the two-volume set LNAI 8397 and LNAI 8398 constitutes the refereed proceedings of the 6thasianconference on Intelligent Information and Database Systems, ACIIDS 2014, held in Bangkok, thailand, in April 2014. the 1...
ISBN:
(数字)9783319054766
ISBN:
(纸本)9783319054759;9783319054766
the two-volume set LNAI 8397 and LNAI 8398 constitutes the refereed proceedings of the 6thasianconference on Intelligent Information and Database Systems, ACIIDS 2014, held in Bangkok, thailand, in April 2014. the 125 revised papers presented were carefully reviewed and selected from 300 submissions. the papers address the following topics: natural language and text processing, intelligent information retrieval, semantic Web, social networks and recommendation systems, intelligent database systems, decision support systems, computer vision techniques, and machinelearning and data mining. the papers are organized in topical sections on multiple model approach to machinelearning, MMAML 2014, computational intelligence, CI 2014, engineering knowledge and semantic systems, IWEKSS 2014, innovations in intelligent computation and applications, IICA 2014, modeling and optimization techniques in information systems, database systems and industrial systems, MOT 2014, innovation via collective intelligences and globalization in business management, ICIGBM 2014, intelligent supply chains, ISC 2014, and human motion: acquisition, processing, analysis, synthesis and visualization for massive datasets, HMMD 2014.
the two-volume set LNAI 8397 and LNAI 8398 constitutes the refereed proceedings of the 6thasianconference on Intelligent Information and Database Systems, ACIIDS 2014, held in Bangkok, thailand in April 2014. the 12...
ISBN:
(数字)9783319054582
ISBN:
(纸本)9783319054575;9783319054582
the two-volume set LNAI 8397 and LNAI 8398 constitutes the refereed proceedings of the 6thasianconference on Intelligent Information and Database Systems, ACIIDS 2014, held in Bangkok, thailand in April 2014. the 125 revised papers presented were carefully reviewed and selected from 300 submissions. Suggestion: the aim of the conference is to provide an internationally respected forum for scientific research in the technologies and applications of intelligent information and database systems. the papers are organized in topical sections on Natural Language and Text Processing, Intelligent Information Retrieval, Semantic Web, Social Networks and Recommendation Systems, Intelligent Database Systems, Decision Support Systems, Computer Vision Techniques, machinelearning and Data Mining, Multiple Model Approach to machinelearning, MMAML 2014, Computational Intelligence, CI 2014, Engineering Knowledge and Semantic Systems , IWEKSS 2014, Innovations in Intelligent Computation and Applications, IICA 2014, Modelling and Optimization Techniques in Information Systems, Database Systems and Industrial Systems, MOT 2014, Innovation via Collective Intelligences and Globalization in Business Management, ICIGBM 2014, Intelligent Supply Chains, ISC 2014, and Human Motion: Acquisition, Processing, Analysis, Synthesis and Visualization for Massive Datasets, HMMD 2014.
the proceedings contain 160 papers. the topics discussed include: movement tracking detection of break dance based on deep learning;multifactorial ant lion optimization algorithm;multi-feature fusion machine translati...
ISBN:
(纸本)9781665453110
the proceedings contain 160 papers. the topics discussed include: movement tracking detection of break dance based on deep learning;multifactorial ant lion optimization algorithm;multi-feature fusion machine translation quality evaluation based on LSTM neural network;multigranulation sequential three-way decisions in interval-valued system;multi-hop diffusion-based graph convolutional networks;multi-modal sarcasm detection with prompt-tuning;multi-objective optimization of room temperature regulation of building phase change materials based on genetic algorithm;multi-robot cooperative defense strategy in RoboCup standard platform league;multi-scale dense feature fusion based loess landslide recognition;network malicious traffic detection model based on combined neural network;a multi-task learning method integrating multi-information fusion for non-intrusive load monitoring;object tracking method combined with lightweight hybrid attention Siamese network;and optimization of inter-frame coding algorithm based on random forest.
the proceedings contain 124 papers. the topics discussed include: combination of multi-view multi-source language classifiers for cross-lingual sentiment classification;a new approach for mining top-rank-k erasable it...
ISBN:
(纸本)9783319054759
the proceedings contain 124 papers. the topics discussed include: combination of multi-view multi-source language classifiers for cross-lingual sentiment classification;a new approach for mining top-rank-k erasable itemsets;query expansion using medical subject headings terms in the biomedical documents;entity recognition in information extraction;incremental refinement of linked data: ontology-based approach;finding the cluster of actors in social network based on the topic of messages;SPARQL - compliant semantic search engine with an intuitive user interface;intelligent fuzzy control with multiple constraints for a model car system with multiplicative disturbance;the design of knowledge-based medical diagnosis system for recognition and classification of dermatoglyphic features;customer lifetime value and defection possibility prediction model using machinelearning: an application to a cloud-based software company;and the AdaBoost algorithm withthe imprecision determine the weights of the observations.
the proceedings contain 124 papers. the topics discussed include: combination of multi-view multi-source language classifiers for cross-lingual sentiment classification;a new approach for mining top-rank-k erasable it...
ISBN:
(纸本)9783319054575
the proceedings contain 124 papers. the topics discussed include: combination of multi-view multi-source language classifiers for cross-lingual sentiment classification;a new approach for mining top-rank-k erasable itemsets;query expansion using medical subject headings terms in the biomedical documents;entity recognition in information extraction;incremental refinement of linked data: ontology-based approach;finding the cluster of actors in social network based on the topic of messages;SPARQL - compliant semantic search engine with an intuitive user interface;intelligent fuzzy control with multiple constraints for a model car system with multiplicative disturbance;the design of knowledge-based medical diagnosis system for recognition and classification of dermatoglyphic features;customer lifetime value and defection possibility prediction model using machinelearning: an application to a cloud-based software company;and the AdaBoost algorithm withthe imprecision determine the weights of the observations.
the proceedings contain 35 papers. the topics discussed include: hierarchical algorithm for pattern extraction from biological sequences;discoverying compounds that activate plant immunity using machinelearning;a K-m...
ISBN:
(纸本)9781632665140
the proceedings contain 35 papers. the topics discussed include: hierarchical algorithm for pattern extraction from biological sequences;discoverying compounds that activate plant immunity using machinelearning;a K-means based approach for the design of rotamer libraries: preliminary results;semi-supervised classification of protein sequences using burrows wheeler transformation-based features;advanced statistical analysis of RNA-seq differential gene expression profiles of animal gene-environment interactions;potential relationship discovery model base on context and its application in lung cancer field;analyzing conservation patterns and its influence on identifying protein functional sites;new weighting method of protein sequences for protein classification;and predicting protein subcellular localization with reduced feature set.
the proceedings contain 54 papers. the special focus in this conference is on Future Data and Security Engineering. the topics include: Computing History-Dependent Schedules for Processes with Temporal Constraints;fin...
ISBN:
(纸本)9783030356521
the proceedings contain 54 papers. the special focus in this conference is on Future Data and Security Engineering. the topics include: Computing History-Dependent Schedules for Processes with Temporal Constraints;finding All Minimal Maximum Subsequences in Parallel;OCL2PSQL: An OCL-to-SQL Code-Generator for Model-Driven Engineering;framework for Peer-to-Peer Data Sharing over Web Browsers;efficiently Semantic-Aware Pairwise Similarity: an Applicable Use-Case;lower Bound on Network Diameter for Distributed Function Computation;a Combined Enhancing and Feature Extraction Algorithm to Improve learning Accuracy for Gene Expression Classification;age and Gender Estimation of asian Faces Using Deep Residual Network;Light-Weight Deep Convolutional Network-Based Approach for Recognizing Emotion on FPGA Platform;a New Test Suite Reduction Approach Based on Hypergraph Minimal Transversal Mining;metagenome-Based Disease Classification with Deep learning and Visualizations Based on Self-organizing Maps;On Analyzing the Trade-Off Between Over-Commitment Ratio and Quality of Service in NFV Datacenter;dynamic Data Management Strategy on Cloud Network by Fog Computing Model;openness in Fog Computing for the Internet of things;A Top-Down Scheduling for Time Efficient Data Aggregation in WSNs;a New Technique to Improve the Security of Elliptic Curve Encryption and Signature Schemes;a Visual Model for Privacy Awareness and Understanding in Online Social Networks;A Method to Enhance the Security Capability of Python IDE;studying machinelearning Techniques for Intrusion Detection Systems;enforcing Access Controls in IoT Networks;machinelearning Based Monitoring of the Pneumatic Actuators’ Behavior through Signal Processing Using Real-World Data Set;adventures in the Analysis of Access Control Policies.
the proceedings contain 22 papers. the special focus in this conference is on Intelligent Technologies for Interactive Entertainment. the topics include: Predicting shot success for table tennis using video analysis a...
ISBN:
(纸本)9783319081885
the proceedings contain 22 papers. the special focus in this conference is on Intelligent Technologies for Interactive Entertainment. the topics include: Predicting shot success for table tennis using video analysis and machinelearning;interactive assessment tools for computational thinking in high school STEM classrooms;affect and semantic interpretation of virtual drama;choreographing digital water for interactive water performance;a critical inquiry into designing creative interactive systems;perception and manipulation of game control;head pose estimation by perspective-n-point solution based on 2D markerless face tracking;towards environments that have a sense of humor;transcending barriers of disability through technology in live comedy performance;creating meaningful experiences with interaction design;RPGS as knowledge creating chronotopes;the organization and distribution of art, literature and information in the 21st century;bass impact DJ Studio - a music mixing software with gesture controls;creativity in the CPND;interactive network installation;using drones for virtual tourism and a mathematical model of game refinement.
the proceedings contain 54 papers. the special focus in this conference is on Knowledge and Systems Engineering. the topics include: Discriminative prediction of enhancers with word combinations as features;natural la...
ISBN:
(纸本)9783319116792
the proceedings contain 54 papers. the special focus in this conference is on Knowledge and Systems Engineering. the topics include: Discriminative prediction of enhancers with word combinations as features;natural language processing for social event classification;an effective NMF-based method for supervised dimension reduction;facial expression recognition using pyramid local phase quantization descriptor;toward a rule-based synthesis of Vietnamese emotional speech;finding relevant functions based on API documentation;a fast method for motif discovery in large time series database under dynamic time warping;using attribute relationships for person re-identification;on automating inference of OCL constraints from counterexamples and examples;improving text-based image search with textual and visual features combination;binary hybrid particle swarm optimization with wavelet mutation;collaborative filtering by co-training method;neural networks with hidden Markov models in skeleton-based gesture recognition;semantic regions recognition in UAV images sequence;fast optimization of the pattern shapes in board games with simulated annealing;modelling timed concurrent systems using activity diagram patterns;accelerometer based verification of 3-D signatures on mobile devices;efficient palm print search based on database clustering for personal identification;improving table of contents recognition using layout-based features;predicting the popularity of social curation;parameter learning for statistical machine translation using CMA-ES;a study of feature combination in gesture recognition with kinect;formalising concurrent UML state machines using coloured petri nets and emotional facial expression analysis in the time domain.
We address a problem of learning ordinal classifiers from partially annotated examples. We introduce a V-shaped interval-insensitive loss function to measure discrepancy between predictions of an ordinal classifier an...
详细信息
We address a problem of learning ordinal classifiers from partially annotated examples. We introduce a V-shaped interval-insensitive loss function to measure discrepancy between predictions of an ordinal classifier and a partial annotation provided in the form of intervals of candidate labels. We show that under reasonable assumptions on the annotation process the Bayes risk of the ordinal classifier can be bounded by the expectation of an associated interval-insensitive loss. We propose several convex surrogates of the interval-insensitive loss which are used to formulate convex learning problems. We described a variant of the cutting plane method which can solve large instances of the learning problems. Experiments on a real-life application of human age estimation show that the ordinal classifier learned from cheap partially annotated examples can achieve accuracy matching the results of the so-far used supervised methods which require expensive precisely annotated examples.
暂无评论