Empowered by deep learning, semantic communication marks a paradigm shift from transmitting raw data to conveying task-relevant meaning, enabling more efficient and intelligent wireless systems. In this study, we explore a deep learning-based task-oriented communication framework that jointly considers classification performance, computational latency, and communication cost. We evaluate ResNets-based models on the CIFAR-10 and CIFAR-100 datasets to simulate real-world classification tasks in wireless environments. We partition the model at various points to simulate split inference across a wireless channel. By varying the split location and the size of the transmitted semantic feature vector, we systematically analyze the trade-offs between task accuracy and resource efficiency. Experimental results show that, with appropriate model partitioning and semantic feature compression, the system can retain over 85\% of baseline accuracy while significantly reducing both computational load and communication overhead.

Integrating cyber-physical systems and the Internet of Things into industrial operations has significantly improved automation, efficiency, and data-driven decision making. However, these advances have also made industrial environments more vulnerable to cybersecurity risks. Our previous work explored lightweight deep learning models for real-time intrusion detection systems on edge devices, yet these models often operate as black boxes, limiting their trustworthiness. This issue is especially critical in the European Union, where the AI Act mandates transparency, accountability, and human oversight for AI solutions to be interpretable. In this paper, we integrate explainable AI solutions into lightweight real-time intrusion detection systems on edge devices to enhance the transparency and interpretability of black-box models. The study demonstrates that integrating SHapley Additive exPlanations significantly enhances the interpretability of intrusion detection systems, providing more transparent insights into model decisionmaking processes while maintaining accuracy and computational efficiency. This work contributes to the development of more secure and trustworthy industrial ecosystems by improving the effectiveness and reliability of intrusion detection.

Ensuring reliable and predictable communications is one of the main goals in modern industrial systems that rely on Wi-Fi networks, especially in scenarios where continuity of operation and low latency are required. In these contexts, the ability to predict changes in wireless channel quality can enable adaptive strategies and significantly improve system robustness. This contribution focuses on the prediction of the Frame Delivery Ratio (FDR), a key metric that represents the percentage of successful transmissions, starting from time sequences of binary outcomes (success/failure) collected in a real scenario. The analysis focuses on two models of deep learning: a Convolutional Neural Network (CNN) and a Long Short-Term Memory network (LSTM), both selected for their ability to predict the outcome of time sequences. Models are compared in terms of prediction accuracy and computational complexity, with the aim of evaluating their applicability to systems with limited resources. Preliminary results show that both models are able to predict the evolution of the FDR with good accuracy, even from minimal information (a single binary sequence). In particular, CNN shows a significantly lower inference latency, with a marginal loss in accuracy compared to LSTM.

In the rapidly evolving cybersecurity landscape, detecting and preventing network attacks has become crucial within the industrial sector. This study aims to explore the potential of intrusion detection by employing deep learning within edge computing, especially for the Industrial Internet of Things. Specifically, TinyML converted CNN, LSTM, Transformer-LSTM, and GCN models on the UNSW-NB15 dataset. A comprehensive dataset analysis gained insights into the nature of attack behavior data. Subsequently, a comparative analysis in an edge computing setup using Raspberry Pi units revealed that the GCN model, with its accuracy of 97.5%, was the best suited of the compared models for this application. However, the study also explored variables like time consumption, where the CNN model was the fastest out of the compared models. This research also highlights the need for continued exploration, especially in addressing dataset imbalances and enhancing model generalizability. By recognizing each model's strengths and areas of improvement, this research serves as a step toward bolstering digital safety and security in an increasingly interconnected industrial world.

News companies have a need to automate and make the process of writing about popular and new events more effective.Current technologies involve robotic programs that fill in values in templates and website listeners that notify editors when changes are made so that the editor can read up on the source change on the actual website.Editors can provide news faster and better if directly provided with abstracts of the external sources and categorical meta-data that supports what the text is about.In this article, the focus is on the importance of evaluating critical parameter modifications of the four classification algorithms Decisiontree, Randomforest, Multi Layer perceptron and Long-Short-Term-Memory in a combination with the paragraph vector algorithms Distributed Memory and Distributed Bag of Words, with an aim to categorise news articles.The result shows that Decisiontree and Multi Layer perceptron are stable within a short interval, while Randomforest is more dependent on the parameters best split and number of trees.The most accurate model is Long-Short-Term-Memory model that achieves an accuracy of 71%.

In this paper we present an overview of the various proximity based authentication mechanisms that can be used in the Industrial Internet of Things (IIoT). We seek to identify and highlight from a holistic point of view which mechanisms can enable proximity based authentication for the Industrial Internet of Things. In addition, we identify which upcoming proximity authentication mechanisms are most important for the proliferation of the Industrial Internet of Things, and highlight major obstacles that remain unsolved with regard to authentication. In answering this, we present seven mechanisms for proximity based authentication (i.e. wire, radio, acoustics, light, image, gesture and biometrics) and discuss each mechanism in perspective of their vulnerability to different kind of attacks (such as eavesdropping, impersonation and denial of service attacks etc.) and their usability (such as proximity range, hardware requirement and ease of use) in terms of the practicality in IIoT environment in the light of which we present two typical IIoT use cases that require proximity based authentication.

The ability to provide a high Quality of Service is a crucial aspect in the acceptance and widespread dispersion of the Industrial Internet of Things and it has a key role to enhance the end user experience. The emerging fog cloud computing architectural concept aims to diminish the experienced latency while simultaneously providing a seemingly unlimited quantity of computational power by moving computations from the cloud and things to the edge. To enhance the reliability, fault-tolerance, and connectivity of the data transmission, the transport layer protocol Stream Control Transport Protocol may be applied. To this end, we analyzed the feasibility of this protocol for an Industrial Internet of Things and fog computing setting by demonstrating and conducting essential network performance measurements. Our results reveal, that the protocol is a valid candidate for industrial scenarios in a fog computing environment and that it outperforms established Internet transport layer protocols in several of the conducted measurements.

Existing sensor-assisted mHealth applications would benefit from large-scale sharing of sensor information in real-time. Existing communication solutions are however limited in this respect, because of centralized application-level communication. In response to this, we presents a distributed communication solution for mHealth applications which circumvents these limitations. Our Internet-of-Things architecture enables mHealth applications to utilize information from sensors and wireless sensor networks via a peer-to-peer overlay, where sensor information is organized in an information model which is stored in the overlay itself. We present a proof-of-concept application and evaluation results regarding the architecture's real-time capabilities. The results indicate that a fully distributed architecture can support real-time sensing in mHealth applications and the support is available as an open source platform, MediaSense. Current work is focused on evaluating scalability in very large scale scenarios using field trials.

Intelligent artifacts are real-world objects enhanced with capabilities in order to display relevant behavior in various types of context-aware applications, such as in mHealth, commerce, or pervasive games. This can be achieved by attaching sensors and store associated information on the Internet. Interaction with such artifacts requires secure communication, to protect personal and private information. This mandates research in how to safeguard interactions via heterogeneous means of communication involving interconnected local and non-local artifacts. In response to these challenges, this paper presents key schemes to secure interaction via heterogeneous means of communication. In conclusion, the architecture can securely authenticate an intelligent artifact as well as securely exchange sensor information with other authenticated artifacts attached in an overlay. Our proof-of-concept application demonstrated in an Internet-of-Things platform validates the approach.

Next generation context-aware mobile applications will require a continuous update of relevant information about a user's surroundings, in order to create low latency notifications and high quality of experience. Existing mobile devices already contain a large number of built in sensors which are capable of producing huge amounts of sensor data, exceeding both the capacity of the local storage and the Internet connection. Therefore, we will in this paper study the limits when sharing contextual information from mobile devices, as well as finding the impact of this information overload for the Internet-of-Things. Furthermore, we present an evaluation model for assessing the effort required to present applications with relevant context information. In conclusion, the model shows that one feasible solution for the future Internet-of-Things is a peer-to-peer based solution which can control the flow of information without any centralized authority, to circumvent earlier limitations.