Abstract
Network traffic sampling is an effective method for understanding the behavior and dynamics of a network, being essential to assist network planning and management. Tasks such as controlling Service Level Agreements or Quality of Service, as well as planning the capacity and the safety of a network can benefit from traffic sampling advantages. The main objective of this paper is focused on evaluating the impact of sampling network traffic on: (i) achieving a low-overhead estimation of the network state and (ii) assessing the statistical properties that sampled network traffic presents regarding the eventual persistence of LongRange Dependence (LRD). For that, different Hurst parameter estimators have been used. Facing the impact of LRD on network congestion and traffic engineering, this work will help clarify the suitability of distinct sampling techniques in accurate network analysis.

Abstract
This chapter aims to discuss about the potential Return on Investment (ROI) measures from Artificial intelligence (AI) investments that business can leverage. It discusses the concepts and describes the dimensions, features and tools of AI investments in Marketing business, to assist the readers to understand about the topic. The authors also describe the major drivers of ROI measures for business applications and discusses the concerns and limitations of tangible measures. So, this document contributes to the literature on ROI (in)tangibles measures that leverage AI investments and features issues in digital marketing, at large and potentially offers a theoretical grounding for many empirical and theoretical future studies.

Abstract

Abstract
Incidental visualizations allow individuals to access information on-the-go, at-a-glance, and without needing to consciously search for it. Unlike ambient visualizations, incidental visualizations are not fixed in a specific location and only appear briefly within a person's field of view while they are engaged in a primary task. Despite their potential, incidental visualizations have not yet been thoroughly studied in current literature. We conducted exploratory research to establish the distinctiveness of incidental visualizations and to advocate for their study as an independent research topic. We tested both incidental and ambient visualizations in two separate studies, each involving one specific scenarios: a cognitively demanding primary task (42 participants), and a mechanical primary task (28 participants). Our findings show that in the cognitively demanding task, both types of visualizations resulted in similar performance. However, in the mechanical task, ambient visualizations led to better results compared to incidental visualizations. Based on these results, we argue that incidental visualizations should be further explored in scenarios involving physical requirements, as these situations present the greatest challenges for their integration.

Abstract

Abstract
Colorectal cancer is a leading health concern worldwide, with late detection being a primary challenge due to its often-asymptomatic nature. Routine examinations like colonoscopies play a pivotal role in early detection. This study harnesses the potential of Deep Learning, specifically convolutional neural networks, in enhancing the accuracy of polyp detection from medical images. Three distinct models, YOLOv5, YOLOv7, and YOLOv8, were trained on the PICCOLO dataset, a comprehensive collection of polyp images. The comparative analysis revealed YOLOv5’s submodel S as the most efficient, achieving an accuracy of 92.2%, a sensitivity of 69%, an F1 score of 74% and a mAP of 76.8%, emphasizing the effectiveness of these networks in polyp detection. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2024.