Attention is an increasingly popular mechanism used in a wide range of neural architectures. The mechanism itself has been realized in a variety of formats. However, because of the fast-paced advances in this domain, a systematic overview of attention is still missing. In this article, we define a unified model for attention architectures in natural language processing, with a focus on those designed to work with vector representations of the textual data. We propose a taxonomy of attention models according to four dimensions: the representation of the input, the compatibility function, the distribution function, and the multiplicity of the input and/or output. We present the examples of how prior information can be exploited in attention models and discuss ongoing research efforts and open challenges in the area, providing the first extensive categorization of the vast body of literature in this exciting domain.

In this work, a flexible and extensive digital platform for Smart Homes is presented, exploiting the most advanced technologies of the Internet of Things, such as Radio Frequency Identification, wearable electronics, Wireless Sensor Networks, and Artificial Intelligence. Thus, the main novelty of the paper is the system-level description of the platform flexibility allowing the interoperability of different smart devices. This research was developed within the framework of the operative project HABITAT (Home Assistance Based on the Internet of Things for the Autonomy of Everybody), aiming at developing smart devices to support elderly people both in their own houses and in retirement homes, and embedding them in everyday life objects, thus reducing the expenses for healthcare due to the lower need for personal assistance, and providing a better life quality to the elderly users.

Craniofacial superimposition is a technique potentially useful for the identification of unidentified human remains if a photo of the missing person is available. We have tested the reliability of the 2D-3D computer-aided nonautomatic superimposition techniques. Three-dimension laser scans of five skulls and ten photographs were overlaid with an imaging software. The resulting superimpositions were evaluated using three methods: craniofacial landmarks, morphological features, and a combination of the two. A 3D model of each skull without its mandible was tested for superimposition; we also evaluated whether separating skulls by sex would increase correct identifications. Results show that the landmark method employing the entire skull is the more reliable one (5/5 correct identifications, 40% false positives [FP]), regardless of sex. However, the persistence of a high percentage of FP in all the methods evaluated indicates that these methods are unreliable for positive identification although the landmark-only method could be useful for exclusion.

No abstract

Sporadic Creutzfeldt-Jakob disease (sCJD) is the commonest form of human prion diseases, accounting for about 85% of all cases. Current criteria for intra vitam diagnosis include a distinct phenotype, periodic sharp and slow-wave complexes at electroencephalography (EEG), and a positive 14-3-3-protein assay in the cerebrospinal fluid (CSF). In sCJD, the disease phenotype may vary, depending upon the genotype at codon 129 of the prion protein gene (PRNP), a site of a common methionine/valine polymorphism, and two distinct conformers of the pathological prion protein. Based on the combination of these molecular determinants, six different sCJD subtypes are recognized, each with distinctive clinical and pathologic phenotypes. We analyzed CSF samples from 127 subjects with definite sCJD to assess the diagnostic value of 14-3-3 protein, total tau protein, phosphorylated181 tau, and amyloid beta (Aβ) peptide 1-42, either alone or in combination. While the 14-3-3 assay and tau protein levels were the most sensitive indicators of sCJD, the highest sensitivity, specificity and positive predictive value were obtained when all the above markers were combined. The latter approach also allowed a reliable differential diagnosis with other neurodegenerative dementias.