A multifactorial analysis of obesity as CVD risk factor: use of neural network based methods in a nutrigenetics context

Obesity is a multifactorial trait, which comprises an independent risk factor for cardiovascular disease (CVD). The aim of the current work is to study the complex etiology beneath obesity and identify genetic variations and/or factors related to nutrition that contribute to its variability. To this end, a set of more than 2300 white subjects who participated in a nutrigenetics study was used. For each subject a total of 63 factors describing genetic variants related to CVD (24 in total), gender, and nutrition (38 in total), e.g. average daily intake in calories and cholesterol, were measured. Each subject was categorized according to body mass index (BMI) as normal (BMI ≤ 25) or overweight (BMI > 25). Two artificial neural network (ANN) based methods were designed and used towards the analysis of the available data. These corresponded to i) a multi-layer feed-forward ANN combined with a parameter decreasing method (PDM-ANN), and ii) a multi-layer feed-forward ANN trained by a hybrid method (GA-ANN) which combines genetic algorithms and the popular back-propagation training algorithm.

Evaluating retraining rules for semi-supervised learning in neural network based cursive word recognition

Training a system to recognize handwritten words is a task that requires a large amount of data with their correct transcription. However, the creation of such a training set, including the generation of the ground truth, is tedious and costly. One way of reducing the high cost of labeled training data acquisition is to exploit unlabeled data, which can be gathered easily. Making use of both labeled and unlabeled data is known as semi-supervised learning. One of the most general versions of semi-supervised learning is self-training, where a recognizer iteratively retrains itself on its own output on new, unlabeled data. In this paper we propose to apply semi-supervised learning, and in particular self-training, to the problem of cursive, handwritten word recognition. The special focus of the paper is on retraining rules that define what data are actually being used in the retraining phase. In a series of experiments it is shown that the performance of a neural network based recognizer can be significantly improved through the use of unlabeled data and self-training if appropriate retraining rules are applied.

Neural network based glucose - insulin metabolism models for children with Type 1 diabetes

In this paper two models for the simulation of glucose-insulin metabolism of children with Type 1 diabetes are presented. The models are based on the combined use of Compartmental Models (CMs) and artificial Neural Networks (NNs). Data from children with Type 1 diabetes, stored in a database, have been used as input to the models. The data are taken from four children with Type 1 diabetes and contain information about glucose levels taken from continuous glucose monitoring system, insulin intake and food intake, along with corresponding time. The influences of taken insulin on plasma insulin concentration, as well as the effect of food intake on glucose input into the blood from the gut, are estimated from the CMs. The outputs of CMs, along with previous glucose measurements, are fed to a NN, which provides short-term prediction of glucose values. For comparative reasons two different NN architectures have been tested: a Feed-Forward NN (FFNN) trained with the back-propagation algorithm with adaptive learning rate and momentum, and a Recurrent NN (RNN), trained with the Real Time Recurrent Learning (RTRL) algorithm. The results indicate that the best prediction performance can be achieved by the use of RNN.

A social network-based approach to assess de facto independence of regulatory agencies

This article uses a policy network perspective to assess the independence of regulatory agencies (RAs) in liberalized public utility sectors. We focus on the de facto independence of RAs from elected politicians, regulatees and other co-regulators. We go further than previous studies, which only undertook a general analysis of the de jure independence of RAs from political authorities. Specifically, we apply a social network analysis (SNA), which concentrates on the attributes and relational profiles of all actors involved in new regulatory arrangements. The concept of de facto independence is applied to the Swiss telecommunications sector in order to provide initial empirical insights. Results clearly show that SNA indicators are an appropriate tool to identify the de facto independence of RAs and can improve knowledge about the issues arising from the emergence of the ‘regulatory State’.

Real-Time Localization Using Software Defined Radio

Service providers make use of cost-effective wireless solutions to identify, localize, and possibly track users using their carried MDs to support added services, such as geo-advertisement, security, and management. Indoor and outdoor hotspot areas play a significant role for such services. However, GPS does not work in many of these areas. To solve this problem, service providers leverage available indoor radio technologies, such as WiFi, GSM, and LTE, to identify and localize users. We focus our research on passive services provided by third parties, which are responsible for (i) data acquisition and (ii) processing, and network-based services, where (i) and (ii) are done inside the serving network. For better understanding of parameters that affect indoor localization, we investigate several factors that affect indoor signal propagation for both Bluetooth and WiFi technologies. For GSM-based passive services, we developed first a data acquisition module: a GSM receiver that can overhear GSM uplink messages transmitted by MDs while being invisible. A set of optimizations were made for the receiver components to support wideband capturing of the GSM spectrum while operating in real-time. Processing the wide-spectrum of the GSM is possible using a proposed distributed processing approach over an IP network. Then, to overcome the lack of information about tracked devices’ radio settings, we developed two novel localization algorithms that rely on proximity-based solutions to estimate in real environments devices’ locations. Given the challenging indoor environment on radio signals, such as NLOS reception and multipath propagation, we developed an original algorithm to detect and remove contaminated radio signals before being fed to the localization algorithm. To improve the localization algorithm, we extended our work with a hybrid based approach that uses both WiFi and GSM interfaces to localize users. For network-based services, we used a software implementation of a LTE base station to develop our algorithms, which characterize the indoor environment before applying the localization algorithm. Experiments were conducted without any special hardware, any prior knowledge of the indoor layout or any offline calibration of the system.

Real-time localization using software defined radio

Service providers make use of cost-effective wireless solutions to identify, localize, and possibly track users using their carried MDs to support added services, such as geo-advertisement, security, and management. Indoor and outdoor hotspot areas play a significant role for such services. However, GPS does not work in many of these areas. To solve this problem, service providers leverage available indoor radio technologies, such as WiFi, GSM, and LTE, to identify and localize users. We focus our research on passive services provided by third parties, which are responsible for (i) data acquisition and (ii) processing, and network-based services, where (i) and (ii) are done inside the serving network. For better understanding of parameters that affect indoor localization, we investigate several factors that affect indoor signal propagation for both Bluetooth and WiFi technologies. For GSM-based passive services, we developed first a data acquisition module: a GSM receiver that can overhear GSM uplink messages transmitted by MDs while being invisible. A set of optimizations were made for the receiver components to support wideband capturing of the GSM spectrum while operating in real-time. Processing the wide-spectrum of the GSM is possible using a proposed distributed processing approach over an IP network. Then, to overcome the lack of information about tracked devices’ radio settings, we developed two novel localization algorithms that rely on proximity-based solutions to estimate in real environments devices’ locations. Given the challenging indoor environment on radio signals, such as NLOS reception and multipath propagation, we developed an original algorithm to detect and remove contaminated radio signals before being fed to the localization algorithm. To improve the localization algorithm, we extended our work with a hybrid based approach that uses both WiFi and GSM interfaces to localize users. For network-based services, we used a software implementation of a LTE base station to develop our algorithms, which characterize the indoor environment before applying the localization algorithm. Experiments were conducted without any special hardware, any prior knowledge of the indoor layout or any offline calibration of the system.

Application and comparison of classification algorithms for recognition of Alzheimer's disease in electrical brain activity (EEG)

The early detection of subjects with probable Alzheimer's disease (AD) is crucial for effective appliance of treatment strategies. Here we explored the ability of a multitude of linear and non-linear classification algorithms to discriminate between the electroencephalograms (EEGs) of patients with varying degree of AD and their age-matched control subjects. Absolute and relative spectral power, distribution of spectral power, and measures of spatial synchronization were calculated from recordings of resting eyes-closed continuous EEGs of 45 healthy controls, 116 patients with mild AD and 81 patients with moderate AD, recruited in two different centers (Stockholm, New York). The applied classification algorithms were: principal component linear discriminant analysis (PC LDA), partial least squares LDA (PLS LDA), principal component logistic regression (PC LR), partial least squares logistic regression (PLS LR), bagging, random forest, support vector machines (SVM) and feed-forward neural network. Based on 10-fold cross-validation runs it could be demonstrated that even tough modern computer-intensive classification algorithms such as random forests, SVM and neural networks show a slight superiority, more classical classification algorithms performed nearly equally well. Using random forests classification a considerable sensitivity of up to 85% and a specificity of 78%, respectively for the test of even only mild AD patients has been reached, whereas for the comparison of moderate AD vs. controls, using SVM and neural networks, values of 89% and 88% for sensitivity and specificity were achieved. Such a remarkable performance proves the value of these classification algorithms for clinical diagnostics.

AccessMod 3.0: computing geographic coverage and accessibility to health care services using anisotropic movement of patients

Background Access to health care can be described along four dimensions: geographic accessibility, availability, financial accessibility and acceptability. Geographic accessibility measures how physically accessible resources are for the population, while availability reflects what resources are available and in what amount. Combining these two types of measure into a single index provides a measure of geographic (or spatial) coverage, which is an important measure for assessing the degree of accessibility of a health care network. Results This paper describes the latest version of AccessMod, an extension to the Geographical Information System ArcView 3.×, and provides an example of application of this tool. AccessMod 3 allows one to compute geographic coverage to health care using terrain information and population distribution. Four major types of analysis are available in AccessMod: (1) modeling the coverage of catchment areas linked to an existing health facility network based on travel time, to provide a measure of physical accessibility to health care; (2) modeling geographic coverage according to the availability of services; (3) projecting the coverage of a scaling-up of an existing network; (4) providing information for cost effectiveness analysis when little information about the existing network is available. In addition to integrating travelling time, population distribution and the population coverage capacity specific to each health facility in the network, AccessMod can incorporate the influence of landscape components (e.g. topography, river and road networks, vegetation) that impact travelling time to and from facilities. Topographical constraints can be taken into account through an anisotropic analysis that considers the direction of movement. We provide an example of the application of AccessMod in the southern part of Malawi that shows the influences of the landscape constraints and of the modes of transportation on geographic coverage. Conclusion By incorporating the demand (population) and the supply (capacities of heath care centers), AccessMod provides a unifying tool to efficiently assess the geographic coverage of a network of health care facilities. This tool should be of particular interest to developing countries that have a relatively good geographic information on population distribution, terrain, and health facility locations.

Structural and Institutional Determinants of Influence Reputation: A Comparison of Collaborative and Adversarial Policy Networks in Decision Making and Implementation

The central assumption in the literature on collaborative networks and policy networks is that political outcomes are affected by a variety of state and nonstate actors. Some of these actors are more powerful than others and can therefore have a considerable effect on decision making. In this article, we seek to provide a structural and institutional explanation for these power differentials in policy networks and support the explanation with empirical evidence. We use a dyadic measure of influence reputation as a proxy for power, and posit that influence reputation over the political outcome is related to vertical integration into the political system by means of formal decision-making authority, and to horizontal integration by means of being well embedded into the policy network. Hence, we argue that actors are perceived as influential because of two complementary factors: (a) their institutional roles and (b) their structural positions in the policy network. Based on temporal and cross-sectional exponential random graph models, we compare five cases about climate, telecommunications, flood prevention, and toxic chemicals politics in Switzerland and Germany. The five networks cover national and local networks at different stages of the policy cycle. The results confirm that institutional and structural drivers seem to have a crucial impact on how an actor is perceived in decision making and implementation and, therefore, their ability to significantly shape outputs and service delivery.

The HIV care cascade in Switzerland: reaching the UNAIDS/WHO targets for patients diagnosed with HIV.

OBJECTIVES To describe the HIV care cascade for Switzerland in the year 2012. DESIGN/METHODS Six levels were defined: (i) HIV-infected, (ii) HIV-diagnosed, (iii) linked to care, (iv) retained in care, (v) on antiretroviral treatment (ART), and (vi) with suppressed viral load (VL). We used data from the Swiss HIV Cohort Study (SHCS) complemented by a nationwide survey among SHCS physicians to estimate the number of HIV-patients not registered in the cohort. We also used Swiss ART sales data to estimate the number of patients treated outside the SHCS network. Based on the number of patients retained in care, we inferred the estimates for levels (i) to (iii) from previously published data. RESULTS We estimate that (i) 15,200 HIV-infected individuals lived in Switzerland in 2012 (margins of uncertainty, 13,400-19,300). Of those, (ii) 12,300 (81%) were diagnosed, (iii) 12,200 (80%) linked, and (iv) 11,900 (79%) retained in care. Broadly based on SHCS network data, (v) 10,800 (71%) patients were receiving ART, and (vi) 10,400 (68%) had suppressed (<200 copies/ml) VLs. The vast majority (95%) of patients retained in care were followed within the SHCS network, with 76% registered in the cohort. CONCLUSIONS Our estimate for HIV-infected individuals in Switzerland is substantially lower than previously reported, halving previous national HIV prevalence estimates to 0.2%. In Switzerland in 2012, 91% of patients in care were receiving ART, and 96% of patients on ART had suppressed VL, meeting recent UNAIDS/WHO targets.

Fine-grained Indoor Tracking by Fusing Inertial Sensor and Physical Layer Information in WLANs

Indoor positioning has become an emerging research area because of huge commercial demands for location-based services in indoor environments. Channel State Information (CSI) as a fine-grained physical layer information has been recently proposed to achieve high positioning accuracy by using range-based methods, e.g., trilateration. In this work, we propose to fuse the CSI-based ranges and velocity estimated from inertial sensors by an enhanced particle filter to achieve highly accurate tracking. The algorithm relies on some enhanced ranging methods and further mitigates the remaining ranging errors by a weighting technique. Additionally, we provide an efficient method to estimate the velocity based on inertial sensors. The algorithms are designed in a network-based system, which uses rather cheap commercial devices as anchor nodes. We evaluate our system in a complex environment along three different moving paths. Our proposed tracking method can achieve 1:3m for mean accuracy and 2:2m for 90% accuracy, which is more accurate and stable than pedestrian dead reckoning and range-based positioning.

A variationist approach to the examination of insertion and deletion of /h/ in Kosraean English

I report on language variation in the unresearched variety of English emerging on Kosrae, Federated States of Micronesia. English is spoken as the inter-island lingua franca throughout Micronesia and has been the official language of FSM since gaining its independence in 1986, though still retaining close ties with the US through and economic “compact” agreement. I present here an analysis of a corpus of over 90 Kosraean English speakers, compiled during a three month fieldwork trip to the island in the Western Pacific. The 45 minute sociolinguistically sensitive recordings are drawn from a corpus of old and young, with varying levels of education and occupations, and off-island experiences. In the paper I analyse two variables. The first variable is the realisation of /h/, often subject to deletion in both L1 and L2 varieties of English. Such occurrences are commonly associated with Cockney English, but also found in Caribbean English and the postcolonial English of Australia. For example:  Male, 31: yeah I build their house their local huts and they pay me /h/ deletion is frequent in Kosraean English, but, perhaps expectedly, occurs slightly less among people with higher contact with American English, through having spent longer periods off island. The second feature under scrutiny is the variable epenthesis of [h] to provide a consonantal onset to vowel-initial syllables.  Male, 31: that guy is really hold now This practice is also found beyond Kosraean English. Previous studies find h-epenthesis arising in L1 varieties including Newfoundland and Tristan de Cunha English, while similar manifestations are identified in Francophone L2 learners of English. My variationist statistical analysis has shown [h] insertion:  to disproportionately occur intervocalically;  to be constrained by both speaker gender and age: older males are much more likely to epenthesis [h] in their speech;  to be more likely in the onset of stressed as opposed to unstressed syllables. In light of the findings of my analysis, I consider the relationship between h-deletion and h-epenthesis, the plausibility of hypercorrection as a motivation for the variation, and the potential influence of the substrate language, alongside sociolinguistic factors such as attitudes towards the US based on mobility. The analysis sheds light on the extent to which different varieties share this characteristic and the comparability of them in terms of linguistic constraints and attributes. Clarke, S. (2010). Newfoundland and Labrador English. Edinburgh: Edinburgh University Press Hackert, S. (2004). Urban Bahamian Creole: System and Variation. Varieties of English Around the World G32. Amsterdam: Benjamins Milroy, J. (1983). On the Sociolinguistic History of H-dropping in English in Current topics in English historical linguistics: Odense UP

TrypanoCyc: a community-led biochemical pathways database for Trypanosoma brucei.

The metabolic network of a cell represents the catabolic and anabolic reactions that interconvert small molecules (metabolites) through the activity of enzymes, transporters and non-catalyzed chemical reactions. Our understanding of individual metabolic networks is increasing as we learn more about the enzymes that are active in particular cells under particular conditions and as technologies advance to allow detailed measurements of the cellular metabolome. Metabolic network databases are of increasing importance in allowing us to contextualise data sets emerging from transcriptomic, proteomic and metabolomic experiments. Here we present a dynamic database, TrypanoCyc (http://www.metexplore.fr/trypanocyc/), which describes the generic and condition-specific metabolic network of Trypanosoma brucei, a parasitic protozoan responsible for human and animal African trypanosomiasis. In addition to enabling navigation through the BioCyc-based TrypanoCyc interface, we have also implemented a network-based representation of the information through MetExplore, yielding a novel environment in which to visualise the metabolism of this important parasite.

Fine-grained indoor positioning and tracking systems

Indoor positioning has attracted considerable attention for decades due to the increasing demands for location based services. In the past years, although numerous methods have been proposed for indoor positioning, it is still challenging to find a convincing solution that combines high positioning accuracy and ease of deployment. Radio-based indoor positioning has emerged as a dominant method due to its ubiquitousness, especially for WiFi. RSSI (Received Signal Strength Indicator) has been investigated in the area of indoor positioning for decades. However, it is prone to multipath propagation and hence fingerprinting has become the most commonly used method for indoor positioning using RSSI. The drawback of fingerprinting is that it requires intensive labour efforts to calibrate the radio map prior to experiments, which makes the deployment of the positioning system very time consuming. Using time information as another way for radio-based indoor positioning is challenged by time synchronization among anchor nodes and timestamp accuracy. Besides radio-based positioning methods, intensive research has been conducted to make use of inertial sensors for indoor tracking due to the fast developments of smartphones. However, these methods are normally prone to accumulative errors and might not be available for some applications, such as passive positioning. This thesis focuses on network-based indoor positioning and tracking systems, mainly for passive positioning, which does not require the participation of targets in the positioning process. To achieve high positioning accuracy, we work on some information of radio signals from physical-layer processing, such as timestamps and channel information. The contributions in this thesis can be divided into two parts: time-based positioning and channel information based positioning. First, for time-based indoor positioning (especially for narrow-band signals), we address challenges for compensating synchronization offsets among anchor nodes, designing timestamps with high resolution, and developing accurate positioning methods. Second, we work on range-based positioning methods with channel information to passively locate and track WiFi targets. Targeting less efforts for deployment, we work on range-based methods, which require much less calibration efforts than fingerprinting. By designing some novel enhanced methods for both ranging and positioning (including trilateration for stationary targets and particle filter for mobile targets), we are able to locate WiFi targets with high accuracy solely relying on radio signals and our proposed enhanced particle filter significantly outperforms the other commonly used range-based positioning algorithms, e.g., a traditional particle filter, extended Kalman filter and trilateration algorithms. In addition to using radio signals for passive positioning, we propose a second enhanced particle filter for active positioning to fuse inertial sensor and channel information to track indoor targets, which achieves higher tracking accuracy than tracking methods solely relying on either radio signals or inertial sensors.