Search results

The purpose of this study is to propose an alternative efficient 3D emotion recognition model for variable-length electroencephalogram (EEG) data.

Classical AMIGOS data set which comprises of multimodal records of varying lengths on mood, personality and other physiological aspects on emotional response is used for empirical assessment of the proposed overlapping sliding window (OSW) modelling framework. Two features are extracted using Fourier and Wavelet transforms: normalised band power (NBP) and normalised wavelet energy (NWE), respectively. The arousal, valence and dominance (AVD) emotions are predicted using one-dimension (1D) and two-dimensional (2D) convolution neural network (CNN) for both single and combined features.

The two-dimensional convolution neural network (2D CNN) outcomes on EEG signals of AMIGOS data set are observed to yield the highest accuracy, that is 96.63%, 95.87% and 96.30% for AVD, respectively, which is evidenced to be at least 6% higher as compared to the other available competitive approaches.

The present work is focussed on the less explored, complex AMIGOS (2018) data set which is imbalanced and of variable length. EEG emotion recognition-based work is widely available on simpler data sets. The following are the challenges of the AMIGOS data set addressed in the present work: handling of tensor form data; proposing an efficient method for generating sufficient equal-length samples corresponding to imbalanced and variable-length data.; selecting a suitable machine learning/deep learning model; improving the accuracy of the applied model.

This will not be an overstatement to state that the micro, small and medium enterprise (MSME) industry is crucial and the vital driver of the world economy. It covers different fields and dimensions such as defense products, electrical components and low-cost products. The sector plays a vital role in rendering work with low capital expenditure and is one of the emerging pillars of the Indian economy. Given the significance of this sector in contributing towards India's gross domestic product (GDP), it becomes appropriate to resolve all the issues related to MSME on a primary basis for ensuring required support. The recent global pandemic of COVID-19 has impacted this sector to a great extent. This research study targets the MSME industry and points out the directly linked enablers adding to improve the sector's resiliency and sustainability. Therefore, identification and the interrelationship between the MSME enablers need to be studied, which helps make a preliminary list that deals with their impedance benefaction towards resiliency increment.

The writers have done a comprehensive literature analysis of the enablers for the MSME sector to enable effectively and efficiently during emergencies and pandemics. An endeavor has been made on the enablers to order them by utilizing the modified Total Interpretative Structure Modelling (m-TISM) technique. Authentication of this research work highlights the significance of enablers and their position in a hierarchical structure. Further, MICMAC investigation on the recognized enablers is performed to arrange them in the four quadrants on their dependence and driving power.

The authors have attempted to predict the significance of the MSME sector and its essential contribution to the development of India's economy. The result of m-TISM in the current research work revealed the essential commitment of a hierarchical design dealing with the MSME considering the viewpoint of future development. The well-planned traditional design in the MSME helps establish better government policies and programs and transport infrastructure.

Every research study has a few restrictions. Likewise, the boundaries of the current study are that inputs collated for fostering the models are from a few specialists that may not mirror the assessment of the whole MSME sector.

The MSME sector is the developing sector in the current day, and it is needed to keep supporting the sector for the country's development. The current study has set out the functional establishment to improve MSME practicality. In addition, the research highlights the accountability of the MSME authorities to go with the identified enablers having solid driving power for successful usage of the available resources. This will help the MSME development and add value to practitioners and policymakers in the future.

The growth of this sector is essential for the development of the economy and the development of a nation. The current study presents a unique structure that gives a superior comprehension of the enablers. It will help play a crucial role in developing the MSME area. The structure model developed with the assistance of m-TISM and MICMAC examine the identified enablers with inputs from experts in the field. The hierarchy developed from the study recognized the enablers located on their commitment of suitability development of the MSME field.

The Multi-Stakeholder Recommendation System learns consumer and producer preferences to make fair and balanced recommendations. Exclusive consumer-focused studies have improved the recommendation accuracy but lack in addressing producers' priorities for promoting their diverse items to target consumers, resulting in minimal utility gain for producers. These techniques also neglect latent and implicit stakeholders' preferences across item categories. Hence, this study proposes a personalized diversity-based optimized multi-stakeholder recommendation system by developing the deep learning-based diversity personalization model and establishing the trade-off relationship among stakeholders.

The proposed methodology develops the deep autoencoder-based diversity personalization model to investigate the producers' latent interest in diversity. Next, this work builds the personalized diversity-based objective function by evaluating the diversity distribution of producers' preferences in different item categories. Next, this work builds the multi-stakeholder, multi-objective evolutionary algorithm to establish the accuracy-diversity trade-off among stakeholders.

The experimental and evaluation results over the Movie Lens 100K and 1M datasets demonstrate that the proposed models achieve the minimum average improvement of 40.81 and 32.67% over producers' utility and maximum improvement of 7.74 and 9.75% over the consumers' utility and successfully deliver the trade-off recommendations.

The proposed algorithm for measuring and personalizing producers' diversity-based preferences improves producers' exposure and reach to various users. Additionally, the trade-off recommendation solution generated by the proposed model ensures a balanced enhancement in both consumer and producer utilities.

This paper developed a theoretical and research framework by identifying the behavioral biases in investment decision and by presenting a review of the available literature in the field of behavior finance-related biases. This paper aims to present a compressive review of the literature available in the public domain in past five decades on behavior finance and biases and its role in investment decision-making process. It also covers insights on the subject for developing a deeper understating of the behavior of investor and related biases.

The work follows the comprehensive literature review approach to review the available literatures. The review carried out on different parameters such as year of publication, journal of publication, country, type of research, data type, statistical technique used and biases identified. This is a funnel approach to decrease the number of behavior biases up to six for further research.

Most of the existing works have summarized behavior finance as an emerging area in finance. This indicates the limited valuable research in developing economy in this area. This literature review helps in identifying major research gap in this domain. It helps in identifying the behavior biases which work dominantly in investment decision-making. It would be interesting to explore the area of behavior biases and their impact on investment decision of individual investors in India.

This paper worked on literature prevailing on the subject and available on various online research data source and search engines. It covers a long time frame of almost five decades (1970-2015). This paper is an attempt to look at the impact of behavior finance and biases and its role in investment decision-making process of the investor behavior. This study builds up a strong theoretical framework for researchers and academicians by detailed demonstration of available literature on behavior biases.