1,720,972 research outputs found
Real-time Energy-efficient Sensor Libraries for Wearable Devices
No full textThe growing popularity of wearable technology has led to a surge in smartwatch usage among the general public. These devices offer a range of features, including internet connectivity, fitness tracking, and real-time notifications, making them valuable tools for staying connected to the online world while remaining engaged in real-world activities. Smartwatches have become powerful platforms for Human Activity Recognition (HAR) applications thanks to the increasing computational power and the presence of a wide array of sensors, such as accelerometers, gyroscopes, heart rate, and step counters. Efficient real-time data collection from internal sensors is a crucial requirement for HAR applications on wearable devices due to their constraints in battery size and duration. In this paper, we introduce the implementation of three energy-efficient user-level libraries developed for real-time data collection from inertial sensors using native Wear OS APIs and different techniques: Thread, Flow, and Channel. Experiments were conducted on a commercially available Oppo smartwatch comparing them in terms of code size, memory utilization, and energy consumption. The characterization results show that the Channel implementation, which reduces code size by 45% and consumes 75% less energy, is lightweight and versatile. This makes it well-suited for wearable devices without significantly impacting battery life and system performance. Additionally, our findings indicate that choice of programming approach significantly impacts energy consumption, highlighting the importance of optimizing performance and battery life. Furthermore, understanding the interactions between application and system optimization policies is essential for improving energy efficiency in Wear OS applications
Ferritin nanocages for theranostic applications
Full text linkFerritin is a ubiquitous protein involved in iron storage composed of 24 subunits assembled in a hollow spherical nano-cage architecture. Channels formed between the intersection of peptide subunits are lined with polar aminoacids and allow for the entry and exit of cations. Ferritin can be successfully used as an highly biocompatible nanocarrier, due to the ability of being recognized and uptaken by TfR-1 overexpressing tumour cells. Furthermore, both inner or outer surface can be easily functionalized conferring multiple functionalities onto a single molecule. For these reasons, ferritins are emerging as novel biotech platforms for biomedical applications (both diagnostical and therapeutic) due to their ability to encapsulate cargo molecules, broad functionalization possibilities and selective targeting properties.
In this framework, the present work has been focused on the development and characterization of engineered recombinant mammalian and archaeal ferritin constructs to expand the scope of their nanotechnological applications.
With the aim of investigating the biological and biophysical properties of prokaryotic homopolymers and characterizing the permeability of the prokaryotic protein shell toward diffusants, two ferritins from Archaea have been chosen as model. A set of engineered mutants of Pyrococcus furiosus ferritin (Pf-Ft) and Archaeoglobus fulgidus ferritin (Af-Ft) have been obtained by placing a reactive cysteine residue per subunit in the same topological positions either inside or outside the internal cavity. These mutants differ from each other by the aminoacid composition of ferritin channels and the related “open” versus “closed” ferritin architecture. The molecular diffusion through the ferritin cavity has been characterized by studying within these mutants the cysteine reactivity toward the bulky and negatively charged DTNB molecule (5,5'-dithiobis-2-nitrobenzoic acid).
Moreover, Archaeoglobus fulgidus ferritin has been genetically engineered by changing the surface exposed loop connecting helices B and C to mimic the sequence of the analogous human H-chain ferritin loop. This novel “humanized” chimeric construct (named HumAf-Ft) thus combines the unique open structure and self-assembly properties of Af-Ft with the typical humanH-ferritin ability to bind the Transferrin Receptor TfR-1, which is overexpressed in several types of tumor cells. HumAfFt has been structurally and biophysically characterized and the improved cellular uptake has been demonstrated on HeLa cell line.
Lastly, to exploit lanthanide fluorescence properties and develop an intrinsically fluorescent nanoparticle, a novel construct has been developed by genetically fusing at the C-terminal end of mouse H-ferritin a lanthanide binding tag (LBT). LBTs are short peptides that selectively bind lanthanide ions at low-nanomolar affinities and, due to the presence of a tryptophan residue, provide strong FRET sensitization. This novel construct (named HFt-LBT) has been designed by locating the tag inside the inner cavity, so that the lanthanide ions diffusing through the surface pores can eventually bind to the LBT sequence. HFt-LBT would thus act both as carrier targeted to TfR-1 receptor and as a FRET sensitizer. Fluorescence improvement and lanthanide binding properties have been investigated by spectrophotometric measurements using Tb+3 as lanthanide probe. The structural characterization has been carried out and cellular uptake by HeLa cell line has been assessed as well
Unstructured Handwashing Recognition using Smartwatch to Reduce Contact Transmission of Pathogens
Full text linkCurrent guidelines from the World Health Organization indicate that the
SARS-CoV-2 coronavirus, which results in the novel coronavirus disease
(COVID-19), is transmitted through respiratory droplets or by contact. Contact
transmission occurs when contaminated hands touch the mucous membrane of the
mouth, nose, or eyes so hands hygiene is extremely important to prevent the
spread of the SARSCoV-2 as well as of other pathogens. The vast proliferation
of wearable devices, such as smartwatches, containing acceleration, rotation,
magnetic field sensors, etc., together with the modern technologies of
artificial intelligence, such as machine learning and more recently
deep-learning, allow the development of accurate applications for recognition
and classification of human activities such as: walking, climbing stairs,
running, clapping, sitting, sleeping, etc. In this work, we evaluate the
feasibility of a machine learning based system which, starting from inertial
signals collected from wearable devices such as current smartwatches,
recognizes when a subject is washing or rubbing its hands. Preliminary results,
obtained over two different datasets, show a classification accuracy of about
95% and of about 94% for respectively deep and standard learning techniques
A power-aware vision-based virtual sensor for real-time edge computing
No full textGraphics processing units and tensor processing units coupled with tiny machine learning models deployed on edge devices are revolutionizing computer vision and real-time tracking systems. However, edge devices pose tight resource and power constraints. This paper proposes a real-time vision-based virtual sensors paradigm to provide power-aware multi-object tracking at the edge while preserving tracking accuracy and enhancing privacy. We thoroughly describe our proposed system architecture, focusing on the Dynamic Inference Power Manager (DIPM). Our proposed DIPM is based on an adaptive frame rate to provide energy savings. We implement and deploy the virtual sensor and the DIPM on the NVIDIA Jetson Nano edge platform to prove the effectiveness and efficiency of the proposed solution. The results of extensive experiments demonstrate that the proposed virtual sensor can achieve a reduction in energy consumption of about 36% in videos with relatively low dynamicity and about 21% in more dynamic video content while simultaneously maintaining tracking accuracy within a range of less than 1.2%
Semantic Template Recognition of Human Activities in Wearable Sensor Data Using Siamese Network
Full text linkHuman activity recognition plays a pivotal role in various fields, such as healthcare monitoring, smart environments, and human-computer interaction. In this study, we propose a novel approach for sensor-based human activity recognition.The key contribution of our work consists of first, defining activity representations we call “semantic templates”, which represent prototypical activity patterns of different human activity classes; second, designing and implementing a novel lightweight and versatile classifier for sensor-based HAR that leverages template matching through a deep-learning Siamese network. Through a series of rigorous experiments conducted on three distinct public datasets, we also demonstrate that the proposed approach yields enhanced performance in recognizing human activities when compared to a traditional deep multi-class classifier for resource-constrained devices. Furthermore, we showcase how our approach outperforms previous works by up to 20% in classifying previously unseen activities, paving the way for developing class-incremental continuous learning techniques
A Vision-based Virtual Sensor to Enhance Privacy and Energy Efficiency on Edge Computing
No full textIntegrating vision-based technologies into distributed sensor domains offers unprecedented potential for data collection. However, it raises privacy concerns over the incredible amount of extra information inadvertently carried by the video stream. On the other hand, the advent of tiny machine learning models running on edge devices with embedded GPUs/TPUs is revolutionizing computer vision and real-time tracking systems, enabling the local execution of computationally demanding tasks traditionally performed in the cloud. This study focuses on developing and characterizing vision-based virtual sensors capable of processing data from a local camera source to provide real-time measures of relevant metrics without storing or transmitting any video stream. The main advantages of vision-based virtual sensors running on the edge are data protection, reduced communication cost, and reduced detection latency. In addition, we propose a dynamic inference power manager (DIPM), based on adaptive frame rate, that allows us to explore the trade-off between power consumption and accuracy. Experimental results conducted on a real hardware platform show that the proposed virtual sensor, equipped with DIPM, can save up to 40% of the processing energy with a reduction of tracking accuracy lower than 10%, while retaining the privacy preservation benefits of virtual sensors
EESiamese: Energy-efficient Siamese Neural Network for Constrained Devices
No full textAs the deployment of artificial intelligence applications continues to expand, the demand for energy-efficient models tailored for resource-constrained devices has become increasingly critical. This paper introduces a novel approach to address this challenge by proposing an Energy-Efficient Siamese Neural Network (EESiamese) specifically designed for constrained devices such as edge computing platforms, IoT devices, and other low-power computing environments deployment. The EESiamese architecture is carefully crafted to optimize both accuracy and energy consumption. Through systematically exploring model architectures and hyperparameters, we present a fine-tuned EESiamese model that achieves competitive performance compared to traditional Siamese networks while significantly mitigating the energy overhead. Extensive experiments are conducted across a variety of constrained devices to validate the efficacy of the proposed EESiamese model in real-world scenarios. The findings demonstrate the high energy efficiency of the EESiamese, which is executed in a fraction of a millisecond and maintains an accuracy greater than 96%
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
- …
