Smart City Digital Twins (SCDT) are virtual replicas of cities (or parts thereof) that integrate real-time data from various sources to enable simulation, monitoring, and optimization of urban systems for more efficient and sustainable urban management. In this article, we provide a survey of modular SCDTs, covering standardization and key enabling technologies. Modular hardware and software architectures pave way for standardization, which is crucial for efficient maintenance as well as scalability and portability to new application domains.
Diabetic retinopathy (DR) is a major global cause of blindness, underscoring the critical need for early and accurate detection. This study addresses this challenge by conducting an in-depth comparative analysis of various image processing techniques coupled with the state-of-the-art EfficientNetB0 model for DR identification. The researchers employed retinal images from the Asia-Pacific Teleophthalmology Society (APTOS) 2019 Blindness Detection competition on Kaggle, a valuable dataset for this purpose. The study considers five image processing methods: Median Subtraction, Ben Graham's Filter, Adaptive Histogram Equalization, Histogram Normalization, and Selective Gamma Correction. These techniques aim to enhance image quality and information content, which is crucial for training the model effectively. The study's primary performance metric is accuracy, recall, precision, and F1 score, which measures the model's ability to classify images correctly. The outcomes reveal that the choice of image pre-processing techniques significantly influences the model's performance. In summary, the study demonstrates that by combining advanced image pre-processing methods with a powerful deep learning model, Ben Graham's Filter can notably enhance diabetic retinopathy detection performance with 86
AI is increasingly present in creative industries, including industrial design. However, there is insufficient understanding of professionals' perceptions of such tools. This knowledge is crucial for fostering adoption and trust in technology. The article explores designers' perceptions and trust in these tools and examines the possibilities for integration and collaboration. It employs a mixed-methods explanatory sequential approach to investigate these professionals' trust in AI during the creative stages of New Product Development (NPD), such as sketching and rendering. The results reveal designers' limited trust in AI tools, influenced equally by their perceptions of the artifacts' risk, competency, and benevolence. Participants envisioned AI as a future adjunct to their toolkit, pinpointing ethics, transparency, tool control, and efficiency as areas for improvement. The study offers insights into fostering trust and presents design recommendations for future AI-enabled applications in industrial design. It sheds light on AI's potential as a creative partner, underlining the need for ethical and transparent integration.
Continuous monitoring of the risk of civil unrest events and predicting their occurrence is of paramount importance. This task involves identifying and understanding the primary factors that contribute to such events, especially in regions with unique dynamics, such as South Africa. Although many global and South African-specific studies have conducted research on predicting the frequency or probability of these events, there is a notable gap in identifying the influential factors behind them. This study unveiled several contributing factors, including demanding behaviour, power outages, service delivery, wage disputes, acts of violence, gender-based conflicts, and unemployment rates. These factors, individually or collectively, contribute to the complexity of civil unrest in the region. The 2021 South African unrest, also known as the July 2021 riots, the Zuma unrest, or Zuma riots, serves as an example. This event was triggered by the imprisonment of former president Jacob Zuma for contempt of court, inciting his followers to demand his release, a situation aligning with the ‘demanding behaviour’ influential factor identified in our study. We used advanced data analysis and machine learning techniques to explore these factors. Specifically, the Logit model was used to determine the coefficients that optimally fit the data, establishing significant relationships between these factors and incidents of civil unrest. Our research not only offers insights on influential factors, but also presents a predictive framework. We evaluated logistic regression, support vector clustering, decision tree classifier, and random forest classifier models to predict civil unrest. The results showed that the decision tree and the random forest classifiers perform better, achieving an accuracy of 98
Predicting credit card defaults is pivotal for financial institutions to mitigate risks and implement proactive measures. Despite the monumental successes of deep learning in domains like computer vision and natural language processing, its efficacy in leveraging tabular data structures, especially in credit default prediction, remains contentious. In this manuscript, we systematically investigate various deep learning architectures, juxtaposing their performance with a meticulously optimized Gradient Boosted Decision Tree (GBDT) classifier. Our empirical findings reveal that the apex deep learning model achieved a performance metric of 0.783, slightly under performing against the GBDT model's 0.791. This reinforces existing literature, accentuating the superior prowess of tree-based algorithms in deciphering the intricacies of credit default prediction over contemporary deep learning paradigms.
