Nokia (Spain)

Intelligent vehicle networks powered by machine learning, AI and blockchain are transforming various sectors beyond transportation. In this context, being able to remote drive a vehicle is key for enhancing autonomous driving systems. After deploying end-to-end teleoperated driving systems under 5G networks, the need to address complex challenges in other critical areas arises. These challenges belong to different technologies that need to be integrated in this particular system: video transmission and visualization technologies, artificial intelligence techniques, and network optimization features, incorporating haptic devices and critical data security. This article explores how these technologies can enhance the teleoperated driving activity experiences already executed in real-life environments by analyzing the quality of the video which is transmitted over the network, exploring its correlation with the current state-of-the-art AI object detection algorithms, analyzing the extended reality and digital twin paradigms, obtaining the maximum possible performance of forthcoming 6G networks and proposing decentralized security schema for ensuring the privacy and safety of the end-users of teleoperated driving infrastructures. An integrated set of conclusions and recommendations will be given to outline the future teleoperated driving systems design in the forthcoming years.

The growing demand for real-time video streaming in power-constrained embedded systems, such as drone navigation and remote surveillance, requires encoding solutions that prioritize low latency. In these applications, even small delays in video transmission can impair the operator’s ability to react in time, leading to instability in closed-loop control systems. To mitigate this, encoding must be lightweight and designed so that streaming can start as soon as possible, ideally even while frames are still being processed, thereby ensuring continuous and responsive operation. This paper presents the design of a hardware implementation of the Logarithmic Hop Encoding (LHE) algorithm on a Field-Programmable Gate Array (FPGA). The proposed architecture is deeply pipelined and parallelized to achieve sub-frame latency. It employs adaptive compression by dividing frames into regions of interest and uses a quantized differential system to minimize data transmission. Our design achieves an encoding latency of between 1.87 ms and 2.1 ms with a power consumption of only 2.7 W when implemented on an FPGA clocked at 150 MHz. Compared to a parallel GPU implementation of the same algorithm, this represents a 6.6-fold reduction in latency at approximately half the power consumption. These results show that FPGA-based LHE is a highly effective solution for low-latency, real-time video applications and establish a robust foundation for its deployment in embedded systems.

<p>The technology associated with 5G and future 6G networks is challenging for military communications in tactical scenarios. This work has selected and analyzed a group of leading technologies that allow tactical networks to evolve. The virtualization of networks with 5G helps to guarantee greater security. These developments are vital in improving the feasibility of truly network-centric operations for military applications. Software-defined networks, IoT, blockchain, Artificial Intelligence, semantic communications, or neuromorphic processors help increase communications performance. These technologies have improved ten classic use cases in the military field. This work is an analysis to serve as a starting point for new scientists to open up new lines of research. It is not merely a compilation but an analytical basis for future work.</p>

Homomorphic encryption allows computations to be performed on encrypted data. However, there is certain impact on data training because certain properties of data change. For instance, ANNs learn better with data using whole valid range. If the original input data range belongs to [0..1] and cypher data belongs to [0.01 … 0.1], this change of magnitude affects learning process. I miss an analysis of the impact of encryption at learning process . In fact, the article from Olzak, T. does not analyze this key point, neither other cited papers Regarding deferential privacy, there is an example of noise addition, but I miss an analysis of the impact of noise

This research paper details the assessment of four distinct interaction techniques for immersive training within the construction industry. The primary focus of this study was to evaluate the extent to which these methods were capable of replicating physical environment interactions within virtual environments. A common challenge associated with immersive training within construction is the need for external tools to facilitate interactions, which can negatively impact user experience. To mitigate this issue, we introduce four immersive training use cases that rely on natural interfaces for interaction. Additionally, we conducted a Quality of Experience (QoE) experiment to validate the efficacy of these use cases and interaction techniques, assessing acceptability, presence, and visual quality. Moreover, this paper presents a classification system for four distinct natural interaction methods, which we evaluated for differences in visual quality.

<p>This deliverable presents the work executed in the iNGENIOUS project with regards to dissemination, communication, standardization, exploitation, and innovation.</p>

Subjective responses from Multimedia Quality Assessment (MQA) experiments are conventionally analysed with methods not suitable for the data type these responses represent. Furthermore, obtaining subjective responses is resource intensive. A method allowing reuse of existing responses would be thus beneficial. Applying improper data analysis methods leads to difficult to interpret results. This encourages drawing erroneous conclusions. Building upon existing subjective responses is resource friendly and helps develop machine learning (ML) based visual quality predictors. We show that using a discrete model for analysis of responses from MQA subjective experiments is feasible. We indicate that our proposed Generalised Score Distribution (GSD) properly describes response distributions observed in typical MQA experiments. We highlight interpretability of GSD parameters and indicate that the GSD outperforms the approach based on sample empirical distribution when it comes to bootstrapping. We evidence that the GSD outcompetes the state-of-the-art model both in terms of goodness-of-fit and bootstrapping capabilities. To do all of that we analyse more than one million subjective responses from more than 30 subjective experiments. Furthermore, we make the code implementing the GSD model and related analyses available through our GitHub repository: https://github.com/Qub3k/subjective-exp-consistency-check

We present FairTraDEX, a decentralized exchange (DEX) protocol based on frequent batch auctions (FBAs), which provides formal game-theoretic guarantees against extractable value. FBAs, when run by a trusted third-party, ensure that the unique game-theoretic optimal strategy for all players is to trade at the true market-implied price of the underlying token swap, excluding explicit, pre-determined fees. FairTraDEX replicates the key features of an FBA that provide these game-theoretic guarantees using a combination of set-membership in zero-knowledge protocols and an escrow-enforced commit-reveal mechanism. We extend the results of FBAs to handle monopolistic and/or malicious liquidity providers. We provide real-world examples that demonstrate that the costs of executing orders in existing academic and industry-standard protocols become prohibitive as order size increases due to basic value extraction techniques, popularized as maximal extractable value. We further demonstrate that FairTraDEX protects against these execution costs, guaranteeing a fixed fee model independent of order size, the first guarantee of it's kind for a DEX protocol. We also provide detailed Solidity and pseudo-code implementations of FairTraDEX, making FairTraDEX a novel and practical contribution.

The preliminary results of immersive virtual reality music therapy experiences are presented, carried out with people between ages of 72 and 96, residents of a nursing home, who suffer from mild mental health problems, potential dementia, moderate cognitive disorders, depressive symptoms, or severe dependency. The experiences are carried out in 15-minute sessions, streaming 180° and 360° music videos of genres that the elderly like, recorded for this purpose and performed by musical groups that collaborate voluntarily. The design of the developed application (the web interface, the application logic and the HMD player) is simple so that it is easy to use during music therapy sessions. Preliminary results show that the elderly experience similar levels of sense of presence as reported by other studies in younger population (< 55), and only 19% of them suffer from simulator sickness. This validates the usage of immersive media for music therapy in elderly patients.