The proceedings contain 49 papers. The topics discussed include: citizen observatories of water: social innovation via eparticipation;environmental assessment of emedia solutions: challenges experienced in case studie...
ISBN:
(纸本)9789462520226
The proceedings contain 49 papers. The topics discussed include: citizen observatories of water: social innovation via eparticipation;environmental assessment of emedia solutions: challenges experienced in case studies of alma media newspapers;power law of engagement: transferring disengaged householders into retrofitting energy savers;web for sustainability: tackling environmental complexity with scale;a practical model for evaluating the energy efficiency of software applications;a review of top-down models of internet network energy intensity;addressing the obsolescence of end-user devices: approaches from the field of sustainable HCI;agent-based analysis of annual energy usages for domestic heating based on a heat pump;bigdata GIS analytics towards efficient waste management in Stockholm;blinded by data: the risks of the implicit focus on data in ICT for sustainability;and characterization of the energy consumption of websites: impact of website implementation on resource consumption.
The proceedings contain 80 papers. The topics discussed include: framework for improving the performance of verification algorithms with a low false positive rate requirement and limited training data;multi-modal biom...
ISBN:
(纸本)9781479935840
The proceedings contain 80 papers. The topics discussed include: framework for improving the performance of verification algorithms with a low false positive rate requirement and limited training data;multi-modal biometrics for mobile authentication;LPIDB v1.0 - latent palmprint identification database;audio-visual gender recognition in uncontrolled environment using variability modeling techniques;cross-view gait recognition using view-dependent discriminative analysis;a coarse-to-fine approach to robust 3D facial landmarking via curvature analysis and active normal model;age invariant face recognition based on texture embedded discriminative graph model;impact of sensor ageing on iris recognition;non-negative sparse coding based scalable access control using fingertip ECG;aiding face recognition with social context association rule based re-ranking;and iris pattern obfuscation in digital images.
Water covers more than 70 % of the entire planet, contains much of its natural resources. With the increasing use of underwater sensors for the exploitation and monitoring of vast underwater resources, underwater wire...
详细信息
The proceedings contain 72 papers. The topics discussed include: agent-based methods for simulation of epidemics with a low number of infected persons;cellular automata model of urbanization in Camiguin, Philippines;t...
ISBN:
(纸本)9783642550317
The proceedings contain 72 papers. The topics discussed include: agent-based methods for simulation of epidemics with a low number of infected persons;cellular automata model of urbanization in Camiguin, Philippines;transformation of digital ecosystems: the case of digital payments;do personality traits work as moderator on the intention to purchase mobile applications work? - a pilot study;empirical and computational issues of microclimate simulation;toward a data-driven performance-guided urban decision-support environment;knowledge management: organization culture in healthcare Indonesia;semantic versioning of in-process scientific document;acceptance and use of information system: e-learning based on cloud computing in Vietnam;requirements identification for migrating egovernment applications to the cloud;a robust visual object tracking approach on a mobile device;and hybridization of Haar wavelet decomposition and computational intelligent algorithms for the estimation of climate change behavior.
With the increase of data dimension, many low dimensional mining algorithms cannot get satisfactory *** the increase of data dimension, it can produce a large amount of redundant information;this information will grea...
详细信息
With the increase of data dimension, many low dimensional mining algorithms cannot get satisfactory *** the increase of data dimension, it can produce a large amount of redundant information;this information will greatly reduce the efficiency of mining, increasing the complexity of the mining *** selection is an efficient way to solve the problem;it can remove a lot of irrelevant and redundant *** this paper, on the basis of Lars algorithm applying differential evolution thought to the extraction of feature subset, puts forward a new method of feature selection, DE- Lars *** prove that DE- Lars algorithm enhances the precision of reducing dimension of space, effectively solve the problem of "Curse of Dimensionality ".
Remote sensing technology has been widely used for monitoring water quality parameters such as suspended solids (turbidity), Secchi Disk, chlorophyll, and phosphorus. Suspended matter plays an important role in water ...
详细信息
ISBN:
(纸本)9781628412765
Remote sensing technology has been widely used for monitoring water quality parameters such as suspended solids (turbidity), Secchi Disk, chlorophyll, and phosphorus. Suspended matter plays an important role in water quality management of several inland-(such as lakes and reservoirs) and coastal-water bodies and can be used to estimate the Trophic State Index of different water bodies. However synoptic information on water quality parameters at a systematic basis is difficult to be obtained from routine in situ monitoring programs since suspended matter, phosphorus, and chlorophyll are spatially inhomogeneous parameters. To meet this need, an integrated use of Landsat satellite images, in situ data and water quality models can be used. Several algorithms were developed at a previous stage using water quality data collected during the in situ sampling campaigns taken place in 2010 and2011 over Asprokremmos Reservoir (Paphos District) for the assessment of turbidity, Secchi Disk, and Trophic State Index fluctuations using spectroradiometric data. Remotely sensed data were atmospherically corrected and water quality models for the estimation of both the turbidity-and Secchi Disk-concentrations were further calibrated using in situ data for the case of Asprokremmos Reservoir and several coastal over Cyprus coastline (Limassol and Paphos District Areas). This methodology can be used as a supporting monitoring tool for water management authorities "gaining" additional information regarding the spatial and temporal alterations of the turbidity-and Secchi Disk-concentrations and the Trophic State Index values over several Case II water bodies.
Lightweight speaker-dependent (SD) automatic speech recognition (ASR) is a promising solution for the problems of possibility of disclosing personal privacy and difficulty of obtaining training material for many seldo...
详细信息
ISBN:
(纸本)9783038350019
Lightweight speaker-dependent (SD) automatic speech recognition (ASR) is a promising solution for the problems of possibility of disclosing personal privacy and difficulty of obtaining training material for many seldom used English words and (often non-English) names. Dynamic time warping (DTW) algorithm is the state-of-the-art algorithm for small foot-print SD ASR applications, which have limited storage space and small vocabulary. In our previous work, we have successfully developed two fast and accurate DTW variations for clean speech data. However, speech recognition in adverse conditions is still a big challenge. In order to improve recognition accuracy in noisy and bad recording conditions, such as too high or low recording volume, we introduce a novel weighted DTW method. This method defines a feature index for each time frame of training data, and then applies it to the core DTW process to tune the final alignment score. With extensive experiments on one representative SD dataset of three speakers' recordings, our method achieves better accuracy than DTW, where 0.5% relative reduction of error rate (RRER) on clean speech data and 7.5% RRER on noisy and bad recording speech data. To the best of our knowledge, our new weighted DTW is the first weighted DTW method specially designed for speech data in noisy and bad recording conditions.
Summary form only given, as follows. data-intensive computing is considered as the fourth paradigm in science. The term “data-intensive computing” did not establish in other communities although they are also confro...
详细信息
ISBN:
(纸本)9781479976010
Summary form only given, as follows. data-intensive computing is considered as the fourth paradigm in science. The term “data-intensive computing” did not establish in other communities although they are also confronted with enormous amounts of data. Nowadays, bigdata refers to data sets that are too large, too complex, too distributed for analysing them by conventional methods. One strategy for handling bigdata is known as “software to the data” which is applicable when it is more efficient to bring the analysis tools to the data than, vice versa, to apply traditional methods where, for example, all data are collected at some place and analysed there. The data production rate is expected to increase exponentially for the time being. This is particularly true in science where the resolution power of experiments is steadily improving. Sooner or later it has to be taken into account that it is not feasible to store all data anymore. A new era is on the horizon: Huge data. Huge data have to be pre-analysed during the data-taking period in order to extract a sufficiently small subset of data that is worth to be analysed in more detail later on. An effective and efficient preselection in real-time or near-realtime is most critical for successfully handling Huge data. This is made more challenging if during the pre-analysis that has to be done in parallel, intermediate results have to be exchanged. The talk considers selected challenges of Huge data. Some examples from different scientific communities are presented. The complete presentation was not made available for publication as part of the conference proceedings.
暂无评论