In deep learning, a convolutional neural network (ConvNet or CNN) is a powerful tool for building interesting embedded applications that use data to make predictions. An application running on an embedded system typically has limited access to memory resources, processing power, and storage. Implementing deep convolutional neural network-based infe...
Published in Archives of Civil and Mechanical Engineering
The paper describes the results obtained from the tensile and compression experimental tests of the structural tempered glass plates with three different types of stress concentrators and without them. The types of stress concentrator have been chosen as close as possible to those usually found in practical situations and also taking into account t...
Published in BMC Biomedical Engineering
Tourniquets in orthopaedic surgery safely provide blood free surgical fields, but their use is not without risk. Tourniquets can result in temporary or permanent injury to underlying nerves, muscles, blood vessels and soft tissues. Advances in safety, accuracy and reliability of surgical tourniquet systems have reduced nerve-related injuries by red...
In recent years, point clouds have gained popularity as a promising representation for volumetric contents in immersive scenarios. Standardization bodies such as MPEG have been developing new compression standards for point cloud contents to reduce the volume of data, while maintaining an acceptable level of visual quality. To do so, reliable metri...
Published in Genome Biology
BackgroundUnsupervised compression algorithms applied to gene expression data extract latent or hidden signals representing technical and biological sources of variation. However, these algorithms require a user to select a biologically appropriate latent space dimensionality. In practice, most researchers fit a single algorithm and latent dimensio...
Published in Heliyon
Condensed matter physics; Materials Science; Physical chemistry; Thermodynamics; CZTS; Photovoltaic conversion; Compression; Dilatation; Electrical conductivity; Density of states.
Published in Journal of fish biology
Vertebral deformities in salmonid interspecific hybrids, some of which were triploidised, were assessed across three separate year classes during the freshwater life stage. Initially we crossed the eggs from a farmed Atlantic salmon Salmo salar with the sperm from either an S. salar, arctic char Salvelinus alpinus, or brown trout S. trutta. For S. ...
Published in Advances in Knowledge Discovery and Data Mining
With the rise of Big Data, there has been a significant effort in increasing compute power through GPUs, TPUs, and heterogeneous architectures. As a result, many applications are memory bound, i.e., they are bottlenecked by the movement of data from main memory to compute units. One way to address this issue is through data prefetching, which relie...
Published in The American Journal of Emergency Medicine
Unlabelled Image
Recurrent Neural Networks (RNNs) are a class of machine learning algorithms used for applications with time-series and sequential data. Recently, there has been a strong interest in executing RNNs on embedded devices. However, difficulties have arisen because RNN requires high computational capability and a large memory space. In this paper, we rev...
