Search results

Organizations in many domains generate a considerable amount of heterogeneous data every day. Such data can be processed to enhance these organizations’ decisions in real time. However, storing and processing large and varied datasets (known as big data) is challenging to do in real time. In machine learning, streaming feature selection has always been considered a superior technique for selecting the relevant subset features from highly dimensional data and thus reducing learning complexity. In the relevant literature, streaming feature selection refers to the features that arrive consecutively over time; despite a lack of exact figure on the number of features, numbers of instances are well-established. Many scholars in the field have proposed streaming-feature-selection algorithms in attempts to find the proper solution to this problem. This paper presents an exhaustive and methodological introduction of these techniques. This study provides a review of the traditional feature-selection algorithms and then scrutinizes the current algorithms that use streaming feature selection to determine their strengths and weaknesses. The survey also sheds light on the ongoing challenges in big-data research.

This chapter analyzes what happens to media use when everyday life is suddenly disrupted, focusing on how the COVID-19 pandemic transformed work, socializing, communication and everyday living. The empirical case is changing media use in Norway during the pandemic, building on a qualitative questionnaire survey conducted in early lockdown, and follow-up interviews eight months later. Expanding on the ideas of destabilization of media repertoires developed in the former chapter, this analysis discusses transforming media repertoires as more digital, as less mobile (but still smartphone-centric) and as essentially social. The chapter further explains new concepts for pandemic media use practices, such as doomscrolling and Zoom fatigue.

Tracing the development of a parallel-engaged pedagogy of care that extended and adapted the critical and transformative pedagogies of Freire, De Sousa Santos and hooks to the South African context. The development of this transformative pedagogy addresses the local conditions of an architectural design studio at a postcolonial, post-Apartheid and post “Fees must Fall” protests South African university. This pedagogy used practice-based design research to build a more conscious, critical and careful design practice in both students and educators.

The pedagogy was developed through participatory action research, over five years, from 2019 to 2023 including two years of the COVID-19 pandemic. Parallel and active engagement of students and educators within a nurturing and caring environment evolved from year to year, through a conscious and critical reflection on the process. Student surveys, reflective essays and focus groups unearth the impact of the parallel-engaged pedagogy of care.

The parallel-engaged pedagogy of care was shown to support and scaffold students becoming more conscious, critical and careful in their design practices validating diverse lived experiences as generative for design and important for social justice and transformative equity.

The parallel-engaged pedagogy of care is part of a global shift to more transformative pedagogies that address student diversity and decoloniality.

Through dismantling traditional hierarchical teaching modes, the pedagogy is more student-led, agile and adaptable. Through centring and demonstrating care in the pedagogy, students are encouraged to develop both self-care and care in their design practice. This is especially critical in the South African context where the cultural capital of the institution, with its roots in colonial and Apartheid education differs from that of the majority of students of colour.

This work presents a novel approach by considering teaching learning based optimization (TLBO) and radial basis function neural networks (RBFNs) for building a classifier for the databases with missing values and irrelevant features. The least square estimator and relief algorithm have been used for imputing the database and evaluating the relevance of features, respectively. The preprocessed dataset is used for developing a classifier based on TLBO trained RBFNs for generating a concise and meaningful description for each class that can be used to classify subsequent instances with no known class label. The method is evaluated extensively through a few bench-mark datasets obtained from UCI repository. The experimental results confirm that our approach can be a promising tool towards constructing a classifier from the databases with missing values and irrelevant attributes.