Related papers: Intelligence Beyond the Edge: Inference on Intermi…

Graphics processing units (GPUs) can improve deep neural network inference throughput via batch processing, where multiple tasks are concurrently processed. We focus on novel scenarios that the energy-constrained mobile devices offload…

Edge inference techniques partition and distribute Deep Neural Network (DNN) inference tasks among multiple edge nodes for low latency inference, without considering the core-level heterogeneity of edge nodes. Further, default DNN inference…

The advancement of smart grid technologies necessitates the integration of cutting-edge computational methods to enhance predictive energy optimization. This study proposes a multi-faceted approach by incorporating (1) Deep Reinforcement…

The paper studies optimal sensor selection for source estimation in energy harvesting Internet of Things (IoT) networks. Specifically, the focus is on the selection of the sensor locations which minimizes the estimation error at a fusion…

Computing at the edge is increasingly important since a massive amount of data is generated. This poses challenges in transporting all that data to the remote data centers and cloud, where they can be processed and analyzed. On the other…

Deep Neural Networks (DNNs) have served as a catalyst in introducing a plethora of next-generation services in the era of Internet of Things (IoT), thanks to the availability of massive amounts of data collected by the objects on the edge.…

The deployment of inference services at the network edge, called edge inference, offloads computation-intensive inference tasks from mobile devices to edge servers, thereby enhancing the former's capabilities and battery lives. In a…

Unlike existing work in deep neural network (DNN) graphs optimization for inference performance, we explore DNN graph optimization for energy awareness and savings for power- and resource-constrained machine learning devices. We present a…

As the accuracy of machine learning models increases at a fast rate, so does their demand for energy and compute resources. On a low level, the major part of these resources is consumed by data movement between different memory units.…

This paper proposes a hardware-aware intrusion detection system (IDS) for Internet of Things (IoT) and Industrial IoT (IIoT) networks; it targets scenarios where classification is essential for fast, privacy-preserving, and…

On-device Deep Neural Network (DNN) inference consumes significant computing resources and development efforts. To alleviate that, we propose LUT-NN, the first system to empower inference by table lookup, to reduce inference cost. LUT-NN…

Energy efficiency of Convolutional Neural Networks (CNNs) has become an important area of research, with various strategies being developed to minimize the power consumption of these models. Previous efforts, including techniques like model…

Collaboration among industrial Internet of Things (IoT) devices and edge networks is essential to support computation-intensive deep neural network (DNN) inference services which require low delay and high accuracy. Sampling rate adaption…

This paper explores Google's Edge TPU for implementing a practical network intrusion detection system (NIDS) at the edge of IoT, based on a deep learning approach. While there are a significant number of related works that explore machine…

Deploying deep neural networks (DNNs) on power-sensitive edge devices presents a formidable challenge. While Dynamic Voltage and Frequency Scaling (DVFS) is widely employed for energy optimization, traditional model-level scaling is often…

Internet of Things (IoT) devices can apply mobile-edge computing (MEC) and energy harvesting (EH) to provide the satisfactory quality of experiences for computation intensive applications and prolong the battery lifetime. In this article,…

Recently, intermittent computing (IC) has received tremendous attention due to its high potential in perpetual sensing for Internet-of-Things (IoT). By harvesting ambient energy, battery-free devices can perform sensing intermittently…

Wireless Sensor Networks (WSNs) are extensively used in monitoring applications such as humidity and temperature sensing in smart buildings, industrial automation, and predicting crop health. Sensor nodes are deployed in remote places to…

Sound event detection (SED) is a hot topic in consumer and smart city applications. Existing approaches based on Deep Neural Networks are very effective, but highly demanding in terms of memory, power, and throughput when targeting…

Advances in deep neural networks (DNNs) are transforming science and technology. However, the increasing computational demands of the most powerful DNNs limit deployment on low-power devices, such as smartphones and sensors -- and this…