1,721,003 research outputs found
Energy-aware human activity recognition for wearable devices: A comprehensive review
No full textWith the rapid advancement of wearable devices, sensor-based human activity recognition has emerged as a fundamental research area with broad applications in various domains. While significant progress has been made in this research field, energy consumption remains a critical aspect that deserves special attention. Recognizing human activities while optimizing energy consumption is essential for prolonging device battery life, reducing charging frequency, and ensuring uninterrupted monitoring and functionality.
The primary objective of this survey paper is to provide a comprehensive review of energy-aware wearable human activity recognition techniques based on wearable sensors without considering vision-based systems. In particular, it aims to explore the state-of-the-art approaches and methodologies that integrate activity recognition with energy management strategies. Finally, by surveying the existing literature, this paper aims to shed light on the challenges, opportunities and potential solutions for energy-aware human activity recognition
Complexity-aware Features Selection for Wrist-worn Human Activity Recognition
No full textWrist-worn wearable devices have become increasingly prevalent in monitoring human activities, with applications ranging from healthcare to fitness tracking. Accurate human activity recognition from wrist-worn sensor data is essential for enabling these applications. However, the high-dimensional nature of sensor data poses challenges in terms of computational complexity and model interpretability. Feature selection is a critical step in mitigating these challenges by identifying a subset of relevant features while preserving the discriminative information. In this study, we propose a complexity-aware feature selection method tailored for wearable systems. Our approach leverages the intrinsic characteristics of the data to prioritize and select the most informative features while simultaneously weighing their computational efficiency by means of an ad-hoc metric that quantifies the number of significant CPU instructions associated with each feature. The results on publicly available datasets demonstrate that the proposed method effectively balances computational complexity and recognition accuracy
Privacy preservation in sensor-based Human Activity Recognition through autoencoders for low-power IoT devices
No full textHuman activity recognition is increasingly recognized as a key task in many applications. However, gathering data from the variety of sensors commonly available on end devices risks compromising user’s privacy when signals are transmitted to more powerful computing units for inference offloading. It is therefore important to design and implement strategies that could prevent privacy breaches without impairing the capability of the system of recognizing activity patterns, and by taking into account the energy constraints of low-power devices. In this work, we propose an energy-aware approach aimed at preserving the privacy of users during inference of human activities. The proposed method is based on a deep learning autoencoder trained to process the signal in order to remove the most sensitive information regarding privacy attributes, without significantly impacting classification accuracy. We also perform a thorough architecture’s parameter tuning of the designed system to enable its implementation on a low- power platform, which we also characterize in terms of energy expenditure. Experimental results show that this system is capable of effectively transforming the signal in order to prevent the inference of sensitive attributes (i.e. weight, height, age, and gender) and it can be conveniently implemented on a constrained embedded system at different levels of the trade-off between accuracy and energy consumption. Indeed, a complete obfuscation of sensitive attributes can be achieved at the cost of a marginal reduction in classification accuracy (5% at most), with an expenditure of around 165 mJ for an execution time of around 30ms needed during the signal transformation step
Do we need early exit networks in human activity recognition?
No full textDeep learning is nowadays considered state-of-the-art technology in many applications thanks to huge performance capabilities. However, the accuracy levels that can be obtained with these models entail computationally demanding resources. This results in a challenging task when such systems have to be deployed on edge devices with tight computing, memory, and communication requirements and when energy expenditure and inference delays have to be kept under control. Early exit is a design methodology aimed at reducing the burden of neural networks on computational resources, trading off accuracy for latency.
In this work, we aim at exploring the use of early exit for human activity recognition tasks. In particular, we propose an experimental assessment of the accuracy–latency trade-off on different deep network architectures across various publicly available datasets. We also evaluate the impact of early exiting in distributed environments by taking into account communication technologies.
Experimental results provide evidence of the significant gain provided by early exits in terms of latency (up to 35
), without a reduction in accuracy (in most cases), confirming the viability of an adaptive approach. In a distributed environment, early exit results are not beneficial in all situations. In particular, it is not convenient for models that are very fast (with inference latency lower than, or as equal as, that of communication) and for models that are forced to make extensive use of far exit points to satisfy the accuracy requirements. Therefore, communication delays in a distributed environment shape performance in an architecture-dependent way
Virtual Networking Performance in OpenStack Platform for Network Function Virtualization
Full text linkThe emerging Network Function Virtualization (NFV) paradigm, coupled with the highly flexible and programmatic control of network devices offered by Software Defined Networking solutions, enables unprecedented levels of network virtualization that will definitely change the shape of future network architectures, where legacy telco central offices will be replaced by cloud data centers located at the edge. On the one hand, this software-centric evolution of telecommunications will allow network operators to take advantage of the increased flexibility and reduced deployment costs typical of cloud computing. On the other hand, it will pose a number of challenges in terms of virtual network performance and customer isolation. This paper intends to provide some insights on how an open-source cloud computing platform such as OpenStack implements multitenant network virtualization and how it can be used to deploy NFV, focusing in particular on packet forwarding performance issues. To this purpose, a set of experiments is presented that refer to a number of scenarios inspired by the cloud computing and NFV paradigms, considering both single tenant and multitenant scenarios. From the results of the evaluation it is possible to highlight potentials and limitations of running NFV on OpenStack
Performance of intent-based virtualized network infrastructure management
No full textThis paper presents the definition and a proof-of-concept implementation of an intent-based northbound interface (NBI) used to orchestrate dynamic service chaining of Virtualized Network Functions (VNFs) by actively controlling the underlying network infrastructure through vendor-independent, technology-agnostic policies. The proof of concept considers a general scenario where VNFs are hosted in different SDN domains, possibly interconnected by non-SDN domains. Being implemented as part of a Virtualized Infrastructure Manager, the proposed NBI is compliant with the ETSI NFV management and orchestration specifications, as well as with the recent ONF definition of intent-based NBI. The case of a network operator that provides adaptive quality of service enforcement in a multi-tenant scenario is considered. Responsiveness of the intent-based NBI is experimentally evaluated under increasing load, proving the correct functionality and the scalability potentials of the proposed approach
Performance of Network Virtualization in cloud computing infrastructures: The OpenStack case
No full textCloud computing infrastructures will likely be a key component of future Internet architectures, owing to the many advantages of server and network virtualization, especially considering the emerging Network Function Virtualization and Software Defined Networking technologies. The cloud infrastructure will then determine the performance of the networking environment. In this paper, such issue is investigated with reference to OpenStack, a widely adopted cloud infrastructure management platform. In particular, the paper provides an insight on how OpenStack deals with multi-tenant network virtualization and evaluates the performance of its main network components by measuring packet throughput in an experimental test-bed
SDN Controller Design for Dynamic Chaining of Virtual Network Functions
No full textNetwork Function Virtualization (NFV) is gaining a lot of interest as a flexible and cost-effective solution for replacing hardware-based, vendor-dependent middle boxes with software appliances running on general purpose hardware in the cloud. This approach provides an unprecedented degree of flexibility with respect to conventional traffic processing based on middle-boxes. In this manuscript a methodology is investigated for the design of general traffic steering policies to implement different service chains through virtual network functions interconnected by a Software Defined Networking (SDN) infrastructure. A proof-of-concept implementation on the Open Stack platform is then presented, to provide a practical example of the feasibility and degree of complexity of the proposed approach
Implementing dynamic chaining of Virtual Network Functions in OpenStack platform
No full textNetwork Function Virtualization (NFV) is gaining a lot of interest as a flexible and cost-effective solution for replacing hardware-based, vendor-dependent middle-boxes with software-based appliances running in a cloud-like network environment. The NFV paradigm is then fundamental to bring the required programmatic capabilities to 5G transport networks. This paper discusses the practical issues of implementing dynamic chaining of virtual network functions running as virtual machines in the industry-standard OpenStack cloud platform. In particular, the focus is on the complexity of the underlying virtual network infrastructure and the design principles of a suitable SDN controller
Smart Mobility and Sensing: Case Studies Based on a Bike Information Gathering Architecture
No full textMapping services and travel planner applications are experiencing a great success in supporting people while they plan a route or while they move across the city, playing a key role in the smart mobility scenario. Nevertheless, they are based on the same algorithms, on the same elements (in terms of time, distance, means of transports, etc.), providing a limited set of personalization. To fill this gap, we propose PUMA, a Personal Urban Mobility Assistant that aims to let the user add different factors of personalization, such as sustainability, street and personal safety, wellness and health, etc. In this paper we focus on the use of smart bikes (equipped with specific sensors) as means of transports and as a mean to collect data about the urban environment. We describe a cloud based architecture, personas and travel scenario to prove the feasibility of our approach
- …
