Cultural Heritage on Internet of Things (IoT) systems: Trends and challenges

Abstract

This special issue collates a selection of representative research articles that were primarily presented at the 1st International Workshop on Data Mining on Internet of Things (IoT) Systems. This annual workshop brings together researchers and practitioners from both academia and industry who are working on data mining approaches on the IoT with applications in the Smart City framework and in the Cultural Heritage research domain, in order to promote an exchange of ideas, discuss future collaborations, and develop new research directions. The IoT envisages a plethora of heterogeneous objects, interacting with the physical environments and producing a huge amount of data. It can be foreseen that IoT applications and services will raise the scale of data to an unprecedented level. Collecting, analysing, and correlating data from different resources is a key role to drive smart interactions between actors of an IoT environment. The success of an IoT system depends on the efficient integration of its devices, sensors, and data management techniques. The scope of this special issue is broad and is representative of the multidisciplinary nature of the IoT framework. Khac-Hoai Nam Bui et al1 propose an approach for improving traffic flow at intersections, which based on the new era technologies of IoT. The approach collects streaming data from connected vehicles, which are seen as smart objects in IoV paradigm, whenever they arrive to the intersection. HyeonCheol Zin et al2 propose a simple and straightforward, exclusive channel–allocation algorithm in IoT networks. In particular, the authors describe 5 rules to support the proposed algorithm. Varun Ramesh et al3 propose a solution for the max-flow min-cut problem on large random lognormal graphs and real-world IoT datasets using the distributed Edmonds-Karp algorithm. To assess the feasibility of the proposed extension, authors tested the model with large road network datasets having more than 2.7 million edges. Jae Kwoin Kim et al4 describe a rare class prediction model for minority class prediction. The proposed method applies data preprocessing for the imbalanced classes and includes data cleaning, feature scaling, feature selection, and oversampling. Analysing data can be considered a crucial task within an IoT framework. Salvatore Cuomo et al5 propose a computational scheme in which the clustering methodology is used to classify information that are adopted as observations of an evolutionary method. The aim is to track and forecast the users' dynamics and behaviours starting from real data. Gribaudo et al6 propose a technique for modeling the performances of the IoT-based monitoring systems that support the planning of incident management in a protected site by exploiting multiple, sparse, heterogeneous, partially controlled sensors to monitor the behaviour of the crowd. This approach allows both for the modeling the possible scenarios and the design of the main parameters of the needed computing infrastructure. Francesco Piccialli et al7 present an innovative system relying on location-based IoT and multimedia services. The assessment of the proposed system has been performed investigating the user satisfaction dimension and the analysis of the users' behaviour using the system. Silvia Rossi et al8 starting from 2 state-of-the-art approaches, propose 2 different variants and compare them with respect to a baseline approach with the use of a dataset in the movie domain. Results show that the elicitation processes permit to obtain preference profiles in a time substantially less than the baseline method, while the differences in terms of prediction accuracy are minimal. We thank all the international reviewers for their professional services. We deeply thank Professor Geoffrey C. Fox, the Editor-in-Chief, for providing the opportunity to publish this special issue. With his continuous support, encouragement, and guidance throughout this publishing project, this special issue has been very successful.