Internet of Things (IoT) applications and resources are highly vulnerable to flood attacks, including Distributed Denial of Service (DDoS) attacks. These attacks overwhelm the targeted device with numerous network packets, making its resources inaccessible to authorized users. Such attacks may comprise attack references, attack types, sub-categories, host information, malicious scripts, etc. These details assist security professionals in identifying weaknesses, tailoring defense measures, and responding rapidly to possible threats, thereby improving the overall security posture of IoT devices. Developing an intelligent Intrusion Detection System (IDS) is highly complex due to its numerous network features. This study presents an improved IDS for IoT security that employs multimodal big data representation and transfer learning. First, the Packet Capture (PCAP) files are crawled to retrieve the necessary attacks and bytes. Second, Spark-based big data optimization algorithms handle huge volumes of data. Second, a transfer learning approach such as word2vec retrieves semantically-based observed features. Third, an algorithm is developed to convert network bytes into images, and texture features are extracted by configuring an attention-based Residual Network (ResNet). Finally, the trained text and texture features are combined and used as multimodal features to classify various attacks. The proposed method is thoroughly evaluated on three widely used IoT-based datasets: CIC-IoT 2022, CIC-IoT 2023, and Edge-IIoT. The proposed method achieves excellent classification performance, with an accuracy of 98.2%. In addition, we present a game theory-based process to validate the proposed approach formally.

Explainability and interpretability have emerged as essential considerations in machine learning, particularly as models become more complex and integral to a wide range of applications. In response to increasing concerns over opaque “black-box” solutions, the literature has seen a shift toward two distinct yet often conflated paradigms: explainable AI (XAI), which refers to post hoc techniques that provide external explanations for model predictions, and interpretable AI, which emphasizes models whose internal mechanisms are understandable by design. Meanwhile, the phenomenon of concept and data drift—where models lose relevance due to evolving conditions—demands renewed attention. High-impact events, such as financial crises or natural disasters, have highlighted the need for robust interpretable or explainable models capable of adapting to changing circumstances. Against this backdrop, our systematic review aims to consolidate current research on explainability and interpretability with a focus on concept and data drift. We gather a comprehensive range of proposed models, available datasets, and other technical aspects. By synthesizing these diverse resources into a clear taxonomy, we intend to provide researchers and practitioners with actionable insights and guidance for model selection, implementation, and ongoing evaluation. Ultimately, this work aspires to serve as a practical roadmap for future studies, fostering further advancements in transparent, adaptable machine learning systems that can meet the evolving needs of real-world applications.

A Wireless Sensor Network (WSN) is composed of distributed sensors with limited processing capabilities and energy restrictions. These unique attributes pose new challenges amongst which prolonging the WSN lifetime is one of the most important. Clustering is an energy efficient routing technique that has been widely applied to report data from the WSN nodes to a centralised Base Station. A plethora of different clustering protocols have been proposed. Some protocols are based on equal-sized clusters while others use clusters of unequal size. Some others make use of rotation techniques to reduce the amount of cluster head elections. When different clustering approaches are presented different simulation settings are used. In this paper we perform a comparison study of HEED based clustering protocols that are HEED, UHEED, RUHEED and a novel variation of R-HEED that is ER-HEED. We have considered the same network model, the same energy consumption model and we have compared the lifetime of the protocols by considering various case studies. Our comparison study shows that the selection of the protocol to be used depends on the case study and the WSN lifetime measure that is considered.

In this paper we show how state-of-the art SMT-based techniques for software verification can be employed in the verification of event–condition–action rules in intelligent environments. Moreover, we exploit the specific features of intelligent environments to optimise the verification process. We compare our approach with previous work in a detailed evaluation section, showing how it improves both performance and expressivity of the language for event–condition–action rules.

Population aging may be seen both as a human success story, the triumph of public health, medical advancements and economic development over diseases and injures, and as one of the most challenging phenomena that society faces in this century. Assistive technology in all its possible implementations (from Telemedicine to Ambient Assisted Living, and Ambient Intelligence) represents an emerging answer to the needs of the new generation of older adults whose desire is to live longer with a higher quality of life. Objective of this paper is to present the results of a public financed action for the development and implementation of an “integration platform” for Ambient Assisted Living that includes features of home automation (energy management, safety, comfort, etc.) and introduces “smart objects”, to monitor activities of daily living and detect any abnormal behavior that may represent a danger, or highlight symptoms of some incipient disease.

Due to the huge volume and complexity of biological data available today, a fundamental component of biomedical research is now in silico analysis. This includes modelling and simulation of biological systems and processes, as well as automated bioinformatics analysis of high-throughput data. The quest for bioinformatics resources (including databases, tools, and knowledge) becomes therefore of extreme importance. Bioinformatics itself is in rapid evolution and dedicated Grid cyberinfrastructures already offer easier access and sharing of resources. Furthermore, the concept of the Grid is progressively interleaving with those of Web Services, semantics, and software agents. Agent-based systems can play a key role in learning, planning, interaction, and coordination. Agents constitute also a natural paradigm to engineer simulations of complex systems like the molecular ones. We present here an agent-based, multilayer architecture for bioinformatics Grids. It is intended to support both the execution of complex in silico experiments and the simulation of biological systems. In the architecture a pivotal role is assigned to an "alive" semantic index of resources, which is also expected to facilitate users' awareness of the bioinformatics domain.