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 computer-aided diagnostic system to characterize CT focal liver lesions: design and optimization of a neural network classifier

In this paper, a computer-aided diagnostic (CAD) system for the classification of hepatic lesions from computed tomography (CT) images is presented. Regions of interest (ROIs) taken from nonenhanced CT images of normal liver, hepatic cysts, hemangiomas, and hepatocellular carcinomas have been used as input to the system. The proposed system consists of two modules: the feature extraction and the classification modules. The feature extraction module calculates the average gray level and 48 texture characteristics, which are derived from the spatial gray-level co-occurrence matrices, obtained from the ROIs. The classifier module consists of three sequentially placed feed-forward neural networks (NNs). The first NN classifies into normal or pathological liver regions. The pathological liver regions are characterized by the second NN as cyst or "other disease." The third NN classifies "other disease" into hemangioma or hepatocellular carcinoma. Three feature selection techniques have been applied to each individual NN: the sequential forward selection, the sequential floating forward selection, and a genetic algorithm for feature selection. The comparative study of the above dimensionality reduction methods shows that genetic algorithms result in lower dimension feature vectors and improved classification performance.

Performance Analysis and Comparison between Legacy-PSM and U-APSD

This paper evaluates the performance of the most popular power saving mechanisms defined in the IEEE 802.11 standard, namely the Power Save Mode (Legacy-PSM) and the Unscheduled Automatic Power Save Delivery (U-APSD). The assessment comprises a detailed study concerning energy efficiency and capability to guarantee the required Quality of Service (QoS) for a certain application. The results, obtained in the OMNeT++ simulator, showed that U-APSD is more energy efficient than Legacy-PSM without compromising the end-to- end delay. Both U-APSD and Legacy-PSM revealed capability to guarantee the application QoS requirements in all the studied scenarios. However, unlike U-APSD, when Legacy-PSM is used in the presence of QoS demanding applications, all the stations connected to the network through the same access point will consume noticeable additional energy.

Real-World Energy Measurements of a Wireless Mesh Network

Over the past several years the topics of energy consumption and energy harvesting have gained significant importance as a means for improved operation of wireless sensor and mesh networks. Energy-awareness of operation is especially relevant for application scenarios from the domain of environmental monitoring in hard to access areas. In this work we reflect upon our experiences with a real-world deployment of a wireless mesh network. In particular, a comprehensive study on energy measurements collected over several weeks during the summer and the winter period in a network deployment in the Swiss Alps is presented. Energy performance is monitored and analysed for three system components, namely, mesh node, battery and solar panel module. Our findings cover a number of aspects of energy consumption, including the amount of load consumed by a mesh node, the amount of load harvested by a solar panel module, and the dependencies between these two. With our work we aim to shed some light on energy-aware network operation and to help both users and developers in the planning and deployment of a new wireless (mesh) network for environmental research.

Approximate decoding approaches for network coded correlated data

This paper considers a framework where data from correlated sources are transmitted with the help of network coding in ad hoc network topologies. The correlated data are encoded independently at sensors and network coding is employed in the intermediate nodes in order to improve the data delivery performance. In such settings, we focus on the problem of reconstructing the sources at decoder when perfect decoding is not possible due to losses or bandwidth variations. We show that the source data similarity can be used at decoder to permit decoding based on a novel and simple approximate decoding scheme. We analyze the influence of the network coding parameters and in particular the size of finite coding fields on the decoding performance. We further determine the optimal field size that maximizes the expected decoding performance as a trade-off between information loss incurred by limiting the resolution of the source data and the error probability in the reconstructed data. Moreover, we show that the performance of the approximate decoding improves when the accuracy of the source model increases even with simple approximate decoding techniques. We provide illustrative examples showing how the proposed algorithm can be deployed in sensor networks and distributed imaging applications.

The Swiss Neonatal Quality Cycle, a monitor for clinical performance and tool for quality improvement

BACKGROUND We describe the setup of a neonatal quality improvement tool and list which peer-reviewed requirements it fulfils and which it does not. We report on the so-far observed effects, how the units can identify quality improvement potential, and how they can measure the effect of changes made to improve quality. METHODS Application of a prospective longitudinal national cohort data collection that uses algorithms to ensure high data quality (i.e. checks for completeness, plausibility and reliability), and to perform data imaging (Plsek's p-charts and standardized mortality or morbidity ratio SMR charts). The collected data allows monitoring a study collective of very low birth-weight infants born from 2009 to 2011 by applying a quality cycle following the steps 'guideline - perform - falsify - reform'. RESULTS 2025 VLBW live-births from 2009 to 2011 representing 96.1% of all VLBW live-births in Switzerland display a similar mortality rate but better morbidity rates when compared to other networks. Data quality in general is high but subject to improvement in some units. Seven measurements display quality improvement potential in individual units. The methods used fulfil several international recommendations. CONCLUSIONS The Quality Cycle of the Swiss Neonatal Network is a helpful instrument to monitor and gradually help improve the quality of care in a region with high quality standards and low statistical discrimination capacity.

Visuospatial working memory in very preterm and term born children - Impact of age and performance

Working memory is crucial for meeting the challenges of daily life and performing academic tasks, such as reading or arithmetic. Very preterm born children are at risk of low working memory capacity. The aim of this study was to examine the visuospatial working memory network of school-aged preterm children and to determine the effect of age and performance on the neural working memory network. Working memory was assessed in 41 very preterm born children and 36 term born controls (aged 7–12 years) using functional magnetic resonance imaging (fMRI) and neuropsychological assessment. While preterm children and controls showed equal working memory performance, preterm children showed less involvement of the right middle frontal gyrus, but higher fMRI activation in superior frontal regions than controls. The younger and low-performing preterm children presented an atypical working memory network whereas the older high-performing preterm children recruited a working memory network similar to the controls. Results suggest that younger and low-performing preterm children show signs of less neural efficiency in frontal brain areas. With increasing age and performance, compensational mechanisms seem to occur, so that in preterm children, the typical visuospatial working memory network is established by the age of 12 years.

Distributed Rate Allocation in Inter-Session Network Coding

In this work, we propose a distributed rate allocation algorithm that minimizes the average decoding delay for multimedia clients in inter-session network coding systems. We consider a scenario where the users are organized in a mesh network and each user requests the content of one of the available sources. We propose a novel distributed algorithm where network users determine the coding operations and the packet rates to be requested from the parent nodes, such that the decoding delay is minimized for all clients. A rate allocation problem is solved by every user, which seeks the rates that minimize the average decoding delay for its children and for itself. Since this optimization problem is a priori non-convex, we introduce the concept of equivalent packet flows, which permits to estimate the expected number of packets that every user needs to collect for decoding. We then decompose our original rate allocation problem into a set of convex subproblems, which are eventually combined to obtain an effective approximate solution to the delay minimization problem. The results demonstrate that the proposed scheme eliminates the bottlenecks and reduces the decoding delay experienced by users with limited bandwidth resources. We validate the performance of our distributed rate allocation algorithm in different video streaming scenarios using the NS-3 network simulator. We show that our system is able to take benefit of inter-session network coding for simultaneous delivery of video sessions in networks with path diversity.

Functional brain network efficiency predicts intelligence

The neuronal causes of individual differences in mental abilities such as intelligence are complex and profoundly important. Understanding these abilities has the potential to facilitate their enhancement. The purpose of this study was to identify the functional brain network characteristics and their relation to psychometric intelligence. In particular, we examined whether the functional network exhibits efficient small-world network attributes (high clustering and short path length) and whether these small-world network parameters are associated with intellectual performance. High-density resting state electroencephalography (EEG) was recorded in 74 healthy subjects to analyze graph-theoretical functional network characteristics at an intracortical level. Ravens advanced progressive matrices were used to assess intelligence. We found that the clustering coefficient and path length of the functional network are strongly related to intelligence. Thus, the more intelligent the subjects are the more the functional brain network resembles a small-world network. We further identified the parietal cortex as a main hub of this resting state network as indicated by increased degree centrality that is associated with higher intelligence. Taken together, this is the first study that substantiates the neural efficiency hypothesis as well as the Parieto-Frontal Integration Theory (P-FIT) of intelligence in the context of functional brain network characteristics. These theories are currently the most established intelligence theories in neuroscience. Our findings revealed robust evidence of an efficiently organized resting state functional brain network for highly productive cognitions.

Validation and reclassification of MGAP and GAP in hospital settings using data from the Trauma Audit and Research Network.

BACKGROUND Recently, two simple clinical scores were published to predict survival in trauma patients. Both scores may successfully guide major trauma triage, but neither has been independently validated in a hospital setting. METHODS This is a cohort study with 30-day mortality as the primary outcome to validate two new trauma scores-Mechanism, Glasgow Coma Scale (GCS), Age, and Pressure (MGAP) score and GCS, Age and Pressure (GAP) score-using data from the UK Trauma Audit and Research Network. First, an assessment of discrimination, using the area under the receiver operating characteristic (ROC) curve, and calibration, comparing mortality rates with those originally published, were performed. Second, we calculated sensitivity, specificity, predictive values, and likelihood ratios for prognostic score performance. Third, we propose new cutoffs for the risk categories. RESULTS A total of 79,807 adult (≥16 years) major trauma patients (2000-2010) were included; 5,474 (6.9%) died. Mean (SD) age was 51.5 (22.4) years, median GCS score was 15 (interquartile range, 15-15), and median Injury Severity Score (ISS) was 9 (interquartile range, 9-16). More than 50% of the patients had a low-risk GAP or MGAP score (1% mortality). With regard to discrimination, areas under the ROC curve were 87.2% for GAP score (95% confidence interval, 86.7-87.7) and 86.8% for MGAP score (95% confidence interval, 86.2-87.3). With regard to calibration, 2,390 (3.3%), 1,900 (28.5%), and 1,184 (72.2%) patients died in the low, medium, and high GAP risk categories, respectively. In the low- and medium-risk groups, these were almost double the previously published rates. For MGAP, 1,861 (2.8%), 1,455 (15.2%), and 2,158 (58.6%) patients died in the low-, medium-, and high-risk categories, consonant with results originally published. Reclassifying score point cutoffs improved likelihood ratios, sensitivity and specificity, as well as areas under the ROC curve. CONCLUSION We found both scores to be valid triage tools to stratify emergency department patients, according to their risk of death. MGAP calibrated better, but GAP slightly improved discrimination. The newly proposed cutoffs better differentiate risk classification and may therefore facilitate hospital resource allocation. LEVEL OF EVIDENCE Prognostic study, level II.

A Tutorial of the Mobile Multimedia Wireless Sensor Network (M3WSN) OMNeT++ Framework

In this work, we will give a detailed tutorial instruction about how to use the Mobile Multi-Media Wireless Sensor Networks (M3WSN) simulation framework. The M3WSN framework has been published as a scientific paper in the 6th International Workshop on OMNeT++ (2013) [1]. M3WSN framework enables the multimedia transmission of real video se- quence. Therefore, a set of multimedia algorithms, protocols, and services can be evaluated by using QoE metrics. Moreover, key video-related information, such as frame types, GoP length and intra-frame dependency can be used for creating new assessment and optimization solutions. To support mobility, M3WSN utilizes different mobility traces to enable the understanding of how the network behaves under mobile situations. This tutorial will cover how to install and configure the M3WSN framework, setting and running the experiments, creating mobility and video traces, and how to evaluate the performance of different protocols. The tutorial will be given in an environment of Ubuntu 12.04 LTS and OMNeT++ 4.2.

Content-Aware Delivery of Scalable Video in Network Coding Enabled Named Data Networks

In this work, we propose a novel network coding enabled NDN architecture for the delivery of scalable video. Our scheme utilizes network coding in order to address the problem that arises in the original NDN protocol, where optimal use of the bandwidth and caching resources necessitates the coordination of the forwarding decisions. To optimize the performance of the proposed network coding based NDN protocol and render it appropriate for transmission of scalable video, we devise a novel rate allocation algorithm that decides on the optimal rates of Interest messages sent by clients and intermediate nodes. This algorithm guarantees that the achieved flow of Data objects will maximize the average quality of the video delivered to the client population. To support the handling of Interest messages and Data objects when intermediate nodes perform network coding, we modify the standard NDN protocol and introduce the use of Bloom filters, which store efficiently additional information about the Interest messages and Data objects. The proposed architecture is evaluated for transmission of scalable video over PlanetLab topologies. The evaluation shows that the proposed scheme performs very close to the optimal performance

NetCodCCN: a Network Coding approach for Content-Centric Networks

Content-Centric Networking (CCN) naturally supports multi-path communication, as it allows the simultaneous use of multiple interfaces (e.g. LTE and WiFi). When multiple sources and multiple clients are considered, the optimal set of distribution trees should be determined in order to optimally use all the available interfaces. This is not a trivial task, as it is a computationally intense procedure that should be done centrally. The need for central coordination can be removed by employing network coding, which also offers improved resiliency to errors and large throughput gains. In this paper, we propose NetCodCCN, a protocol for integrating network coding in CCN. In comparison to previous works proposing to enable network coding in CCN, NetCodCCN permit Interest aggregation and Interest pipelining, which reduce the data retrieval times. The experimental evaluation shows that the proposed protocol leads to significant improvements in terms of content retrieval delay compared to the original CCN. Our results demonstrate that the use of network coding adds robustness to losses and permits to exploit more efficiently the available network resources. The performance gains are verified for content retrieval in various network scenarios.

Small Cell Carcinoma of the Urinary Bladder: A Retrospective, Multicenter Rare Cancer Network Study of 107 Patients

PURPOSE Small cell carcinomas of the bladder (SCCB) account for fewer than 1% of all urinary bladder tumors. There is no consensus regarding the optimal treatment for SCCB. METHODS AND MATERIALS Fifteen academic Rare Cancer Network medical centers contributed SCCB cases. The eligibility criteria were as follows: pure or mixed SCC; local, locoregional, and metastatic stages; and age ≥18 years. The overall survival (OS) and disease-free survival (DFS) were calculated from the date of diagnosis according to the Kaplan-Meier method. The log-rank and Wilcoxon tests were used to analyze survival as functions of clinical and therapeutic factors. RESULTS The study included 107 patients (mean [±standard deviation, SD] age, 69.6 [±10.6] years; mean follow-up time, 4.4 years) with primary bladder SCC, with 66% of these patients having pure SCC. Seventy-two percent and 12% of the patients presented with T2-4N0M0 and T2-4N1-3M0 stages, respectively, and 16% presented with synchronous metastases. The most frequent curative treatments were radical surgery and chemotherapy, sequential chemotherapy and radiation therapy, and radical surgery alone. The median (interquartile range, IQR) OS and DFS times were 12.9 months (IQR, 7-32 months) and 9 months (IQR, 5-23 months), respectively. The metastatic, T2-4N0M0, and T2-4N1-3M0 groups differed significantly (P=.001) in terms of median OS and DFS. In a multivariate analysis, impaired creatinine clearance (OS and DFS), clinical stage (OS and DFS), a Karnofsky performance status <80 (OS), and pure SCC histology (OS) were independent and significant adverse prognostic factors. In the patients with nonmetastatic disease, the type of treatment (ie radical surgery with or without adjuvant chemotherapy vs conservative treatment) did not significantly influence OS or DFS (P=.7). CONCLUSIONS The prognosis for SCCB remains poor. The finding that radical cystectomy did not influence DFS or OS in the patients with nonmetastatic disease suggests that conservative treatment is appropriate in this situation.