Automatic recognition of gait-related health problems in the elderly using machine learning

This paper proposes a system for the early automatic recognition of health problems that manifest themselves in distinctive form of gait. Purpose of the system is to prolong the autonomous living of the elderly at home. When the system identifies a health problem, it automatically notifies a physician and provides an explanation of the automatic diagnosis. The gait of the elderly user is captured using a motion-capture system, which consists of body-worn tags and wall-mounted sensors. The positions of the tags are acquired by the sensors and the resulting time series of position coordinates are analyzed with machine-learning algorithms in order to recognize a specific health problem. Novel semantic features based on medical knowledge for training a machine-learning classifier are proposed in this paper. The classifier classifies the user’s gait into: 1) normal, 2) with hemiplegia, 3) with Parkinson’s disease, 4) with pain in the back and 5) with pain in the leg. The studies of 1) the feasibility of automatic recognition and 2) the impact of tag placement and noise level on the accuracy of the recognition of health problems are presented. The experimental results of the first study (12 tags, no noise) showed that the k-nearest neighbors and neural network algorithms achieved classification accuracies of 100%. The experimental results of the second study showed that classification accuracy of over 99% is achievable using several machine-learning algorithms and 8 or more tags with up to 15 mm standard deviation of noise. The results show that the proposed approach achieves high classification accuracy and can be used as a guide for further studies in the increasingly important area of Ambient Assisted Living. Since the system uses semantic features and an artificial-intelligence approach to interpret the health state, provides a natural explanation of the hypothesis and is embedded in the domestic environment of the elderly person; it is an example of the semantic ambient media for Ambient Assisted Living.     

Mechanical properties of wollastonite‐reinforced polypropylene composites modified with SEBS and SEBS‐g‐MA elastomers

Mechanical properties of isotactic polypropylene/wollastonite/styrene rubber block copolymers (iPP/wollastonite/SRBC) composites were studied as a function of elastomeric poly(styrene‐b‐ethylene‐co‐butylene‐b‐styrene) triblock copolymer (SEBS) and SEBS grafted with maleic anhydride (SEBS‐g‐MA) content from 0 to 20 vol%. Microphase morphology was stronger influenced by SRBC elastomers than by different wollastonite types. Higher encapsulation ability of SEBS‐g‐MA than SEBS caused more expressive core‐shell morphology and consequently higher notched impact strength as well as yield parameters, but lower Young's modulus. Higher ductility of the composites with SEBS than with SEBS‐g‐MA has been primarily caused by better miscibility of the polypropylene chains with SEBS molecules. Surface properties of components and adhesion parameters also indicated that adhesion at SEBS‐g‐MA/wollastonite interface, which was stronger than the one at the SEBS/wollastonite interface, influenced higher encapsulation of wollastonite particles by SEBS‐g‐MA. POLYM. ENG. SCI., 47:1873–1880, 2007. © 2007 Society of Plastics Engineers     

Limitations of a Mapping Algorithm with Fragmentation Mimics (MAFM) when modeling statistical data sources based on measured packet network traffic

Knowing the estimation of a statistical process’s parameters for measured network traffic is very important as it can then be further used for the statistical analyses and modeling of network traffic in simulation tools. It is for this reason that different estimation methods are proposed that allow estimations of the statistical processes of network traffic. One of them is our own histograms comparison (EMHC) based method that can be used to estimate statistical data-length process parameters from measured packet traffic. The main part of EMHC method is Mapping Algorithm with Fragmentation Mimics (MAFM).     

Computing median and antimedian sets in median graphs

The median (antimedian) set of a profile π=(u ₁,…,u _k ) of vertices of a graph G is the set of vertices x that minimize (maximize) the remoteness ∑ _i d(x,u _i ). Two algorithms for median graphs G of complexity O(n idim(G)) are designed, where n is the order and idim(G) the isometric dimension of G. The first algorithm computes median sets of profiles and will be in practice often faster than the other algorithm which in addition computes antimedian sets and remoteness functions and works in all partial cubes.     

Interoperability requirements for automated manufacturing systems in construction

Multi-disciplinary software interoperability in the Architecture, Engineering, Construction and Operations industry is becoming a new and widely adopted business culture. Technical advances in interoperability architectures, frameworks, methods and standards during the last decade resulted in higher maturity of product and process models. Mature models, in effect, enable data exchange by an increasing number of software applications in the industry. This establishes trust in data exchange and results in the lower cost impact of inefficient interoperability. The negative cost impact increases with advancing life-cycle phase, from planning and design phase to construction phase and to operation and maintenance phase. Interoperability in the planning and design phase is most mature and well published, while interoperability in the construction phase and for automated manufacturing is less researched. This paper reviews state-of-the art automated manufacturing systems in construction and researches interoperability requirements for automated construction in context of the entire building lifecycle. Our research is based on experimental free-form clay building, designed with embedded simple HVAC components, and manufactured with additive layer technology. Conclusions provide valuable results for interoperability research and practice in construction projects with automated manufacturing systems in place.     

Polypropylene/silica micro‐ and nanocomposites modified with poly(styrene‐b‐ethylene‐co‐butylene‐b‐styrene)

The effects of different silica loadings and elastomeric content on interfacial properties, morphology and mechanical properties of polypropylene/silica 96/4 composites modified with 5, 10, 15, and 20 vol % of poly(styrene‐b‐ethylene‐co‐butylene‐b‐styrene) SEBS added to total composite volume were investigated. Four silica fillers differing in size (nano‐ vs. micro‐) and in surface properties (untreated vs. treated) were chosen as fillers. Elastomer SEBS was added as impact modifier and compatibilizer at the same time. The morphology of ternary polymer composites revealed by light and scanning electron microscopies was compared with morphology predicted models based on interfacial properties. The results indicated that general morphology of composite systems was determined primarily by interfacial properties, whereas the spherulitic morphology of polypropylene matrix was a result of two competitive effects: nucleation effect of filler and solidification effect of elastomer. Tensile and impact strength properties were mainly influenced by combined competetive effects of stiff filler and tough SEBS elastomer. Spherulitic morphology of polypropylene matrix might affect some mechanical properties additionally. © 2014 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2015 , 132, 41486.