A location‐based IoT platform supporting the cultural heritage domain

Federated learning (FL), a cooperative distributed learning framework, has been employed in various intelligent Internet of Things (IoT) applications (e.g., smart health-care, smart home, and smart industry). However, there may be malicious devices in these IoT applications inferring other devices’ privacy or destroying the uploaded model parameters. Besides, due to the heterogeneity of IoT devices, it is difficult for the existing synchronized FL to effectively train models through non-identical independently distributed (non-IID) local data sets. To address these issues, we propose an asynchronous grouped federated learning framework (PAG-FL) for IoT, enabling multiple devices and the server to collaboratively and efficiently train models without revealing privacy. PAG-FL framework consists of an adaptive Rényi Differential Privacy-based privacy budget allocation (ARB) protocol and an asynchronous weight-based grouped update (AWGU) algorithm. In particular, our ARB protocol applies Rényi Differential Privacy and adaptively adjusts the privacy budget to obtain an efficient local model. The AWGU algorithm can defend against the poisoning attack on non-IID data set by weighing grouped local models to generate a global model. Meanwhile, it also realizes the asynchronous optimized update by adopting a lazy loading strategy. Theoretically, the proposed framework has a convergence guarantee and a privacy guarantee when training over the non-IID data set in an asynchronous FL. Our empirical experiments validate the effectiveness of the theoretical design and demonstrate the improved utility and robustness of PAG-FL in heterogeneous IoT.

The traditional Internet of Things (IoT) paradigm has evolved towards intelligent IoT applications which exploit knowledge produced by IoT devices using artificial intelligence techniques. Knowledge sharing between IoT devices is a challenging issue in this trend. In this paper, we propose a Knowledge of Things (KoT) framework which enables sharing self-taught knowledge between IoT devices which require similar or identical knowledge without help from the cloud. The proposed KoT framework allows an IoT device to effectively produce, cumulate, and share its self-taught knowledge with other devices at the edge in the vicinity. This framework can alleviate behavioral repetition in users and computational redundancy in systems in intelligent IoT applications. To demonstrate the feasibility of the proposed concept, we examine a smart home case study and build a prototype of the KoT framework-based smart home system. Experimental results show that the proposed KoT framework reduces the response time to use intelligent IoT devices from a user’s perspective and the power consumption for compuation from a system’s perspective.

Most cultural promotion and dissemination are nowadays performed through the digitization of heritage sites and museums, a necessary requirement to meet the new needs of the public. Augmented Reality (AR), Mixed Reality (MR), and Virtual Reality (VR) have the potential to improve the experience quality and educational effect of these sites by stimulating users’ senses in a more natural and vivid way. In this respect, head-mounted display (HMD) devices allow visitors to enhance the experience of cultural sites by digitizing information and integrating additional virtual cues about cultural artifacts, resulting in a more immersive experience that engages the visitor both physically and emotionally.This study contributes to the development and incorporation of AR, MR, and VR applications in the cultural heritage domain by providing an overview of relevant studies utilizing fully immersive systems, such as headsets and CAVE systems, emphasizing the advantages that they bring when compared to handheld devices. We propose a framework study to identify the key features of headset-based Extended Reality (XR) technologies used in the cultural heritage domain that boost immersion, sense of presence, and agency. Furthermore, we highlight core characteristics that favor the adoption of these systems over more traditional solutions (e.g., handheld devices), as well as unsolved issues that must be addressed to improve the guests’ experience and the appreciation of the cultural heritage.An extensive search of Google Scholar, Scopus, IEEE Xplore, ACM Digital Library, and Wiley Online Library databases was conducted, including papers published from January 2018 to September 2022. To improve review reporting, the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were used. Sixty-five papers met the inclusion criteria and were classified depending on the study’s purpose: education, entertainment, edutainment, touristic guidance systems, accessibility, visitor profiling, and management.Immersive cultural heritage systems allow visitors to feel completely immersed and present in the virtual environment, providing a stimulating and educational cultural experience that can improve the quality and learning purposes of cultural visits. Nonetheless, the analyzed studies revealed some limitations that must be faced to give a further impulse to the adoption of these technologies in the cultural heritage domain.

The purpose of this research is to explore and develop the potential of a location-based mobile application to support informal learning in the cultural heritage domain. Since the notion that learning is interweaved with people's daily lives, and also that learners get motivated to learn in different contexts and spaces while they are moving, mobile learning has emerged to support learning throughout a lifetime. This research is going to investigate how mobile technology could be developed to support informal learning with respect to cultural heritage sites, and how learners use mobile technology for learning purposes. A major contribution of this research is to develop a task model for mobile location-based learning in order to provide a general framework for informal learning in the cultural heritage domain. Furthermore, this research will use mixed methods (e.g. Interview, questionnaire and focus group) in order to gather the requirements of users and also the officials who have the responsibility for managing and maintaining cultural heritage sites. Finally, a guideline will be provided for researchers who are working in the cultural heritage domain.

Nowadays, Intelligent Internet of things (IoT) have essential influence on human life. Generally, the normal issue among retail stores is that the supervisor doesn't have data of which rack is going to get unfilled and should be refilled. This issue leads to substantial loss. The objective of this paper is to utilize computer vision procedures and IoT in racking system to perform object detection. In the proposed IoT based smart shelf Intelligent IoT the changes about rack and products are distinguished in real-time utilizing OpenCV. This task is complex, because of the high number of possible variations in which similar scene of images can happen into the scene. The simple solution proposed here is both best in class locators dependent on deep learning and traditional methods for object detection. The IoT empowers connectivity of physical object with the real-time communication by ESP8266 and data logged into cloud. The smart shelf rack and products details are logged into Database Management system are some desirable characteristics that result.

This paper proposes a novel multimodal generative adversarial network AVSR (multimodal AVSR GAN) architecture, to improve both the energy efficiency and the AVSR classification accuracy of artificial intelligence Internet of things (IoT) applications. The audio-visual speech recognition (AVSR) modality is a classical multimodal modality, which is commonly used in IoT and embedded systems. Examples of suitable IoT applications include in-cabin speech recognition systems for driving systems, AVSR in augmented reality environments, and interactive applications such as virtual aquariums. The application of multimodal sensor data for IoT applications requires efficient information processing, to meet the hardware constraints of IoT devices. The proposed multimodal AVSR GAN architecture is composed of a discriminator and a generator, each of which is a two-stream network, corresponding to the audio stream information and the visual stream information, respectively. To validate this approach, we used augmented data from well-known datasets (LRS2-Lip Reading Sentences 2 and LRS3) in the training process, and testing was performed using the original data. The research and experimental results showed that the proposed multimodal AVSR GAN architecture improved the AVSR classification accuracy. Furthermore, in this study, we discuss the domain of GANs and provide a concise summary of the proposed GANs.

As technology continues to advance and become more integrated into our society, especially in the era of digital transformations, it is imperative that software engineering practices and products are sustainable. However, in the Cultural Heritage domain, sustainability is often overlooked, even though knowledge management solutions are essential for the long-term capture, preservation, and dissemination of cultural heritage in a digital form. This paper aims to address this gap by identifying the key sustainability requirements to consider when designing and developing sustainability-aware knowledge management software solutions for the Cultural Heritage sector. A survey was conducted among professionals with experience in digitizing and managing cultural heritage materials, including cultural heritage experts and software engineers. Despite some differences in the perceived importance of sustainability requirements between the two groups of professionals, the most important sustainability features were mainly agreed upon. The acknowledged requirements encompass features from both the social and technical dimensions of sustainability, such as Usefulness, Effectiveness, and Trust for the former and Maintainability, Functional Suitability, and Efficiency for the latter. The research results provide valuable insights into how domain experts and software engineers view software sustainability in the studied domain. The findings can aid the decision-making process for prioritizing requirements related to sustainability and can serve as recommendations for developing knowledge management information systems in the Cultural Heritage domain with sustainability in mind.

With the acceleration of economic development, enterprise management is facing more severe challenges. Big data analysis based on the intelligent Internet of Things (IoT) has a positive effect on the development of enterprise management and can make up for the shortcomings of enterprise management. In this paper, we develop a big data processing method based on intelligent IoT which can mine the factors that affect the company’s market sales from the collected data. Then, we propose a KNN classification algorithm based on overlapping k‐means clustering. This algorithm adds a training process to the traditional KNN algorithm, which can accurately classify data and greatly improve the efficiency of the classification algorithm. Numerical analysis results prove the effectiveness of the proposed algorithm.

Currently, with the pandemic wave, the collecting of medical waste is becoming a problem. Unwanted rubbish dumping on the edges of cities and towns causes damage, and these overflowing landfills are impossible to restore. Moreover, the manual labour required by the current technology may result in the individual using it developing a chronic illness. The suggested system's noble goals include creating an automated system to save the lives of countless people and create a cleaner, greener society. The main goal of this paper is an intelligent Internet of Things (IoT) based dry and wet waste separation and management process of medical waste material. It detects wastes in dustbins with the aid of using sensor devices. As soon as it is detected, its waste substances will be separated with sensors. Right away, information is transferred to cloud databases via IoT, making it easier to efficiently and shrewdly remove trash from the trash can. The proposed approach will prevent harmful wastes from taking numerous lives.

Indoor localization has gained significant attention recently due to the growing demand for location-aware applications within indoor environments. Among various techniques, Wi-Fi fingerprinting combined with the Internet of Things (IoT) has emerged as a promising solution for accurate and cost-effective indoor localization. This paper surveys the existing research related to indoor localization using Wi-Fi fingerprinting with the IoT, aiming to provide a comprehensive understanding of the advancements, challenges, and potential applications in this field. The paper begins by introducing the fundamental concepts of indoor localization and the role of Wi-Fi fingerprinting in achieving accurate position estimation. In addition, this paper focuses on the contributions of Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) in improving localization accuracy, robustness, and scalability. The reviewed papers have been examined from various aspects, including system architecture, deployment strategies, fingerprint creation techniques, and localization algorithms, with a discussion about the advantages and limitations of each approach. In addition to discussing the state-of-the-art techniques, this paper identifies research gaps and open challenges in indoor localization using Wi-Fi fingerprinting with the IoT. The findings presented in this paper can guide future research efforts, leading to the development of intelligent and context-aware IoT applications within indoor environments.

The concept of Ontologies has been used in a wide range of application domains, due to the fact that ontologies provide a useful mean for establishing a formal, shared and collective understanding of the concepts and their underlying relations at a certain domain of interest, which allows for interoperability and information exchange in a formal an understandable way for both humans and machines. In Cultural Heritage (CH) domain, ontologies serve as a fundamental building block for the traceability of the cultural heritage objects, especially with the increasing demand of providing digital formats for cultural objects and make them available for public. In this paper we implement OntoM; an Ontology model that incorporates the relevant concepts of the Cultural Heritage (CH) domain in Qatar. Then, we will use such an ontology to perform inferences about cultural object classifications via two approaches: string matching, that allows for direct matching between the object and the ontology concepts, and semantic matching, in which we use WordNet lexical database to find all possible synonyms for properties of a given anonymous object.

Developed in the context of the Horizon 2020 project SPICE, this paper explores methods and tools for citizen curation, with a focus on designing activities that can effectively elicit and motivate citizens to produce meaningful interpretations and reflections on cultural heritage. Additionally, the paper aims to evaluate the potential of such methods and activities in supporting the analysis and reflection processes within the SPICE Interpretation-Reflection loop (IRL). We explore a selection of narrative-based methods for citizen curation to propose an approach for eliciting meaningful stories related to cultural heritage artifacts from citizens. The proposed approach is subsequently applied in a digital co-design workshop, conducted with members of the SPICE consortium, including the five SPICE museum partners. The collected story contributions are thereafter analysed using qualitative methods and tools adapted from narrative inquiry and the study of narrative identity. The findings provide valuable insights into the potential of narrative-based approaches for citizen engagement in the cultural heritage domain and support the development of the SPICE digital tools for promoting reflection, i.e. sentiment analysis, personalization, recommendation systems, and user- and community modeling tools. In SPICE, such tools play a central role in enabling citizens to create representations of themselves, while also cultivating an understanding and appreciation of similarities and differences across citizen groups. In this direction, the paper offers ideas and insights for designing engaging participatory approaches to elicit citizen input. At the same time, it aims to support the development of digital systems and tools in the cultural heritage domain, with the goal of fostering more inclusive and dynamic representations of citizens and citizen groups.

The 3D Semantic Annotation (3DSA) system expedites the classification of 3D digital surrogates from the cultural heritage domain, by leveraging crowd-sourced semantic annotations. More specifically, the 3DSA system generates high-level classifications of 3D objects by applying rule-based reasoning across community-generated annotations and low-level shape and size attributes. This paper describes a particular use of the 3DSA system — cataloguing Greek pottery. It also describes our novel approach to rule-based reasoning that is modelled on concepts inspired from Markov logic networks. Our evaluation of this approach demonstrates its efficiency, accuracy and versatility, compared to classical rule-based reasoning.

Semantic-Based Data Access to Digital Cultural Heritage: A Qualitative Analysis of Linked Open Data Implementation

This research introduces a novel security-aware optimization framework for intelligent Internet of Things (IoT) networks in smart agriculture, leveraging Federated Artificial Intelligence (AI) to address the critical trade-offs between performance, reliability, and trust. We formulate a multi-objective optimization problem that simultaneously maximizes network performance metrics while ensuring robust security guarantees and maintaining computational efficiency. The proposed Federated Security-Aware Optimization (FSAO) framework employs differential privacy, secure multi-party computation, and blockchain-based trust management to protect sensitive agricultural data while enabling collaborative learning across distributed agricultural sites. Our mathematical formulation incorporates threat modeling using game-theoretic approaches and implements Byzantine-resilient aggregation for federated learning. Extensive experiments across three agricultural testbeds with 1,500+ IoT devices demonstrate that FSAO achieves 89.7% attack detection accuracy with only 12.3% performance overhead, while maintaining 94.5% model accuracy under coordinated poisoning attacks. Statistical analysis confirms significant improvements in security metrics (p < 0.001) while preserving network performance within acceptable bounds. The framework establishes optimal operating points across the performance-reliability-trust trade-off space, providing practical guidelines for secure agricultural IoT deployments in real-world scenarios.