Network


Latest external collaboration on country level. Dive into details by clicking on the dots.

Hotspot


Dive into the research topics where João Neves is active.

Publication


Featured researches published by João Neves.


international conference on adaptive and natural computing algorithms | 2009

Extracting discriminative features using non-negative matrix factorization in financial distress data

Bernardete Ribeiro; Catarina Silva; Armando Vieira; João Neves

In the recent financial crisis the incidence of important cases of bankruptcy led to a growing interest in corporate bankruptcy prediction models. In addition to building appropriate financial distress prediction models, it is also of extreme importance to devise dimensionality reduction methods able to extract the most discriminative features. Here we show that Non-Negative Matrix Factorization (NMF) is a powerful technique for successful extraction of features in this financial setting. NMF is a technique that decomposes financial multivariate data into a few basis functions and encodings using non-negative constraints. We propose an approach that first performs proper initialization of NMF taking into account original data using K-means clustering. Second, builds a bankruptcy prediction model using the discriminative financial ratios extracted by NMF decomposition. Model predictive accuracies evaluated in real database of French companies with statuses belonging to two classes (healthy and distressed) are illustrated showing the effectiveness of our approach.


iberoamerican congress on pattern recognition | 2008

Supervised Isomap with Dissimilarity Measures in Embedding Learning

Bernardete Ribeiro; Armando Vieira; João Neves

In this paper we propose a supervised version of the Isomap algorithm by incorporating class label information into a dissimilarity matrix in a financial analysis setting. On the credible assumption that corporates financial status lie on a low dimensional manifold, nonlinear dimensionality reduction based on manifold learning techniques has strong potential for bankruptcy analysis in financial applications. We apply the method to a real data set of distressed and healthy companies for proper geometric tunning of similarity cases. We show that the accuracy of the proposed approach is comparable to the state-of-the-art Support Vector Machines (SVM) and Relevance Vector Machines (RVM) despite the fewer dimensions used resulting from embedding learning.


international conference machine learning and computing | 2010

Hybrid Genetic Algorithm and Learning Vector Quantization Modeling for Cost-Sensitive Bankruptcy Prediction

Ning Chen; Bernardete Ribeiro; Armando Vieira; João M. M. Duarte; João Neves

Cost-sensitive classification algorithms that enable effective prediction, where the costs of misclassification can be very different, are crucial to creditors and auditors in credit risk analysis. Learning vector quantization (LVQ) is a powerful tool to solve bankruptcy prediction problem as a classification task. The genetic algorithm (GA) is applied widely in conjunction with artificial intelligent methods. The hybridization of genetic algorithm with existing classification algorithms is well illustrated in the field of bankruptcy prediction. In this paper, a hybrid GA and LVQ approach is proposed to minimize the expected misclassified cost under the asymmetric cost preference. Experiments on real-life French private company data show the proposed approach helps to improve the predictive performance in asymmetric cost setup.


Archive | 2016

Ergonomics and Information Design: Design, Standardization and Uniformization of Graphical Symbols for Public Information

João Neves; Fernando Moreira da Silva; Daniel Raposo; J. Silva

The present research addresses the issue of public information and try to achieve the standardization of sign systems, thereby contributing to the uniformity, legibility, understanding and perception of quality of guidance systems, by normalizing the existing signaling, the development of new methodologies applied to the design of symbols and even the application of a tool to assist the design of signs systems specific for public information. This study contributes to a broader understanding of the systems of signs and the interrelation of its components. It seems crucial to this research, which aims at obtaining a detailed study of signs systems for public information, a careful analysis of all aspects related to three areas: The sign and its meaning; The system or how signs are organized; The Culture or users to whom the signs are developed.


Omega-international Journal of Management Science | 1985

Ascertaining the effect of planned organizational change on the work environment

Edward J. Lusk; Debbie Diserens; P. Cormier; Ali Geranmayeh; João Neves

In a dynamic environment, organizations often are required to effect major changes in operations. The success of such changes invariably depends upon numerous factors one of which is how the change affects the work environment. Therefore, in planning organizational change it is important to consider the work environment and to objectively evaluate changes in the work environment in a timely fashion so that corrective actions may be formulated if needed. Such framing and monitoring of the organizational change facilitates successful implementation of the organizational change. This paper suggests a measure which may be used in evaluating an organizations work environment. A case is discussed.


Archive | 2017

Higher Education in Management: The Case of Portugal

João Neves; Vítor da Conceição Gonçalves

Formal management education started in Portugal by 1759 when the Board of Trade, with the support of the Prime Minister, Marquis of Pombal, founded the School of Commerce in Lisbon. ISEG Lisbon School of Economics and Management, actually integrated in the University of Lisbon, is the heir of this eighteenth-century venture.


International Conference on Applied Human Factors and Ergonomics | 2017

Clarifying the Concept of Corporate Identity: From a Collective Vision to Cultural Interface

Daniel Raposo; Fernando Moreira da Silva; João Neves; J. Silva

This study aims to explain the understanding that has been made about Corporate Identity, because it’s common to find divergent views about it. Our purpose is to provide knowledge about Corporate Identity, often mistaken with other related concepts. The paper is based on literature reviews, establishing an analysis of developments on this specific topic over time. It highlights and discusses important points previously reported in the literature. The novelty of this type of paper consists in the relation established between different views and by its conclusions concerning to definitions. The brand is positioned as cultural interface between the business and the stakeholders. The results of this paper are to make a clear distinction between Corporate Identity, Corporate Visual Identity, Brand and Corporate Image. It also establishes a connection between culture, values, mission and Corporate Identity, explaining how these concepts are in the geneses of the brand personality.


International Conference on Applied Human Factors and Ergonomics | 2017

Drawing as Reasoning Tool in UX Design - Doodling and Drawing as Foundation for Project Planning

J. Silva; Fernando C. Silva; Daniel Raposo; João Neves

Thinking through drawing in classroom settings on a Design bachelor degree, is a learning strategy capable of developing perception on new project values. Several studies explain how drawing serves as a reasoning tool to build knowledge upon a subject of study. The act of doodling and drawing, plays a role in a narrative structure, constructing a map of symbols and allowing different associations. Students interact with the subject of study through the graphic representation of an idea. Although drawing is useful as a tool, in learning settings is still missed a stronger link with writing and talking. There is the need to empower drawing as a reasoning tool, find new connections and project other future associations. The learning strategy developed in this article was carried out in the Curricular Unit of Interaction Systems, during the first semester of 2016/2017, in the Bachelor Visual Communication Design and Audiovisual degree, Applied Arts School, Polytechnic Institute of Castelo Branco, Portugal.


International Conference on Applied Human Factors and Ergonomics | 2017

Ergonomics and Warning Design: Standardization of Graphical Symbols for Safety Signs

João Neves; Fernando Moreira da Silva; Daniel Raposo; J. Silva

The International Organization for Standardization (ISO), possess a Technical Committee (ISO TC 145) which addresses the issues of standardization in the field of graphical symbols, establishing principles for preparation, coordination and application of graphical symbols. The Technical Committee, is divided by standardization of public information symbols (Subcommittee SC1), safety identification, signs, shapes, symbols and colors (SC2) and Graphical symbols for use on equipment (SC3). The Technical Committee also has a working group for testing the usability of graphical symbols. From the vast work of standardization, the TC 145 has developed various standards relating to graphic symbols, addressing issues as vast as design principles for safety signs and safety markings, for product safety labels, and graphical symbols for use in safety signs. The committee also has developed requirements for creation and design of public information symbols, has developed and normalized public information, registered symbols for use on equipment, water safety signs and beach safety flags and still safety colors and safety signs, Safety way guidance systems, among other topics. It is therefore important in this context to understand the triadic relationship between the design, standardization and the decoding of messages by users, relating the process of graphic conception of graphical symbols for safety signs, the standardization programs and the usability of graphical symbols.


Archive | 2016

The Contribute of Graphic Style and Connotations to Memorability of Brand Marks from Agri-Food Sector

Daniel Raposo; João Neves; J. Silva; Catarina Laginha

This study aims to understand the process of decoding brand marks particularly how people perceive brand marks styles and connotations, and also reveal which characteristics contribute a better memorization. It is not intended to create standards or a system for brands to employ during brand marks design or visual identity projects. Our purpose is to provide knowledge, a reference frame and principles according to which companies can make informed decisions about how to evaluate or design brand marks. The study was conducted online with 150 respondents in Portugal, asking them to evaluate 15 brands marks of agri-food sector, specifically, olive oil brands. It was used a model adapted from the C-HIP model (Wogalter et al. in Warnings and risk communication. Taylor & Francis, London, 1999 [1]) particularly for meaning/comprehension; Subjective evaluations; Self-reports. The respondents were asked to name the brands they found to be the most memorable and visually appealing, selecting the top attributes recognizable and those they did not recognize. The brand marks were organized by typologies, iconographic, descriptive or abstracts, establishing relations with graphic style, connotations and memorability.

Collaboration


Dive into the João Neves's collaboration.

Top Co-Authors

Avatar

J. Silva

University of Lisbon

View shared research outputs
Top Co-Authors

Avatar

Daniel Raposo

Instituto Politécnico Nacional

View shared research outputs
Top Co-Authors

Avatar
Top Co-Authors

Avatar

Armando Vieira

Instituto Superior de Engenharia do Porto

View shared research outputs
Top Co-Authors

Avatar
Top Co-Authors

Avatar

Juan Pineiro-Chousa

University of Santiago de Compostela

View shared research outputs
Top Co-Authors

Avatar
Top Co-Authors

Avatar

Catarina Silva

Polytechnic Institute of Leiria

View shared research outputs
Top Co-Authors

Avatar
Top Co-Authors

Avatar

João M. M. Duarte

Instituto Superior de Engenharia do Porto

View shared research outputs
Researchain Logo
Decentralizing Knowledge