Related papers: Data Movement Manager (DMM) for the SENSE-Rucio In…
This master thesis introduces the idea of dynamic cutoffs in molecular dynamics simulations, based on the distance between particles and the interface, and presents a solution for detecting interfaces in real-time. Our dynamic cutoff method…
Multispectral oriented object detection faces challenges due to both inter-modal and intra-modal discrepancies. Recent studies often rely on transformer-based models to address these issues and achieve cross-modal fusion detection. However,…
The energy consumed by running large deep neural networks (DNNs) on hardware accelerators is dominated by the need for lots of fast memory to store both states and weights. This large required memory is currently only economically viable…
The increasing size and complexity of modern deep neural networks (DNNs) pose significant challenges for on-device inference on mobile GPUs, with limited memory and computational resources. Existing DNN acceleration frameworks primarily…
The communication network context in actual systems like 5G, cloud and IoT (Internet of Things), presents an ever-increasing number of users, applications, and services that are highly distributed with distinct and heterogeneous…
We present NetReduce, a novel RDMA-compatible in-network reduction architecture to accelerate distributed DNN training. Compared to existing designs, NetReduce maintains a reliable connection between end-hosts in the Ethernet and does not…
Software-defined networking (SDN) paradigm, with the flexible and logically centralized control, enables dynamically minimizing the network energy consumption by redirecting paths of packets. However, the links and switches are designed to…
Recently, action recognition has been dominated by transformer-based methods, thanks to their spatiotemporal contextual aggregation capacities. However, despite the significant progress achieved on scene-related datasets, they do not…
Real-time networks based on Ethernet require robust quality-of-service for time-critical traffic. The Time-Sensitive Networking (TSN) collection of standards enables this in real-time environments like vehicle on-board networks. Runtime…
Deep neural network (DNN) inference is increasingly being executed on mobile and embedded platforms due to low latency and better privacy. However, efficient deployment on these platforms is challenging due to the intensive computation and…
Partitioning and distributing deep neural networks (DNNs) across end-devices, edge resources and the cloud has a potential twofold advantage: preserving privacy of the input data, and reducing the ingress bandwidth demand beyond the edge.…
Dataset Condensation (DC) has emerged as a promising solution to mitigate the computational and storage burdens associated with training deep learning models. However, existing DC methods largely overlook the multi-domain nature of modern…
This paper proposes the possibility of integrating Dynamic Knowledge Graph (DKG) with Software-Defined Networking (SDN). This new approach aims to assist the management and control capabilities of the swarm network. The DKG works as a…
To increase the scalability of Software Defined Networks (SDNs), flow aggregation schemes have been proposed to merge multiple mouse flows into an elephant aggregated flow for traffic engineering. In this paper, we first notice that the…
Network performance monitoring holds a pivotal role in improving the overall network performance. It is essential to monitor the traffic statistics at Internet eXchange Points (IXPs) to optimize the traffic flows. The existing monitoring…
Computing-in-memory (CIM) architectures demonstrate superior performance over traditional architectures. To unleash the potential of CIM accelerators, many compilation methods have been proposed, focusing on application scheduling…
Electricity demand of electric railways is a relatively unexplored source of flexibility in demand response applications in power systems. In this paper, we propose a transactive control based optimization framework for coordinating the…
The distributed edge storage system can store data collected at the edge of the network in a decentralised manner, with low latency, high security, and flexibility. Traditional edge-distributed storage systems only consider one single…
Optimal deployment of deep neural networks (DNNs) on state-of-the-art Systems-on-Chips (SoCs) is crucial for tiny machine learning (TinyML) at the edge. The complexity of these SoCs makes deployment non-trivial, as they typically contain…
The exponential growth in mobile broadband usage [1] has catalyzed the need for high data rate communication systems. In this regard, activities for standardizing the next generation mobile broadband system, known as the Fifth…