Search results

Hundreds of thousands of deaths each year in the world are caused by breast cancer (BC). An early-stage diagnosis of this disease can positively reduce the morbidity and mortality rate by helping to select the most appropriate treatment options, especially by using histological BC images for the diagnosis.

The present study proposes and evaluates a novel approach which consists of 24 deep hybrid heterogenous ensembles that combine the strength of seven deep learning techniques (DenseNet 201, Inception V3, VGG16, VGG19, Inception-ResNet-V3, MobileNet V2 and ResNet 50) for feature extraction and four well-known classifiers (multi-layer perceptron, support vector machines, K-nearest neighbors and decision tree) by means of hard and weighted voting combination methods for histological classification of BC medical image. Furthermore, the best deep hybrid heterogenous ensembles were compared to the deep stacked ensembles to determine the best strategy to design the deep ensemble methods. The empirical evaluations used four classification performance criteria (accuracy, sensitivity, precision and F1-score), fivefold cross-validation, Scott–Knott (SK) statistical test and Borda count voting method. All empirical evaluations were assessed using four performance measures, including accuracy, precision, recall and F1-score, and were over the histological BreakHis public dataset with four magnification factors (40×, 100×, 200× and 400×). SK statistical test and Borda count were also used to cluster the designed techniques and rank the techniques belonging to the best SK cluster, respectively.

Results showed that the deep hybrid heterogenous ensembles outperformed both their singles and the deep stacked ensembles and reached the accuracy values of 96.3, 95.6, 96.3 and 94 per cent across the four magnification factors 40×, 100×, 200× and 400×, respectively.

The proposed deep hybrid heterogenous ensembles can be applied for the BC diagnosis to assist pathologists in reducing the missed diagnoses and proposing adequate treatments for the patients.

In this research, arbitrage opportunity is tested between the yield rates computed by the NSS model, and the computed forward rates between conventional and Islamic finance to see any arbitrage opportunity. The research questions are the conventional and Islamic finance yields at the same level and equal to each other to avoid arbitrage? Whether conventional and Islamic forward rates differ significantly and thus create any arbitrage opportunity. This study aims to find the presence or absence of arbitrage between conventional and Islamic finance yield rates.

The NSS model is the latest model in calculating yield and forward rates. In the method the error level is minimized so expected yield rate and given yield rate both converged (Vahidin and Anastasios, 2020). When they converged it gives the researchers all six months’ yield rates. For the Nelson Siegal method, all the six months’ yield rates are available and these yield rates can be used to compute the forward rates.

The authors concluded there is a significant difference between the conventional yield rate and the Islamic yield rate. It suggests that because there are significant differences, its suggest arbitrage is possible. So anyone interested in making a guaranteed profit. The conventional yield rates are lower; hence, anyone can borrow from the conventional finance system and invest the money in the Islamic financial system because investments are getting higher rates of income in the form of yield rate in Islamic Finance. So, one can make money because of this difference. Statistically, it is possible to make money, but practically, the authors observed the difference, however it is very meager. The arbitrage opportunity between Islamic finance and conventional finance will not affect the economy because the significant difference is too small. The disturbance in the arbitrage opportunity due to the values is very meager and insignificant.

This research does not address the derivative contracts’ role in risk management; future researchers could take up this as another research.

This research will be beneficial for financial institutions, especially institutional investors. Besides, this research will help the regulators and investment bankers in assisting where and future losses especially bond portfolios in conventional finance and Islamic finance. This study will also contribute and help the asset manager of mutual funds in the mutual fund industries.

In effect, this research will strengthen the financial system, capital market and bond market, derivative contracts such as options contracts, futures contracts, swap contracts and forward contracts will use computed forward rates for assessing future losses (value at risk [VaR]) and to hedge them (Balakrishnan, 2020).

As this topic is rarely studied it will increase the literature present in this domain.

This paper aims to propose an approach to automatically annotate a large corpus in Arabic dialect. This corpus is used in order to analyse sentiments of Arabic users on social medias. It focuses on the Algerian dialect, which is a sub-dialect of Maghrebi Arabic. Although Algerian is spoken by roughly 40 million speakers, few studies address the automated processing in general and the sentiment analysis in specific for Algerian.

The approach is based on the construction and use of a sentiment lexicon to automatically annotate a large corpus of Algerian text that is extracted from Facebook. Using this approach allow to significantly increase the size of the training corpus without calling the manual annotation. The annotated corpus is then vectorized using document embedding (doc2vec), which is an extension of word embeddings (word2vec). For sentiments classification, the authors used different classifiers such as support vector machines (SVM), Naive Bayes (NB) and logistic regression (LR).

The results suggest that NB and SVM classifiers generally led to the best results and MLP generally had the worst results. Further, the threshold that the authors use in selecting messages for the training set had a noticeable impact on recall and precision, with a threshold of 0.6 producing the best results. Using PV-DBOW led to slightly higher results than using PV-DM. Combining PV-DBOW and PV-DM representations led to slightly lower results than using PV-DBOW alone. The best results were obtained by the NB classifier with F1 up to 86.9 per cent.

The principal originality of this paper is to determine the right parameters for automatically annotating an Algerian dialect corpus. This annotation is based on a sentiment lexicon that was also constructed automatically.

This study aims to examine the impact of liquidity creation per capita of tri-banking system and dual banking system on real economic output.

This study applies the feasible generalized least square framework on the data set of 12 countries, 8 with tri-banking system and 4 with dual banking system over the 2013–2022 period.

The findings show that for countries with tri-banking system, only liquidity creation by full-fledged Islamic Banks (FIBs) and hybrid conventional banks (HCBs) spurs real output, with the impact of HCBs being greater than that of FIBs. Nonetheless, for countries with dual banking system, both FIBs’ and pure CBs’ (PCBs) liquidity creation fosters real output. However, the impact of PCBs is slightly greater. Finally, Granger causality results confirm only the positive impact of the tri-banking system’s liquidity creation on real output.

For countries with tri-banking system, only HCBs’ and FIBs’ liquidity creation spurs real output. However, for countries with dual banking system, liquidity created by both FIBs and PCBs fosters real output. However, only liquidity created by tri-banking system has a unidirectional Granger causality with real output.

To the best of the authors’ knowledge, this is the first study that examines the impact of the banking subsystem liquidity creation on real economic output. Examining the impact of the liquidity created by this banking subsystem on the real economy is important for both regulators and policymakers.

Islamic finance is an alternative approach of financial intermediation based on risk-sharing and asset-backed operations, which evolved substantially in recent years in academic research raising the need for quantitative studies to address the intellectual development and scientific performance of this field. This study aims to provide quantitative statistics and comprehensive review of the key influential and intellectual structure of Islamic finance literature.

The authors apply the trending and cutting-edge quali-quantitative approach of bibliometric citation analysis. This study reviews 1,940 English studies and review papers published in scientific journals indexed by the Scopus database from 1983 to 2019. RStudio, VOSviewer and Excel’s software are used to analyze the collected data and apply the bibliometric tests.

The results identify the leading academic authors, journals, institutions and countries with relation to Islamic finance. The authors also propose six main research themes in this field, which are as follows: Islamic finance – fundamentals, growth and legitimacy; customer’s attitude and perception toward Islamic finance; accounting and social reporting of Islamic finance; performance and risk management of Islamic finance; Islamic financial markets; and efficiency of Islamic financial institutions. Lastly, the authors identify research gaps in the existing Islamic finance literature and present 24 future research directions.

The data in this study is confined only to the Scopus database of English papers and reviews. It also considers papers directly related to the field of Islamic finance.

To the best of the authors’ knowledge, this paper is one of the first to address the literature of Islamic finance from a bibliometric aspect. The results of this study along with future research questions will help researchers and practitioners to further explore and stand on firm quantitative bases regarding the scientific development of Islamic finance.

Demand planning (DP) is a key element of supply chain management (SCM) and is widely regarded as an important catalyst for improving supply chain performance. Regarding the availability of technology to process large amounts of data, artificial intelligence (AI) has received increasing attention in the DP literature in recent years, but there are no reviews of studies on the application of AI in supply chain DP. Given the importance and value of this research area, we aimed to review the current body of knowledge on the application of AI in DP to improve SCM performance.

Using a systematic literature review approach, we identified 141 peer-reviewed articles and conducted content analysis to examine the body of knowledge on AI in DP in the academic literature published from 2012 to 2023.

We found that AI in DP is still in its early stages of development. The literature is dominated by modelling studies. We identified three knowledge clusters for AI in DP: AI tools and techniques, AI applications for supply chain functions and the impact of AI on digital SCM. The three knowledge domains are conceptualised in a framework to demonstrate how AI can be deployed in DP to improve SCM performance. However, challenges remain. We identify gaps in the literature that make suggestions for further research in this area.

This study makes a theoretical contribution by identifying the key elements in applying AI in DP for SCM. The proposed conceptual framework can be used to help guide further empirical research and can help companies to implement AI in DP.

This paper aims to offer a wider examination of the research concerning entrepreneurship characteristics in the Middle East and North Africa (MENA) region via a review of recent studies relevant to this topic. Research publications concerning entrepreneurship within the MENA region evidence growing interest in this field of study, with the potential to boost and drive future economic development and growth. This focus within entrepreneurship research is because of the economic development in the region, which is becoming increasingly important for policymakers and businesses.

The author performed a systematic literature review to produce robust information about entrepreneurship in the MENA region, followed by a thematic analysis to identify key research themes within each category.

Despite the growth in entrepreneurship research in the MENA region, research on certain factors is lacking. An analysis of 271 studies published between 2009 and 2019 identifies 9 main research categories, within which 30 themes have attracted significant academic attention. Female entrepreneurship and gender, youth entrepreneurship and entrepreneurship behaviour and orientation are the three key categories influencing perspectives on entrepreneurship in the MENA region. This study highlights research gaps and provides recommendations to guide future research on the sustainable development of entrepreneurship in the MENA region.

This paper highlights trends in entrepreneurship research amongst scholars within the MENA region and suggests paths for future research efforts.

The purpose of the study is to propose a framework for fleet management and make suitable distribution solution choices in the food industry.

This study reviews the literature to examine food distribution criteria. These criteria are used in the analytic hierarchy process (AHP) assessment and combined with discrete events simulation in a structured framework, which is validated through an empirical study.

The empirical case results demonstrate that both the AHP and discrete events simulation converge toward the same solution in most cases.

This study contributes to the literature on distribution management and develops a framework that can both guide future research and aid logistics practitioners in analysing distribution decision-making systems in dynamic environments.

This study aims to provide empirical insights pertaining to the impact of trait emotional intelligence on the mental well-being of students in higher education institutions (HEIs) in India.

In the current study, responses from a total of 252 students were randomly taken from different universities of Uttarakhand (India). The analysis was done using structural equation modelling AMOS 23.

The current study empirically established the positive impact of trait emotional intelligence (TEI) on the mental well-being of students and highlighted the relevance of TEI in curbing the psychological distress in students of HEIs.

This study endeavours to bridge the empirical and population gap by examining the emotional intelligence and its impact on mental well-being of the students of Indian HEIs, where studies are still scant and demand massive exploration of the perceptions of students. Strong emotional intelligence is pivotal in strengthening the mental well-being of students so that they can make appropriate decisions pertaining to their career and personal life.