Search results

Depression is a mental health problem characterized by a persistent sense of sadness and loss of interest. EEG signals are regarded as the most appropriate instruments for diagnosing depression because they reflect the operating status of the human brain. The purpose of this study is the early detection of depression among people using EEG signals.

(i) Artifacts are removed by filtering and linear and non-linear features are extracted; (ii) feature scaling is done using a standard scalar while principal component analysis (PCA) is used for feature reduction; (iii) the linear, non-linear and combination of both (only for those whose accuracy is highest) are taken for further analysis where some ML and DL classifiers are applied for the classification of depression; and (iv) in this study, total 15 distinct ML and DL methods, including KNN, SVM, bagging SVM, RF, GB, Extreme Gradient Boosting, MNB, Adaboost, Bagging RF, BootAgg, Gaussian NB, RNN, 1DCNN, RBFNN and LSTM, that have been effectively utilized as classifiers to handle a variety of real-world issues.

1. Among all, alpha, alpha asymmetry, gamma and gamma asymmetry give the best results in linear features, while RWE, DFA, CD and AE give the best results in non-linear feature. 2. In the linear features, gamma and alpha asymmetry have given 99.98% accuracy for Bagging RF, while gamma asymmetry has given 99.98% accuracy for BootAgg. 3. For non-linear features, it has been shown 99.84% of accuracy for RWE and DFA in RF, 99.97% accuracy for DFA in XGBoost and 99.94% accuracy for RWE in BootAgg. 4. By using DL, in linear features, gamma asymmetry has given more than 96% accuracy in RNN and 91% accuracy in LSTM and for non-linear features, 89% accuracy has been achieved for CD and AE in LSTM. 5. By combining linear and non-linear features, the highest accuracy was achieved in Bagging RF (98.50%) gamma asymmetry + RWE. In DL, Alpha + RWE, Gamma asymmetry + CD and gamma asymmetry + RWE have achieved 98% accuracy in LSTM.

A novel dataset was collected from the Central Institute of Psychiatry (CIP), Ranchi which was recorded using a 128-channels whereas major previous studies used fewer channels; the details of the study participants are summarized and a model is developed for statistical analysis using N-way ANOVA; artifacts are removed by high and low pass filtering of epoch data followed by re-referencing and independent component analysis for noise removal; linear features, namely, band power and interhemispheric asymmetry and non-linear features, namely, relative wavelet energy, wavelet entropy, Approximate entropy, sample entropy, detrended fluctuation analysis and correlation dimension are extracted; this model utilizes Epoch (213,072) for 5 s EEG data, which allows the model to train for longer, thereby increasing the efficiency of classifiers. Features scaling is done using a standard scalar rather than normalization because it helps increase the accuracy of the models (especially for deep learning algorithms) while PCA is used for feature reduction; the linear, non-linear and combination of both features are taken for extensive analysis in conjunction with ML and DL classifiers for the classification of depression. The combination of linear and non-linear features (only for those whose accuracy is highest) is used for the best detection results.

The multimedia data are also known as interactive data. The multimedia is progressively turning into the “greatest big data” which are the most imperative and important hotspot for bits of knowledge and data. The multimedia data also provide incredible open door for the multimedia computing in the big data centric as a functioning disciplinary research field. As per current technological usage in terms of Internet or smart devices, the data manipulate in the form of digital. Massive multimedia data have been produced in the different forms like text, image, video, and audio which is shared among vast number of people. The multimedia data are real-time unstructured, heterogeneous, and multimodal. It has vast scope to mine model, learn, and analyze the service provided by multimedia. Of course, some primarily level challenges need to be addressed like analysis, storage, retrieval, and data processing. The most complicated thing in multimedia big data (MMBD) analytics is that the computer cannot understand higher level of semantics. The quality of experience (QoE) is the most evolving part of MMBD which are directly intended with storage and performance. MMBD are highly resource intensive. They often require dedicated processing capabilities in terms of graphical processing unit (GPU). An advance-level storage-related mechanism is also needed for efficient parallel processing, transmission, and presentation. Generally, non-multimedia data are always forming in text which is normally understood by machine. The multimedia data always in the form of videos are easily understood by human compared to textual data, but it is more complex task to make it understandable to machines. The MMBD performs the task by converting the human language to computer language in an efficient manner. This chapter is also introducing salient features of MMBD. The main aim of this chapter is to cover the fundamentals for MMBD computing and feasibility study. The chapter explores the technical problems and challenges to be addressed. It also focuses on methodologies and approaches that are available from the perspectives of MMBD computing life cycle. The chapter may be beneficial for the readers to understand the features, importance and application of MMBD.

Conventional economic contexts and value creation exert on the extensive use of intangible resources whose value is much greater than the tangible assets. In particular, intellectual capital (IC) is recognized as an important source of value creation for firms. However, the field of IC is majorly dominated by large firms, and little has been done in exploring IC in small and medium enterprises (SMEs). Within this context, the purpose of this article is to contribute to the body of literature on IC in the SMEs context by investigating the different dynamics of IC and understanding its impact on their organizational performance and processes.

The study has contextualized an integrative review of literature collected from Web of Science (WoS) and further analyzed integrating the bibliometric and manual review in a systematic approach.

The paper summarizes the key findings highlighting how SMEs can grasp IC in their core competencies and operational processes to achieve sustainable business performance. The study provides theoretical propositions highlighting the conceptual underpinnings of the literature on IC in SMEs and proposed methods outlining the methodological issues arising out of the diverse empirical/quantitative approaches adopted in the previous literature. Furthermore, empirical findings from the literature show that IC management affects a broad range of financial performance metrics in SMEs, however, sometimes with unexpected and mixed results. Hence, more research to replicate prior studies and corroborate extant research in both similar and different contexts would be desirable.

The study adopts an integrative review to understand the context of IC in SMEs; however, it does not study the synergy between varied IC components individually and their role in SMEs performance. Furthermore, the review relates IC to SMEs and does not cover the role of IC in large corporations.

The originality of this paper lies in its contribution to the body of knowledge in the field of IC and SMEs by exploring IC's impact on SME performance, especially the market performance, knowledge management (KM), strategic business models, sustainability performance (corporate social responsibility [CSR]), innovation and their intercollaborations (varied stakeholders).

The present paper explores and analyses various aspects of entrepreneurial marketing in the different regions (developed or developing) and attempts to consolidate the extant literature in the field of entrepreneurial marketing and suggests future directions for research.

The research questions developed by the paper deal with (1) comparison of entrepreneurial marketing in the developed and developing world; (2) methodological approaches used in entrepreneurial marketing; (3) the constructs or theories used in literature; (4) the existing research gaps and potential future directions in research of entrepreneurial marketing. To answer the same, we conduct a systematic literature review of the 82 research papers extracted from the Web of Science (WoS) and ScienceDirect databases.

The findings are presented in the form of descriptive and results. The descriptive findings show that more studies are needed in developing nations, introducing or developing entrepreneurial marketing conceptually, using mixed research designs, having objective measurements of constructs and contributing to comparative studies. The results discuss the constructs and theories employed in the extant literature and suggest that theories like human capital, creation, causation or trust are fundamental to study entrepreneurial marketing.

The paper adopts the existing entrepreneurial, marketing, innovation, and customer orientation (EMICO) framework and further develops an organizing framework to discover several gaps in the existing literature that can further be explored and promote the development of research in entrepreneurial marketing.

The purpose of this paper is to offer a complete guide to a qualitative method for capturing critical moments of managerial practice that combines interpretative phenomenological analysis (IPA) and existential hermeneutic phenomenology (EHP).

This article is based on the findings of extensive research and describes in detail the specific steps that must be taken for complete replication of research. The research uses methods of IPA and critically develops the EHP framework with an emphasis on the analysis of interpersonal relationships.

Depending on the testing of the research method in practice, the article evaluates the IPA-EHP method as suitable for the research on critical moments of managerial lived experience, considering the causes of the crisis.

This article is based on demand from academics who would like to use this method to analyse managerial practice. Especially now, at a time associated with a number of challenging events, such as the ongoing COVID-19 pandemic, qualitative research is gaining in importance, even in management science. The original interpretative framework based on the phenomenology of Fink and Patočka is appropriate in this respect.