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.

Computer-aided diagnosis of carotid atherosclerosis based on ultrasound image statistics, laws' texture and neural networks

Quantitative characterisation of carotid atherosclerosis and classification into symptomatic or asymptomatic is crucial in planning optimal treatment of atheromatous plaque. The computer-aided diagnosis (CAD) system described in this paper can analyse ultrasound (US) images of carotid artery and classify them into symptomatic or asymptomatic based on their echogenicity characteristics. The CAD system consists of three modules: a) the feature extraction module, where first-order statistical (FOS) features and Laws' texture energy can be estimated, b) the dimensionality reduction module, where the number of features can be reduced using analysis of variance (ANOVA), and c) the classifier module consisting of a neural network (NN) trained by a novel hybrid method based on genetic algorithms (GAs) along with the back propagation algorithm. The hybrid method is able to select the most robust features, to adjust automatically the NN architecture and to optimise the classification performance. The performance is measured by the accuracy, sensitivity, specificity and the area under the receiver-operating characteristic (ROC) curve. The CAD design and development is based on images from 54 symptomatic and 54 asymptomatic plaques. This study demonstrates the ability of a CAD system based on US image analysis and a hybrid trained NN to identify atheromatous plaques at high risk of stroke.

Calibrating Wireless Sensor Network Simulation Models with Real-World Experiments

This paper studies the energy-efficiency and service characteristics of a recently developed energy-efficient MAC protocol for wireless sensor networks in simulation and on a real sensor hardware testbed. This opportunity is seized to illustrate how simulation models can be verified by cross-comparing simulation results with real-world experiment results. The paper demonstrates that by careful calibration of simulation model parameters, the inevitable gap between simulation models and real-world conditions can be reduced. It concludes with guidelines for a methodology for model calibration and validation of sensor network simulation models.

Chinese Internet language: A sociolinguistic analysis of adaptations of the Chinese writing system

This paper examines the adaptations of the writing system in Internet language in mainland China from a sociolinguistic perspective. A comparison is also made of the adaptations in mainland China with those that Su (2003) found in Taiwan. In Computer-Mediated Communication (CMC), writing systems are often adapted to compensate for their inherent inadequacies (such as difficulty in input). Su (2003) investigates the creative uses of the writing system on the electronic bulletin boards (BBS) of two college student organizations in Taipei, Taiwan, and identifies four popular and creative uses of the Chinese writing system: stylized English, stylized Taiwanese-accented Mandarin, stylized Taiwanese, and the recycling of a transliteration alphabet used in elementary education. According to Coupland (2001; cited in Su 2003), stylization is “the knowing deployment of culturally familiar styles and identities that are marked as deviating from those predictably associated with the current speaking context”. Within this framework and drawing on the data in previous publications on Internet language and online sources, this study identifies five types of adaptations in mainland China’s Internet language: stylized Mandarin (e.g., 漂漂 piāopiāo for 漂亮 ‘beautiful’), stylized dialect-accented Mandarin (e.g., 灰常 huīcháng for 非常 ‘very much’), stylized English (e.g., 伊妹儿 yīmèier for ‘email’), stylized initials (e.g., bt 变态 biàntài for ‘abnormal’; pk, short form for ‘player kill’), and stylized numbers (e.g., 9494 jiùshi jiùshi 就是就是 ‘that is it’). The Internet community is composed of highly mobile individuals and thus forms a weak-tie social network. According to Milroy and Milroy (1992), a social network with weak ties is often where language innovation takes place. Adaptations of the Chinese writing system in Internet language provide interesting evidence for the innovations within a weak-tie social network. Our comparison of adaptations in mainland China and Taiwan shows that, in maximizing the effectiveness and functionality of their communication, participants of Internet communication are confronted with different language resources and situations, including differences in Romanization systems, English proficiency level, and attitudes towards English usage. As argued by Milroy and Milroy (1992), a weak-tie social network model can bridge the social class and social network. In the Internet community, the degree of diversity of the stylized linguistic varieties indexes the virtual and/or social status of its participants: the more diversified one’s Internet language is, the higher is his/her virtual and/or social status.

Opportunistic Content-Centric Data Transmission During Short Network Contacts

In this paper, we investigate content-centric data transmission in the context of short opportunistic contacts and base our work on an existing content-centric networking architecture. In case of short interconnection times, file transfers may not be completed and the received information is discarded. Caches in content-centric networks are used for short-term storage and do not guarantee persistence. We implemented a mechanism to extend caching on persistent storage enabling the completion of disrupted content transfers. The mechanisms have been implemented in the CCNx framework and have been evaluated on wireless mesh nodes. Our evaluations using multicast and unicast communication show that the implementation can support content transfers in opportunistic environments without significant processing and storing overhead.

Improving Management of Distributed Services Using Correlations and Predictions in SLA-Driven Cloud Computing Systems

Recent advancements in cloud computing have enabled the proliferation of distributed applications, which require management and control of multiple services. However, without an efficient mechanism for scaling services in response to changing environmental conditions and number of users, application performance might suffer, leading to Service Level Agreement (SLA) violations and inefficient use of hardware resources. We introduce a system for controlling the complexity of scaling applications composed of multiple services using mechanisms based on fulfillment of SLAs. We present how service monitoring information can be used in conjunction with service level objectives, predictions, and correlations between performance indicators for optimizing the allocation of services belonging to distributed applications. We validate our models using experiments and simulations involving a distributed enterprise information system. We show how discovering correlations between application performance indicators can be used as a basis for creating refined service level objectives, which can then be used for scaling the application and improving the overall application's performance under similar conditions.

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.

Demo Abstract: Disseminating WMSN Data by Using Social Network and Web

For smart cities applications, a key requirement is to disseminate data collected from both scalar and multimedia wireless sensor networks to thousands of end-users. Furthermore, the information must be delivered to non-specialist users in a simple, intuitive and transparent manner. In this context, we present Sensor4Cities, a user-friendly tool that enables data dissemination to large audiences, by using using social networks, or/and web pages. The user can request and receive monitored information by using social networks, e.g., Twitter and Facebook, due to their popularity, user-friendly interfaces and easy dissemination. Additionally, the user can collect or share information from smart cities services, by using web pages, which also include a mobile version for smartphones. Finally, the tool could be configured to periodically monitor the environmental conditions, specific behaviors or abnormal events, and notify users in an asynchronous manner. Sensor4Cities improves the data delivery for individuals or groups of users of smart cities applications and encourages the development of new user-friendly services.

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.

3G network traffic sources measurement and analysis

In this paper, we show statistical analyses of several types of traffic sources in a 3G network, namely voice, video and data sources. For each traffic source type, measurements were collected in order to, on the one hand, gain better understanding of the statistical characteristics of the sources and, on the other hand, enable forecasting traffic behaviour in the network. The latter can be used to estimate service times and quality of service parameters. The probability density function, mean, variance, mean square deviation, skewness and kurtosis of the interarrival times are estimated by Wolfram Mathematica and Crystal Ball statistical tools. Based on evaluation of packet interarrival times, we show how the gamma distribution can be used in network simulations and in evaluation of available capacity in opportunistic systems. As a result, from our analyses, shape and scale parameters of gamma distribution are generated. Data can be applied also in dynamic network configuration in order to avoid potential network congestions or overflows. Copyright © 2013 John Wiley & Sons, Ltd.