With the booming development of multimodal data (e.g., image, text) on internet platforms, multimodal sequential recommendation methods continue to emerge. Most existing methods incorporate item modal features as auxiliary information, typically concatenating them to learn unified user representations. However, these methods directly use modal features for representation learning, neglecting the impact of inherent modal noise. We argue that internal-modal noise and cross-modal noise hinder the acquisition of more accurate user representations. To address this problem, we propose SGP4SR - Separated-modality Guided user Preference learning for multimodal Sequential Recommendation. Globally, the user preference modeling is carried out from a separated-modality perspective to alleviate cross-modal noise. Locally, for each individual modality, we use item relationship graphs and user interest centers, aggregated with ID embeddings, to replace direct modal features, thereby mitigating internal-modal noise. Finally, user representations from both separated-modality and multimodal perspectives participate in prediction independently. In experiments conducted on four real-world datasets, our method outperforms state-of-the-art approaches, achieving an average performance improvement of up to 8.84% over the best baseline. The comprehensive experiments further validate the superior noise tolerance and robustness of our method.

Complex electronic control unit (ECU) architectures, software models and in-vehicle networks are consistently improving safety and comfort functions in modern vehicles. However, the extended functionality and increased connectivity introduce new security risks and vulnerabilities that can be exploited on legacy automotive networks such as the controller area network (CAN). With the rising complexity of vehicular systems and attack vectors, the need for a flexible hardware-in-the-loop (HIL) test fixture that can inject attacks and validate the performance of countermeasures in near-real-world conditions in real time is vital. This paper presents an FPGA-based HIL framework tailored towards validating network security approaches (IDS, IPS) and smart integration strategies of such capabilities for an automotive CAN bus. FAV-NSS replicates an actual vehicular system environment with functional ECUs and network infrastructure on an FPGA, allowing functional validation of IDS/IPS algorithms, accelerator designs and integration schemes (software task on ECU, dedicated accelerator). Software APIs on the attached host machine control and configure ECUs, automate test case execution and log signals from the ECUs and the 'virtual' CAN bus during runtime. To show the efficacy of FAV-NSS, we evaluate an IDS accelerator integration problem, both as a traditional coupled accelerator (to the ECU), and secondly close to the CAN controller (mimicking an extended CAN controller). We show that the latter strategy can be fully validated by our framework, which would otherwise require integration of specialised CAN modules into otherwise standard HIL fixtures with ability to instrument internal signals for characterising timing performance. The tests demonstrate a promising latency reduction of$6.3 \times$when compared to the traditional coupled accelerator. Our case study demonstrates the potential of FAV-NSS for accelerating the optimisation, integration and verification of smart ECUs and communication controllers in current and future vehicular systems.

We describe the results obtained when using a desktop videoconferencing system for distance learning and, at the same time, doing measurements about its performance. The system hardware is based on a PC with a LAN network controller, and a compression card implementing the CCITT H.261 algorithm. Our network environment consists of a campus network (Ethernets connected with routers and bridges) and a wide area network connection (0.5 Mbit/s frame relay) to another university 150 miles away. In this environment TCP/IP is used as the transport and network protocol suite. The quality of the videoconferencing application is first analysed on a subjective perceptual basis in four different subnetworks. Then, the transmission rate of the application and the number of TCP retransmissions is measured in those subnetworks under varying background traffic load. As one may assume, severe problems with audio appear when the networking environment gets more demanding. With video, the problems are not so evident. Yet, slight degradation of perceptual quality can be observed and related to the increase of load and number of packet switches (routers and frame relay nodes) in the network connection.>