this work focuses on learning a double-sparse dictionary directly from specific data. the proposed method combines wavelet transform with sparse principal component analysis (SPCA), namely wavelet sparse PCA (WSPCA). ...
详细信息
ISBN:
(纸本)9789897580765
this work focuses on learning a double-sparse dictionary directly from specific data. the proposed method combines wavelet transform with sparse principal component analysis (SPCA), namely wavelet sparse PCA (WSPCA). the double-sparsity of the learned dictionary is achieved by obtaining both sparse signal components and sparse signal loadings. this work also examines the application of the proposed method to epileptic EEG signal classification problem. the nearly perfect classification accuracy (i.e., 99.7%) is obtained for a set of 8-hour long EEGs and the results are compared to other PCA-based sparse methods. Our experiments illustrate that the WSPCA approach lowers data variability of the extacted features, and it outperforms both sparse PCA and wavelet PCA methods in classifying the EEG signals that we consider.
Auditory researchers have developed various non-speech cues in designing auditory user interfaces. A preliminary study of "lyricons" (lyrics + earcons [1]) has provided a novel approach to devising auditory ...
详细信息
there is increasing interest in Big Data analytics in health care. Behavioral health analytics is a care management technology that aims to improve the quality of care and reduce health care costs based capture and an...
详细信息
ISBN:
(数字)9783319191560
ISBN:
(纸本)9783319191560;9783319191553
there is increasing interest in Big Data analytics in health care. Behavioral health analytics is a care management technology that aims to improve the quality of care and reduce health care costs based capture and analysis of data on patient's behavioral patterns. Big Data analytics of behavioral health data offers the potential of more precise and personalized treatment as well as monitor population-wide events such as epidemics. Mobile phones are powerful social sensors that are usually physically close to users and leave digital traces of users' behaviors and movement patterns. New Apps (application or piece of software) are emerging that passively collect and analyze mobile phone data of at-risk patients such as their location, calling and texting records and app usage, and can find deviations in a user's daily patterns to detect that something is wrong before an event occurs. Data mining and machinelearning techniques are adopted to analyze the "automated diaries" created by the smart phone and monitor the well-being of people. the App first learns a patients daily behavioral patterns using machinelearning techniques. Once trained, the App detects deviations and alerts carers based on predictive models. this paper describes the techniques used and algorithms for reality mining and predictive analysis used in eHealth Apps.
the proceedings contain 18 papers. the special focus in this conference is on theory and Methods. the topics include: Density difference detection withapplication to exploratory visualization;identifying and mitigati...
ISBN:
(纸本)9783319276762
the proceedings contain 18 papers. the special focus in this conference is on theory and Methods. the topics include: Density difference detection withapplication to exploratory visualization;identifying and mitigating labelling errors in active learning;a holistic classification optimization framework with feature selection, preprocessing, manifold learning and classifiers;detection of abrupt changes in spatial relationships in video sequences;diffusion-based similarity for image analysis;automatic detection and recognition of symbols and text on the road surface;using BLSTM for spotting regular expressions in handwritten documents;a similarity-based color descriptor for face detection;pose estimation and movement detection for mobility assessment of elderly people in an ambient assisted living application;a non-rigid face tracking method for wide rotation using synthetic data;3-D face recognition using geodesic-map representation and statistical shape modelling;learning discriminative mid-level patches for fast scene classification;modification of polyp size and shape from two endoscope images using RBF neural network;detecting and dismantling composite visualizations in the scientific literature;tensor deep stacking networks and kernel deep convex networks for annotating natural scene images and multi-object segmentation for assisted image reconstruction.
Side-channel analysis (SCA) is a serious threat to embedded cryptography. Any SCA has two important components: leakage modeling and distinguisher. Although distinguisher has received much research efforts, leakage mo...
详细信息
the proceedings contain 148 papers. the special focus in this conference is on Algorithm Design and Data Processing. the topics include: A spatiotemporal cluster method for trajectory data;use case points method of so...
ISBN:
(纸本)9783319111032
the proceedings contain 148 papers. the special focus in this conference is on Algorithm Design and Data Processing. the topics include: A spatiotemporal cluster method for trajectory data;use case points method of software size measurement based on fuzzy inference;ATPG algorithm for crosstalk delay faults of high-speed interconnection circuits;application of a fuzzy-PID control method to synchronized control of a multistepping motor;the improved bayesian algorithm to spam filtering;evolution of community structure in complex networks;construction of a thermal power enterprise environmental performance evaluation model;a mobile localization algorithm based on SPSO algorithm;a fast and accurate algorithm of subspace spectrum peak search based on bisection method;a CRF-based method for DDoS attack detection;advanced SOM algorithm based on extension distance and its application;a trilateral centroid localization and modification algorithm for wireless sensor network;simulation study on trajectory tracking in manipulator based on the iterative learning control algorithm;an improved gaussian mixture model and its application;GPU acceleration for the gaussian elimination in magnetotelluric occam inversion algorithm;artificial neural networks in biomedicine applications;SOC prediction method of a new lithium battery based on GA-BP neural network;implementation and performance evaluation of the fully enclosed region upper confidence bound applied to trees algorithm;a new linear feature item weighting algorithm;trust value of the role access control model based on trust and universal approximation by generalized mellin approximate identity neural networks.
Open-Source Intelligence (OSINT) is intelligence collected and inferred from publicly available and overt sources of information. Open-Source social media intelligence is a sub-field within OSINT with a focus on extra...
详细信息
ISBN:
(纸本)9783319270579;9783319270562
Open-Source Intelligence (OSINT) is intelligence collected and inferred from publicly available and overt sources of information. Open-Source social media intelligence is a sub-field within OSINT with a focus on extracting insights from publicly available data in Web 2.0 platforms like Twitter (micro-blogging website), YouTube (video-sharing website) and Facebook (social-networking website). In this paper, we present an overview of Intelligence and Security Informatics (ISI) applications in the domain of open-source social media intelligence. We present technical challenges and introduce basic machinelearning based framework, tools and techniques within the context of open-source social media intelligence using two case-studies. the focus of the paper is on mining free-form textual content present in social media websites. In particular we describe two important application: online radicalization and civil unrest. In addition to covering basic concepts and applications, we discuss open research problem, important papers, publication venues, research results and future directions.
this is the first volume of the two-volume set (CCIS 528 and CCIS 529) that contains extended abstracts of the posters presented during the 17thinternationalconference on Human-computer Interaction, HCII 2015, held ...
ISBN:
(数字)9783319213804
ISBN:
(纸本)9783319213798
this is the first volume of the two-volume set (CCIS 528 and CCIS 529) that contains extended abstracts of the posters presented during the 17thinternationalconference on Human-computer Interaction, HCII 2015, held in Heraklion, Crete, Greece in August *** total of 1462 papers and 246 posters presented at the HCII 2015 conferences was carefully reviewed and selected from 4843 submissions. these papers address the latest research and development efforts and highlight the human aspects of design and use of computing systems. the papers thoroughly cover the entire field of human-computer interaction, addressing major advances in knowledge and effective use of computers in a variety of application areas. the papers included in this volume are organized in the following topical sections: design and evaluation methods, techniques and tools; cognitive and psychological issues in HCI; virtual, augmented and mixed reality; cross-cultural design; design for aging; children in HCI; product design; gesture, gaze and motion detection, modelling and recognition; reasoning, optimisation and machinelearning for HCI; information processing and extraction for HCI; image and video processing for HCI; brain and physiological parameters monitoring; dialogue systems.
the proceedings contain 33 papers. the special focus in this conference is on Ontology and Reasoning, Linked Data, learning and Discovery, RDF and SPARQL and Ontological Engineering. the topics include: Revisiting def...
ISBN:
(纸本)9783319156149
the proceedings contain 33 papers. the special focus in this conference is on Ontology and Reasoning, Linked Data, learning and Discovery, RDF and SPARQL and Ontological Engineering. the topics include: Revisiting default description logics - and their role in aligning ontologies;on desirable properties of the structural subsumption-based similarity measure;a graph-based approach to ontology debugging in DL Lite;reasoning for ALCQ extended with a flexible meta-modelling hierarchy;ontology based inferences engine for veterinary diagnosis;a roadmap for navigating the life sciences linked open data cloud;link prediction in linked data of interspecies interactions using hybrid recommendation approach;linked data exploitation for tourist mobile apps in rural areas;publishing Danish agricultural government data as semantic web data;a lightweight treatment of inexact dates;a multi-strategy learning approach to competitor identification;mining type information from Chinese online encyclopedias;a grouping algorithm for RDF change detection on mapreduce;graph pattern based RDF Data compression;optimizing SPARQL query processing on dynamic and static data based on query time/freshness requirements using materialization;RDF a parser for hybrid resources;ontology construction and schema merging using an application-independent ontology for humanitarian aid in disaster management;development of the belief culture ontology and its application: case study of the greater Mekong subregion and representations of psychological functions of peer support services for diabetic patients.
As citizens of countries and employees become comfortable using mobile technology, there is an opportunity for the workplace to deliver training using mobile technology. Using mobile learning allows employees to learn...
详细信息
暂无评论