constructional alternatives in written Estonian. One of the central questions in statistical modelling concerns the evaluation of model fit. It is proposed that for linguistic analysis, the performance of alternative corpus-based models can be evaluated by, first, pitting them against each other and second, pitting them against experimental data. Previous work on modelling constructional and lexical choice has focused on one of the two aspects. The present paper takes this line of analysis further by combining the two approaches.

scholarly journals Which data for quantitative landslide susceptibility mapping at operational scale? Case study of the Pays d'Auge plateau hillslopes (Normandy, France)

2013 ◽  
Vol 1 (2) ◽  
pp. 957-1000 ◽  
Author(s):  
M. Fressard ◽  
Y. Thiery ◽  
O. Maquaire
Keyword(s):  
Landslide Susceptibility ◽  
Roc Curves ◽  
Statistical Modelling ◽  
Susceptibility Mapping ◽  
Landslide Susceptibility Mapping ◽  
Statistical Accuracy ◽  
Multivariate Statistical ◽  
The Impact ◽  
Modelling Methods

Abstract. The objective of this paper is to assess the impact of the datasets quality for the landslide susceptibility mapping using multivariate statistical modelling methods at detailed scale. This research is conducted in the Pays d'Auge plateau (Normandy, France) with a scale objective of 1/10000, in order to fit the French guidelines on risk assessment. Five sets of data of increasing quality (considering accuracy, scale fitting, geomophological significance) and cost of acquisition are used to map the landslide susceptibility using logistic regression. The best maps obtained with each set of data are compared on the basis of different statistical accuracy indicators (ROC curves and relative error calculation), linear cross correlation and expert opinion. The results highlights that only high quality sets of data supplied with detailed geomorphological variables (i.e. field inventory and surficial formations maps) can predict a satisfying proportion of landslides on the study area.

Use of Statistical Modelling Techniques for Simulation

1993 ◽  
Author(s):  
Ebrahim Mazharsolook ◽  
David C. Robinson ◽  
Jonathan D. Casey
Keyword(s):  
Quality Control ◽  
Statistical Modelling ◽  
Test Results ◽  
Final Test ◽  
Product Model ◽  
Design Changes ◽  
Discrete Manufacturing ◽  
Similar Product ◽  
Modelling Techniques

Abstract Statistical methods are explored for the use in modelling of discrete manufacturing. The developed methodologies based on Design of Experiments (DOE) and stepwise regression to obtain the product model are described. This model is then embedded within a software system which is used for simulation of design changes, process changes and disturbances. The software is used to predict final test results in respect of up-stream parameter changes. A case study is presented o show the implementation of this method of modelling in Quality Control of manufacture. This case study has successfully been implemented. The system is currently assisting the company in design of similar product. Feasibility of applying Artificial Intelligen (AI) techniques to Model-Based Quality Control (MBQC) is investigated. An outline of the future development of Hybrid MBQC is then presented.

scholarly journals Which data for quantitative landslide susceptibility mapping at operational scale? Case study of the Pays d'Auge plateau hillslopes (Normandy, France)

2014 ◽  
Vol 14 (3) ◽  
pp. 569-588 ◽  
Author(s):  
M. Fressard ◽  
Y. Thiery ◽  
O. Maquaire
Keyword(s):  
Landslide Susceptibility ◽  
Roc Curves ◽  
Statistical Modelling ◽  
Susceptibility Mapping ◽  
Landslide Susceptibility Mapping ◽  
Multivariate Statistical ◽  
Data Set ◽  
The Impact ◽  
Modelling Methods

Abstract. This paper aims at assessing the impact of the data set quality for landslide susceptibility mapping using multivariate statistical modelling methods at detailed scale. This research is conducted on the Pays d'Auge plateau (Normandy, France) with a scale objective of 1 / 10 000, in order to fit the French guidelines on risk assessment. Five sets of data of increasing quality (considering accuracy, scale fitting, and geomorphological significance) and cost of acquisition are used to map the landslide susceptibility using logistic regression. The best maps obtained with each set of data are compared on the basis of different statistical accuracy indicators (ROC curves and relative error calculation), linear cross correlation and expert opinion. The results highlight that only high-quality sets of data supplied with detailed geomorphological variables (i.e. field inventory and surficial formation maps) can predict a satisfying proportion of landslides in the study area.

A Machine for Feeling: Ping's Posthuman Affect

2017 ◽  
Vol 26 (1) ◽  
pp. 87-102
Author(s):  
Alys Moody
Keyword(s):  
Twentieth Century ◽  
Scholarly Work ◽  
Active Involvement ◽  
Affective Quality ◽  
Contemporary Perspective ◽  
The Moment ◽  
Natural Emotion ◽  
Archival Quality ◽  
Historical Moment

Beckett's famous claim that his writing seeks to ‘work on the nerves of the audience, not the intellect’ points to the centrality of affect in his work. But while his writing's affective quality is widely acknowledged by readers of his work, its refusal of intellect has made it difficult to take fully into account in scholarly work on Beckett. Taking Beckett's 1967 short prose text Ping as a case study, this essay is an attempt to take the affective qualities of Beckett's writing seriously and to consider the implications of his affectively dense writing for his texts’ relationship to history. I argue that Ping's affect emerges from the rhythms of its prose, producing a highly ‘speakable’ text in which affect precedes interpretation. In Ping, however, this affective rhythmic patterning is portrayed as mechanical, the product of the machinic ‘ping’ that punctuates the text and the text's own mechanical rhythms, demanding the active involvement of the reader. The essay concludes by arguing that Ping's mechanised affect is a specifically historical feeling. Arising from a specifically twentieth-century anxiety about technology's tendency to evacuate ‘natural’ emotion in favour of inhuman affect, it participates in a tradition of affectively resonant but curiously blank or indifferent performances of cyborg embodiment. Read in this historical light, Ping's implication of the reader in the production of its mechanised affect grants it, from our contemporary perspective, an archival quality. At the same time, it asks us to broaden the way in which we understand the Beckettian text's relationship to history, pointing to the existence of a more complex and recursive relationship between literature, its historical moment, and our contemporary moment of reading. Such a post-archival historicism sees texts as generated by but not bound to their historical moments of composition, and understands the moment of reception as an integral, if shifting, part of the text's history.

scholarly journals An Algorithm for the Removal of Cosmic Ray Artifacts in Spectral Data Sets

2019 ◽  
Vol 73 (8) ◽  
pp. 893-901
Author(s):  
Sinead J. Barton ◽  
Bryan M. Hennelly
Keyword(s):  
Cosmic Ray ◽  
Data Sets ◽  
Biological Cells ◽  
Statistical Classification ◽  
Signal To Noise ◽  
Multivariate Statistical ◽  
Data Set ◽  
Artefact Removal ◽  
Single Capture ◽  
Acquisition Method

Cosmic ray artifacts may be present in all photo-electric readout systems. In spectroscopy, they present as random unidirectional sharp spikes that distort spectra and may have an affect on post-processing, possibly affecting the results of multivariate statistical classification. A number of methods have previously been proposed to remove cosmic ray artifacts from spectra but the goal of removing the artifacts while making no other change to the underlying spectrum is challenging. One of the most successful and commonly applied methods for the removal of comic ray artifacts involves the capture of two sequential spectra that are compared in order to identify spikes. The disadvantage of this approach is that at least two recordings are necessary, which may be problematic for dynamically changing spectra, and which can reduce the signal-to-noise (S/N) ratio when compared with a single recording of equivalent duration due to the inclusion of two instances of read noise. In this paper, a cosmic ray artefact removal algorithm is proposed that works in a similar way to the double acquisition method but requires only a single capture, so long as a data set of similar spectra is available. The method employs normalized covariance in order to identify a similar spectrum in the data set, from which a direct comparison reveals the presence of cosmic ray artifacts, which are then replaced with the corresponding values from the matching spectrum. The advantage of the proposed method over the double acquisition method is investigated in the context of the S/N ratio and is applied to various data sets of Raman spectra recorded from biological cells.

scholarly journals APPLICATION OF DOMAIN INTEGRATED DESIGN METHODOLOGY FOR BIO-INSPIRED DESIGN- A CASE STUDY OF SUTURE PIN DESIGN

2021 ◽  
Vol 1 ◽  
pp. 487-496
Author(s):  
Pavan Tejaswi Velivela ◽  
Nikita Letov ◽  
Yuan Liu ◽  
Yaoyao Fiona Zhao
Keyword(s):  
Cross Sections ◽  
Design Methodology ◽  
Reaction Force ◽  
Integrated Design ◽  
Total Deformation ◽  
Insertion Force ◽  
Force Reaction ◽  
The Moment ◽  
Work Done

AbstractThis paper investigates the design and development of bio-inspired suture pins that would reduce the insertion force and thereby reducing the pain in the patients. Inspired by kingfisher's beak and porcupine quills, the conceptual design of the suture pin is developed by using a unique ideation methodology that is proposed in this research. The methodology is named as Domain Integrated Design, which involves in classifying bio-inspired structures into various domains. There is little work done on such bio-inspired multifunctional aspect. In this research we have categorized the vast biological functionalities into domains namely, cellular structures, shapes, cross-sections, and surfaces. Multi-functional bio-inspired structures are designed by combining different domains. In this research, the hypothesis is verified by simulating the total deformation of tissue and the needle at the moment of puncture. The results show that the bio-inspired suture pin has a low deformation on the tissue at higher velocities at the puncture point and low deformation in its own structure when an axial force (reaction force) is applied to its tip. This makes the design stiff and thus require less force of insertion.

Sign in / Sign up

Export Citation Format

Share Document