Giovanni Bortolan and Witold Pedrycz
This paper sets out to design hyperbox classifiers of high interpretation capabilities. They are based on a collection of hyperboxes – generic and highly interpretable geometric…
Abstract
Purpose
This paper sets out to design hyperbox classifiers of high interpretation capabilities. They are based on a collection of hyperboxes – generic and highly interpretable geometric descriptors of data belonging to a certain class. Such hyperboxes directly translate into conditional statements (rules) taking on the well‐known format “if feature1 assumes values in [a,b] and feature2 assumes values in [d,f] and … and featuren assumes values in [w,z] then class ω” where the intervals ([a,b],…[w,z]) are the respective edges (features) of the corresponding hyperbox.
Design/methodology/approach
The proposed design process of hyperboxes consists of two main phases. In the first phase, a collection of “seeds” of the hyperboxes is constructed through data clustering being realized by means of the fuzzy C‐means algorithm. During the second phase, the hyperboxes are “grown” (expanded) by applying mechanisms of genetic optimization (and genetic algorithm, in particular).
Findings
It is demonstrated how the underlying geometry of the hyperboxes supports an immediate interpretation of arrhythmia data by linking the ranges of the features (parameters of the ECG signal) forming the edges of the hyperboxes with the two classes of the signals (normal – abnormal). A collection of comprehensive experiments offers an interesting insight into the geometry of the individual categories of the ECG signals and discusses how the resulting hyperbox classifiers link their geometric properties with the obtained classification rates.
Research limitations/implications
The structure of the classifier is essential to enhance interpretation capabilities of the architecture and generate a collection of “if‐then” classification rules.
Originality/value
The study addresses an issue of design of highly interpretable, granular classifiers with the use of the technology of computational intelligence and evolutionary optimization, in particular.
Details
Keywords
Earl D. Benson and Barry R. Marks
In April and May of 2010 Moody's recalibrated its municipal bond ratings to a global scale, the system they use for other asset classes and the same scale used by Standard and…
Abstract
Purpose
In April and May of 2010 Moody's recalibrated its municipal bond ratings to a global scale, the system they use for other asset classes and the same scale used by Standard and Poor's (S&P). The authors investigate the impact of Moody's recalibration on true interest cost (TIC) of competitively-sold, uninsured, new bond issues with split bond ratings, by looking at a sample of bond issues before recalibration (1997–2010) and after recalibration (2010–2017).
Design/methodology/approach
Two different hypotheses are tested for each period to estimate whether TIC remains the same when the S&P rating is higher (H1) than Moody's rating or lower (H2) compared to bond issues for which the S&P and Moody's rating are the same. Further, two additional hypotheses are tested. H3 tests whether the impact of having a higher rating from S&P is the same as having a lower rating from S&P. H4 tests whether the impact of having a split rating is the same in the pre- and post-recalibration period.
Findings
Tests suggest that before recalibration a higher S&P rating leads to significantly lower interest costs, but a lower S&P rating does not lead to significantly higher costs. After recalibration, a higher S&P rating leads to significantly lower interest costs; however, a lower S&P rating leads to significantly higher interest costs for the bonds in the sample. The findings also suggest that the rating systems of Moody's and S&P became more similar to each other after recalibration and that the impact on interest cost of a higher S&P rating is reduced after the recalibration.
Originality/value
It appears that a given Moody's rating (which used higher credit standards in the period before recalibration) was more influential than the S&P rating prior to recalibration because investors “ignored” a lower S&P rating during this period. After recalibration, the lower S&P rating was no longer ignored by investors. Therefore, Moody's recalibration seems to have had the intended effect of moving the credit standards of the two rating agencies more into parity. This provides value to investors since they may now assume, unlike the situation in the pre-recalibration period, that similar ratings from the two companies provide similar information about the probability of default and loss that would occur following a default. From the standpoint of regulators, the municipal credit information is easier to understand and is more transparent for investors.
Details
Keywords
The equator principles constitute an international voluntary code developed by banks to encourage consideration of environmental and social issues in project financing. Such codes…
Abstract
Purpose
The equator principles constitute an international voluntary code developed by banks to encourage consideration of environmental and social issues in project financing. Such codes can flexibly bridge the gap between individual companies' sustainability initiatives and mandatory, legal regulation. However, concerns continue to be expressed that the equator principles reporting of banks is not fully satisfactory, so the aim of this paper is to investigate both the nature of the success and the shortcomings of equator principles reporting.
Design/methodology/approach
The paper is based on academic literature on motivations for corporate social responsibility and various publications by non‐government organisations and professional accounting and legal organisations, together with analysis of the disclosures made by Barclays and HSBC. In addition, access was gained for semi‐structured interviews with some senior executives/consultants.
Findings
While the voluntary equator principles initiative has been remarkably successful in matching banks' strategic motivation, the environmental benefit may primarily be a by‐product of the risk management processes of banks, consistent with enlightened shareholder theory. This does not mean the environmental benefits may not be real but, without more detailed project‐level disclosure and a standardised performance evaluation system, it is difficult to measure the extent to which the equator principles have had a positive effect on the environment.
Research limitations/implications
Further research is needed to gauge how the equator principles impact front‐line decision making. There could usefully be further standardisation of equator principles reporting formats, with more detail about project‐level implementation. With respect to reports of external assurers, it remains an open question as to whether these should be made compulsory, subject to further specification of the independence and competence standards.
Originality/value
The study helps to illuminate the effectiveness of a voluntary code such as the equator principles in the social construction of how enlightened shareholder theory is to be interpreted and implemented. It makes an initial response to recent calls by Bebbington et al. and Adams for further empirical corporate social responsibility research and more direct engagement with organisations.
Details
Keywords
Linh Tran Hoai and Stanislaw Osowski
This paper presents new approach to the integration of neural classifiers. Typically only the best trained network is chosen, while the rest is discarded. However, combining the…
Abstract
Purpose
This paper presents new approach to the integration of neural classifiers. Typically only the best trained network is chosen, while the rest is discarded. However, combining the trained networks helps to integrate the knowledge acquired by the component classifiers and in this way improves the accuracy of the final classification. The aim of the research is to develop and compare the methods of combining neural classifiers of the heart beat recognition.
Design/methodology/approach
Two methods of integration of the results of individual classifiers are proposed. One is based on the statistical reliability of post‐processing performance on the trained data and the second uses the least mean square method in adjusting the weights of the weighted voting integrating network.
Findings
The experimental results of the recognition of six types of arrhythmias and normal sinus rhythm have shown that the performance of individual classifiers could be improved significantly by the integration proposed in this paper.
Practical implications
The presented application should be regarded as the first step in the direction of automatic recognition of the heart rhythms on the basis of the registered ECG waveforms.
Originality/value
The results mean that instead of designing one high performance classifier one can build a number of classifiers, each of not superb performance. The appropriate combination of them may produce a performance of much higher quality.
Details
Keywords
Sarah Elison, Jonathan Ward, Glyn Davies and Mark Moody
The purpose of this paper is to explore the adoption and implementation of computer-assisted therapy (CAT) using Breaking Free Online (BFO) in a social care and health charity…
Abstract
Purpose
The purpose of this paper is to explore the adoption and implementation of computer-assisted therapy (CAT) using Breaking Free Online (BFO) in a social care and health charity working with people affected by drugs and alcohol dependence, Crime Reduction Initiatives (CRI).
Design/methodology/approach
Semi-structured interviews were conducted with service managers, practitioners, peer mentors and service users. Data were thematically analysed and themes conceptualised using Roger's Diffusion of Innovation Theory (Rogers, 1995, 2002, 2004).
Findings
A number of perceived barriers to adoption of BFO throughout CRI were identified within the social system, including a lack of IT resources and skills. However, there were numerous perceived benefits of adoption of BFO throughout CRI, including broadening access to effective interventions to support recovery from substance dependence, and promoting digital inclusion. Along with the solutions that were found to the identified barriers to implementation, intentions around longer-term continuation of adoption of the programme were reported, with this process being supported through changes to both the social system and the individuals within it.
Research limitations/implications
The introduction of innovations such as BFO within large organisations like CRI can be perceived as being disruptive, even when individuals within the organisation recognise its benefits. For successful adoption and implementation of such innovations, changes in the social system are required, at organisational and individual levels.
Practical implications
The learning points from this study may be relevant to the substance misuse sector, and more widely to criminal justice, health and social care organisations.
Originality/value
This study is the first of its kind to use a qualitative approach to examine processes of implementation of CAT for substance misuse within a large treatment and recovery organisation.
Details
Keywords
Pervasive analytics act as a prominent role in computer-aided prediction of non-communicating diseases. In the early stage, arrhythmia diagnosis detection helps prevent the cause…
Abstract
Purpose
Pervasive analytics act as a prominent role in computer-aided prediction of non-communicating diseases. In the early stage, arrhythmia diagnosis detection helps prevent the cause of death suddenly owing to heart failure or heart stroke. The arrhythmia scope can be identified by electrocardiogram (ECG) report.
Design/methodology/approach
The ECG report has been used extensively by several clinical experts. However, diagnosis accuracy has been dependent on clinical experience. For the prediction methods of computer-aided heart disease, both accuracy and sensitivity metrics play a remarkable part. Hence, the existing research contributions have optimized the machine-learning approaches to have a great significance in computer-aided methods, which perform predictive analysis of arrhythmia detection.
Findings
In reference to this, this paper determined a regression heuristics by tridimensional optimum features of ECG reports to perform pervasive analytics for computer-aided arrhythmia prediction. The intent of these reports is arrhythmia detection. From an empirical outcome, it has been envisioned that the project model of this contribution is more optimal and added a more advantage when compared to existing or contemporary approaches.
Originality/value
In reference to this, this paper determined a regression heuristics by tridimensional optimum features of ECG reports to perform pervasive analytics for computer-aided arrhythmia prediction. The intent of these reports is arrhythmia detection. From an empirical outcome, it has been envisioned that the project model of this contribution is more optimal and added a more advantage when compared to existing or contemporary approaches.
Details
Keywords
Saroj Kumar Pandey and Rekh Ram Janghel
According to the World Health Organization, arrhythmia is one of the primary causes of deaths across the globe. In order to reduce mortality rate, cardiovascular disease should be…
Abstract
Purpose
According to the World Health Organization, arrhythmia is one of the primary causes of deaths across the globe. In order to reduce mortality rate, cardiovascular disease should be properly identified and the proper treatment for the same should be immediately provided to the patients. The objective of this paper was to implement a better heartbeat classification model which will work better than the other implemented heartbeat classification methods.
Design/methodology/approach
In this paper, the ensemble of two deep learning models is proposed to classify the MIT-BIH arrhythmia database into four different classes according to ANSI-AAMI standards. First, a convolutional neural network (CNN) model is used to classify heartbeats on a raw data set. Secondly, four features (wavelets, R-R intervals, morphological and higher-order statistics) are extracted from the data set and then applied to a long short-term memory (LSTM) model to classify the heartbeats. Finally, the ensemble of CNN and LSTM model with sum rule, product rule and majority voting has been used to identify the heartbeat classes.
Findings
Among these, the highest accuracy obtained is 98.58% using ensemble method with product rule. The results show that the ensemble of CNN and BLSTM has offered satisfactory performance compared to other techniques discussed in this study.
Originality/value
In this study, we have developed a new combination of two deep learning models to enhance the performance of arrhythmia classification using segmentation of input ECG signals. The contributions of this study are as follows: First, a deep CNN model is built to classify ECG heartbeat using a raw data set. Second, four types of features (R-R interval, HOS, morphological and wavelet) were extracted from the raw data set and then applied to the bidirectional LSTM model to classify the ECG heartbeat. Third, combination rules (sum rules, product rules and majority voting rules) were tested to ensure the accumulated probabilities of the CNN and LSTM models.
Details
Keywords
Nicholas O'Regan and Abby Ghobadian
The purpose of this paper is to demonstrate how key strategic decisions are made in practice at successful FTSE 100 companies.
Abstract
Purpose
The purpose of this paper is to demonstrate how key strategic decisions are made in practice at successful FTSE 100 companies.
Design/methodology/approach
The paper is based on a semi‐structured interview with Ms Cynthia Carroll, Chief Executive of Anglo American plc.
Findings
The interview outlines a number of important factors on: the evolution of strategy within Anglo American, strategy execution, leadership at board and executive levels, and capturing synergies within the company.
Originality/value
The paper bridges the gap between theory and practice. It provides a practical view and demonstrates how corporate leaders think about key strategic issues.
Details
Keywords
Louise Gardiner, Catherine Rubbens and Elena Bonfiglioli
Focuses on “big business” and what is seen as its growing influence on the state of the world and argues that increasing globalization is posing significant challenges that…
Abstract
Focuses on “big business” and what is seen as its growing influence on the state of the world and argues that increasing globalization is posing significant challenges that require new thinking about global governance, particularly with regard to international trade. Businesses are required to operate within legislative and economic frameworks created by governments and should be helped to develop global, values‐based systems of management rooted in internationally accepted principles. Concludes that corporate social responsibility will only make a visible difference if the concept is fully integrated into corporate principles and practices, and if progress is monitored over time.