Suchergebnisse

This study provides an insight into the visual information (colours, symbols) of waste classification based on the three principles of closure, similarity and continuation of Gestalt theory. A field survey of Xiamen University Town in China and a survey of 1,000 local and international university students in the area were used to understand the level of awareness of visual information on waste recycling and segregation. The study found that the current level of awareness of visual classification information (colours, symbols) in the Xiamen University Town urban area and among students is low. Visual messages must convey accurate and standardised information such as colours and symbols. In addition, the purpose of this study was to illustrate the need for accuracy in visual information. This study concludes the need for uniform colour and symbol standards for waste recycling and segregation under the Gestalt theory to help achieve SDG goal 12, responsible consumption and production, as this study highlights the potential ripple effect on future stakeholders, especially considering the international mobility of university students, who epitomise global diversity. As users travelled across countries, ambiguous visual messages about waste classification became a key issue in responding to UN advocacy for a sustainable future. Addressing and correcting these visual discrepancies is critical to effective waste management strategies on a global scale.

This study aims to enhance business sustainability in the context of Higher Education Institutions (HEIs) by utilizing AI and forecasting techniques. It explores the development and comparison of prediction models, including the use of dashboard development, to support decision-making processes within HEIs. The study covers various aspects, including the background of forecasting and prediction models, the use of specific models such as the Prophet Model, Long Short-Term Memory (LSTM) Model, and Polynomial Regression Model, as well as the importance of dashboards for HEIs. The methodology section outlines the data collection and preparation process, model selection, approach, diagrams, functional and non-functional requirements, justification of tools, and libraries and models used. The implementation section delves into the system design and development of the dashboard, including the login page, homepage, forecast page, and insert data page. As for the findings, the LSTM Model has proven to be the most accurate and suitable model to be implemented for forecasting student enrolment data in this study. The dashboard's future enhancements involve adding more faculties, predictive features for resource allocation, refining the visual identity, improving user registration on the login page, and exploring better models for student enrolment predictions. Overall, the study provides valuable insights into the application of AI and forecasting techniques in HEIs, aiming to enhance business sustainability and decision-making processes. It contributes to the growing body of knowledge on the use of technology-enabled AI in higher education institutions, with a focus on forecasting student enrolment data and developing prediction models.