Search results for " classification"
showing 10 items of 1043 documents
Exploring relationships between audio features and emotion in music
2009
In this paper, we present an analysis of the associations between emotion categories and audio features automatically extracted from raw audio data. This work is based on 110 excerpts from film soundtracks evaluated by 116 listeners. This data is annotated with 5 basic emotions (fear, anger, happiness, sadness, tenderness) on a 7 points scale. Exploiting state-of-the-art Music Information Retrieval (MIR) techniques, we extract audio features of different kind: timbral, rhythmic and tonal. Among others we also compute estimations of dissonance, mode, onset rate and loudness. We study statistical relations between audio descriptors and emotion categories confirming results from psychological …
First impression misleads emotion recognition
2019
Recognition of others' emotions is a key life ability that guides one's own choices and behavior, and it hinges on the recognition of others' facial cues. Independent studies indicate that facial appearance-based evaluations affect social behavior, but little is known about how facial appearance-based trustworthiness evaluations influence the recognition of specific emotions. We tested the hypothesis that first impressions based on facial appearance affect the recognition of basic emotions. A total of 150 participants completed a dynamic emotion recognition task. In a within-subjects design, the participants viewed videos of individuals with trustworthy-looking, neutral, or untrustworthy-lo…
Ensemble of Hankel Matrices for Face Emotion Recognition
2015
In this paper, a face emotion is considered as the result of the composition of multiple concurrent signals, each corresponding to the movements of a specific facial muscle. These concurrent signals are represented by means of a set of multi-scale appearance features that might be correlated with one or more concurrent signals. The extraction of these appearance features from a sequence of face images yields to a set of time series. This paper proposes to use the dynamics regulating each appearance feature time series to recognize among different face emotions. To this purpose, an ensemble of Hankel matrices corresponding to the extracted time series is used for emotion classification withi…
Quality management in the public sector accounting department - (un)avoidable quality costs and unlikely financial impacts
2017
This paper investigates the nature of quality costs and the likelihood of their having financial impacts in the public sector. An illustrative quality development case project in an accounting department of a Finnish city administration is presented. The empirical data includes answers to a qualitative project question sheet, workshop material and participative observation. Quality problems are classified according to their quality cost category and the extent to which they are avoidable. Some of the quality costs proved unavoidable and some are likely to lack financial impact, exhibiting sticky cost behaviour. The study indicates that certain prevention and appraisal costs in the public se…
Inequalities in mortality in small areas of eleven Spanish cities (the multicenter MEDEA project)
2009
The objectives of this study are to identify inequalities in mortality among census tracts of 11 Spanish cities in the period 1996-2003 and to analyse the relationship between these geographical inequalities and socioeconomic deprivation. It is a cross-sectional ecological study where the units of analysis are census tracts. We obtained an index of socioeconomic deprivation and estimated SMR by each census tract using hierarchical Bayesian models which take into account the spatial structure. In the majority of the cities geographical patterns in total mortality were found in both sexes, which were similar to those for the index of socioeconomic deprivation. Among men, four specific causes …
ELECTRE TRI-based approach to the failure modes classification on the basis of risk parameters: An alternative to the risk priority number
2017
Proposing an ELECTRE TRI-based approach for the failure modes classification into predefined and ordered risk classes.Direct identification of failure modes on which performing the corrective actions with priority.Easy definition of risk classes on the basis of DMs expertise and perception of the industrial context considered.Application to dairy manufacturing processes. Failure Mode and Effects Analysis (FMEA) is an engineering technique aimed at the detection of potential failures, their causes and consequences on the system/process under investigation. When used for the failure modes prioritization, FMEA is also referred to as Failure Mode, Effects and Criticality Analysis (FMECA). In tr…
Towards online bearing fault detection using envelope analysis of vibration signal and decision tree classification algorithm
2017
Online bearing fault detection is an important method for monitoring the health status of bearings in critical machines. This work proposes a classification algorithm, which can be extended towards an online bearing fault detection. The objective is to detect and classify the bearing faults in early stages. The overall design aspects of the online bearing fault detection and classification system are discussed. The proposed method is validated using experimental data, and a high accuracy of the fault classification was observed. Therefore, the proposed method can be applied for an online early fault detection and classification system.
History and Environmental Impact of Mining Activity in Celtic Aeduan Territory Recorded in a Peat Bog (Morvan, France)
2003
The present study aims to document historical mining and smelting activities by means of geochemical and pollen analyses performed in a peat bog core collected around the Bibracte oppidum (Morvan, France), the largest settlement of the great Aeduan Celtic tribe (ca. 180 B.C. to 25 A.D.). The anthropogenic Pb profile indicates local mining operations starting from the Late Bronze Age, ca. cal. 1300 B.C. Lead inputs peaked at the height of Aeduan civilization and then decreased after the Roman conquest of Gaul, when the site was abandoned. Other phases of mining are recognized from the 11th century to modern times. They have all led to modifications in plant cover, probably related in part to…
Influence of the channel design on the heat and mass exchange of induction channel furnace
2011
PurposeThe purpose of this paper is to present in‐depth numerical modelling of heat and mass exchange in industrial induction channel furnace (ICF).Design/methodology/approachThe turbulent heat and mass exchange in the melt is calculated using a three‐dimensional (3D) electromagnetic model and a 3D transient large eddy simulation method. The simulation model has been verified by flow velocity and temperature measurements, which were carried out using an industrial sized channel inductor operating with Wood's metal as a low temperature model melt.FindingsThe ICF is well‐established for melting, holding and casting in the metallurgical industry. But there are still open questions regarding th…
Vibration analysis for bearing fault detection and classification using an intelligent filter
2014
Abstract This paper proposes an intelligent method based on artificial neural networks (ANNs) to detect bearing defects of induction motors. In this method, the vibration signal passes through removing non-bearing fault component (RNFC) filter, designed by neural networks, in order to remove its non-bearing fault components, and then enters the second neural network that uses pattern recognition techniques for fault classification. Four different categories include; healthy, inner race defect, outer race defect, and double holes in outer race are investigated. Compared to the regular fault detection methods that use frequency-domain features, the proposed method is based on analyzing time-d…