Ambient Intelligence for Monitoring Alzheimer Patients

2013 ◽  
Vol 4 (1) ◽  
pp. 23-35 ◽  
Author(s):  
Walid Bourennane ◽  
Yoann Charlon ◽  
Fehd Bettahar ◽  
Marie Chan ◽  
Daniel Esteve ◽  
...  
Keyword(s):  
System Architecture ◽  
Web Application ◽  
Independent Living ◽  
Ambient Intelligence ◽  
Hospital Environment ◽  
Integrated Systems ◽  
Infrared Sensors ◽  
Decision Algorithm ◽  
Distributed Sensors ◽  
Set Up

Distributed sensors allow people to be followed in independent living situations. In this paper, the authors present a multisensor system which allows monitoring elderly people in hospital environment. The system is composed of motion infrared sensors installed in the ceiling, presence sensor in bed and ZigBee tags embedded on the person. From data collected on locations and movements of people, the system determines, through learning, the behavior model and lifestyle. Analysis and decision algorithm in integrated systems provide the functionality to choose actions in order to alert surveillance team and help them by providing historical events record. A web application is also set up to display results of data processing allowing caregivers to monitor patient behavior. Here, they present the system architecture, the technology used, and some preliminary results.

Heterogeneous fairness algorithm based on federated learning in intelligent transportation system

2021 ◽  
pp. 1-9
Author(s):  
Yue Jiang ◽  
Gaochao Xu ◽  
Zhiyi Fang ◽  
Shinan Song ◽  
Bingbing Li
Keyword(s):  
Intelligent Transportation System ◽  
Influence Factor ◽  
Learning Algorithm ◽  
Intelligent Transportation ◽  
Transportation System ◽  
Massive Data ◽  
Infrared Sensors ◽  
Distributed Sensors ◽  
Average Accuracy ◽  
Global Fairness

With the development of the Intelligent Transportation System, various distributed sensors (including GPS, radar, infrared sensors) process massive data and make decisions for emergencies. Federated learning is a new distributed machine learning paradigm, in which system heterogeneity is the difficulty of fairness design. This paper designs a system heterogeneous fair federated learning algorithm (SHFF). SHFF introduces the equipment influence factor I into the optimization target and dynamically adjusts the equipment proportion with other performance. By changing the global fairness parameter θ, the algorithm can control fairness according to the actual needs. Experimental results show that, compared with the popular q-FedAvg algorithm, the SHFF algorithm proposed in this paper improves the average accuracy of the Worst 10% by 26% and reduces the variance by 61%.

scholarly journals Epigraphic Squeezes: Digitisation, Publication, and Enhancement

2020 ◽  
Vol 65 (1) ◽  
pp. 5-16
Author(s):  
Eloisa Paganoni
Keyword(s):  
Relational Database ◽  
Web Application ◽  
Initial Phase ◽  
Current Phase ◽  
Methodological Issues ◽  
The Third ◽  
Research And Teaching ◽  
Database Architecture ◽  
Set Up ◽  
Greek Epigraphy

"Epigraphic squeezes are a key tool for research and teaching. They also have historical and documentary value. They are reliable copies of inscribed text and become the only evidence that remains if inscriptions are lost or destroyed. This paper describes the Venice Squeeze Project for the preservation and enhancement of epigraphic squeezes in the Department of Humanities at Ca’ Foscari University of Venice. For the initial phase of the project, the Ca’ Foscari University collection of epigraphic squeezes was published in the digital ektypotheke E-stampages. The current phase involves developing a web application to digitise epigraphic squeezes according to the metadata architecture of E-stampages. The first part of this paper describes the background of the Venice Squeeze Project and methodological issues, which fostered the partnership with E-stampages. The second part describes the relational database that was set up to digitise the Ca’ Foscari collection. The third part introduces the project initiatives to promote a network of Italian institutions interested in digitizing their collections of epigraphic squeezes. Keywords: Greek epigraphy, squeezes, database architecture"

scholarly journals AUTOMATED INFORMA¬TION SYSTEM FOR GPS MONITORING DATA PROCESSING

2021 ◽  
Vol 2 (37) ◽  
pp. 88-92
Author(s):  
K. Yalova ◽  
K. Yashyna ◽  
O. Tarasiyk
Keyword(s):  
User Interface ◽  
Data Processing ◽  
System Architecture ◽  
Web Application ◽  
Gps Tracking ◽  
System Software ◽  
Web Interfaces ◽  
Application Service ◽  
Functional Features ◽  
Tion System

Using of automated information systems in the field of geolocation data processing increases the control and management efficiency of freight and passenger traffic. The article presents the results of design and software implementation of the automated information system that allows monitoring of GPS tracking data in real time, build routes and set control points for it, generate system messages about the status of vehicles on the route and generate reporting information on the base of user requests. The design of the system architecture and interface was carried out on the basis of developed object and functional data domain models, which take into account its structural and functional features. The microservice approach principles were applied during the developing of the system architecture. The system software is a set of independent services that work in their own process, implement a certain business logic algorithm and communicate with other services through the HTTP protocol. The set of the system software services consists of: a service for working with GPS data, a service for implementing geolocation data processing functions, and a web application service. The main algorithms of the developed system services and their functional features are described in the work. Article’s figures graphically describe developed system site map and system typical Web forms. This data displays the composition of web pages, paths between them and shows the user interface. The design of the user interface was carried out taking into account quality requirements of user graphical web interfaces.

scholarly journals On Rapid Development of Reactive Wireless Sensor Systems

2019 ◽  
Vol 1 (1) ◽  
pp. 574-582
Author(s):  
Paweł Gburzyński ◽  
Elżbieta Kopciuszewska
Keyword(s):  
Operating System ◽  
Software Development ◽  
Programming Language ◽  
Independent Living ◽  
Rapid Development ◽  
Wireless Sensor ◽  
Sensors And Actuators ◽  
Execution Platform ◽  
Small Footprint ◽  
Set Up

AbstractWe present a software platform for designing and testing wireless networks of sensors and actuators (WSNs). The platform consists of three components: an operating system for small-footprint microcontrollers (dubbed PicOS), a software development kit (SDK) amounting to a C-based, event-oriented (reactive) programming language, and a virtual execution platform (VUE2) capable of emulating complete deployment environments for WSNs and thus facilitating their rapid development.1 Its most recent incarnation introduced in the present paper is a component of the WSN lab being currently set up at Vistula in collaboration with Olsonet Communications Corporation.2 We highlight the platform’s most interesting features within the context of a production WSN installed at independent-living facilities.

scholarly journals AtChem, an open source box-model for the Master Chemical Mechanism

2019 ◽  
Author(s):  
Roberto Sommariva ◽  
Sam Cox ◽  
Chris Martin ◽  
Kasia Borońska ◽  
Jenny Young ◽  
...  
Keyword(s):  
Open Source ◽  
Atmospheric Chemistry ◽  
Web Application ◽  
Box Model ◽  
Chemical Mechanism ◽  
Control Software ◽  
Sensitivity Studies ◽  
Master Chemical Mechanism ◽  
Field Campaigns ◽  
Set Up

Abstract. AtChem is an open source zero-dimensional box-model for atmospheric chemistry. Any general set of chemical reactions can be used with AtChem, but the model was designed specifically for use with the Master Chemical Mechanism (MCM, http://mcm.york.ac.uk/). AtChem was initially developed within the EUROCHAMP project as a web application (AtChem-online, https://atchem.leeds.ac.uk/webapp/) for modelling environmental chamber experiments; it was recently upgraded and further developed into a standalone offline version (AtChem2) which allows the user to run complex and long simulations, such as those needed for modelling of intensive field campaigns, as well as to perform batch model runs for sensitivity studies. AtChem is installed, set up and configured using semi-automated scripts and simple text configuration files, making it easy to use even for non-experienced users. A key feature of AtChem is that it can easily be constrained to observational data which may have different timescales, thus retaining all the information contained in the observations. Implementation of a continuous integration workflow, coupled with a comprehensive suite of tests and version control software, makes the AtChem codebase robust, reliable and traceable. The AtChem2 code and documentation are available at https://github.com/AtChem/, under the open source MIT license.

scholarly journals Tracking and Separation of Smart Home Residents through Ambient Activity Sensors

Proceedings ◽  
2019 ◽  
Vol 31 (1) ◽  
pp. 29 ◽  
Author(s):  
Sebastian Matthias Müller ◽  
Andreas Hein
Keyword(s):  
Independent Living ◽  
Tracking System ◽  
Error Rates ◽  
Learning Approaches ◽  
Clustering Methods ◽  
Activity Data ◽  
Related Data ◽  
Health Related ◽  
Increasing Demand ◽  
Set Up

To enable independent living for people in need of care and to accommodate the increasing demand of ambulant care due to demographic changes, a multitude of systems and applications that monitor activities and health-related data based on ambient sensors commonly found in smart homes have been developed. When such a system is used in a multi-person household, some form of identification or separation of residents is required. Most of these systems require permanent participation in the form of body-worn sensors or a complicated supervised learning procedure which may take hours or days to set up. To resolve this, we study several unsupervised learning approaches for the separation of activity data of multiple residents recorded with ambient, binary sensors such as light barriers and contact switches. We show how various clustering methods on data from a tracking system can, under optimal conditions, separate the activity of two residents with low error rates (<2%, Rand Index of 0 . 959 ). We also show that imprecisions in the underlying tracking algorithm have a significant impact on the clustering performance and that most of these errors can be corrected by adding a single “identifying sensor area” into the environment. As a consequence, activity monitoring applications need to rely less on body-worn sensors, which may be forgotten or biometric sensors, which may be perceived as a violation of privacy.

scholarly journals PinAPL-Py: A comprehensive web-application for the analysis of CRISPR/Cas9 screens

2017 ◽  
Author(s):  
Philipp N. Spahn ◽  
Tyler Bath ◽  
Ryan J. Weiss ◽  
Jihoon Kim ◽  
Jeffrey D. Esko ◽  
...  
Keyword(s):  
Web Application ◽  
Large Scale ◽  
Sequencing Data ◽  
Bioinformatic Tools ◽  
Link Type ◽  
Screening Experiments ◽  
Independent Analysis ◽  
Wide Range ◽  
Set Up ◽  
Sequence Quality

AbstractBackgroundLarge-scale genetic screens using CRISPR/Cas9 technology have emerged as a major tool for functional genomics. With its increased popularity, experimental biologists frequently acquire large sequencing datasets for which they often do not have an easy analysis option. While a few bioinformatic tools have been developed for this purpose, their utility is still hindered either due to limited functionality or the requirement of bioinformatic expertise.ResultsTo make sequencing data analysis of CRISPR/Cas9 screens more accessible to a wide range of scientists, we developed a Platform-independent Analysis of Pooled Screens using Python (PinAPL-Py), which is operated as an intuitive web-service. PinAPL-Py implements state-of-the-art tools and statistical models, assembled in a comprehensive workflow covering sequence quality control, automated sgRNA sequence extraction, alignment, sgRNA enrichment/depletion analysis and gene ranking. The workflow is set up to use a variety of popular sgRNA libraries as well as custom libraries that can be easily uploaded. Various analysis options are offered, suitable to analyze a large variety of CRISPR/Cas9 screening experiments. Analysis output includes ranked lists of sgRNAs and genes, and publication-ready plots.ConclusionsPinAPL-Py helps to advance genome-wide screening efforts by combining comprehensive functionality with user-friendly implementation. PinAPL-Py is freely accessible at http://pinapl-py.ucsd.edu with instructions, documentation and test datasets. The source code is available at https://github.com/LewisLabUCSD/PinAPL-Py

scholarly journals Systemic Problem Structuring in a Complex Hospital Environment using Viable System Diagnosis – Keeping the Blood Flowing

2021 ◽  
Author(s):  
Maren Berge Vik ◽  
Hanne Finnestrand ◽  
Robert L. Flood
Keyword(s):  
Orthopedic Surgery ◽  
Complex Form ◽  
Hospital Environment ◽  
Problem Structuring ◽  
Large Hospital ◽  
Systemic Thinking ◽  
System Diagnosis ◽  
Human Organization ◽  
Set Up ◽  
Viable System

AbstractThis article presents the application of the systemic problem structuring approach Viable System Diagnosis (VSD) within the Department of Orthopedic Surgery in a large hospital in Norway. It explains why systemic thinking is relevant to this uniquely complex form of human organization. The department was coping with systemic dysfunction and VSD was chosen because previous applications demonstrated VSD excels at diagnosis of what is causing dysfunction. VSD was employed through a participatory framework that included in the process, among other stakeholders, medics, technologists, managers, administrators and, as far as possible given the sensitive nature of patient information, the patient. VSD guided thinking about what the organization is set up to do and the existing organizational arrangements to achieve that. The outcome was an agenda for debate that guided stakeholder discussions toward ways and means of improving organizational arrangements. The article briefly reviews previous applications of VSD in the hospital sector and other large complex organisations.

Sign in / Sign up

Export Citation Format

Share Document