
Mining Intelligence and Knowledge Exploration
Description
Alles über E-Books | Antworten auf Fragen rund um E-Books, Kopierschutz und Dateiformate finden Sie in unserem Info- & Hilfebereich.
The 40 full papers presented were carefully reviewed and selected from 139 submissions. The papers were grouped into various subtopics including arti ficial intelligence, machine learning, image processing, pattern recognition, speech processing, information retrieval, natural language processing, social network analysis, security, and fuzzy rough sets.
More details
Other editions
Additional editions

Content
- Intro
- Preface
- Organization
- Contents
- Functional Link Artificial Neural Network for Multi-label Classification
- 1 Introduction
- 2 Related Works
- 3 Preliminaries
- 3.1 Functional Link Artificial Neural Network (FLANN)
- 3.2 Representation of Multi-label Data
- 4 The Proposed Multi-label FLANN (MLFLANN)
- 4.1 Architecture of the Network
- 4.2 Training Phase
- 4.3 Testing Phase
- 5 Experimental Details and Analysis of Results
- 5.1 Datasets Used
- 5.2 Results and Analysis
- 6 Conclusion
- References
- Emotion Recognition Through Facial Gestures - A Deep Learning Approach
- Abstract
- 1 Introduction
- 2 Dataset
- 3 Preprocessing
- 4 Emotion Prediction Using SVM
- 5 System Architecture
- 5.1 Training Phase
- 5.2 Testing Phase
- 6 Convolutional Neural Network
- 7 Various Attempted Networks, Their Comparisons and the Selection of Proposed Network
- 8 Proposed Network Architecture
- 9 Results
- 10 Conclusion
- References
- Supervised Approaches to Assign Cooperative Patent Classification (CPC) Codes to Patents
- 1 Introduction
- 2 Related Work and Background
- 3 Datasets
- 4 Methods: Label Scoring, Reranking, and Thresholding
- 4.1 Label Scoring
- 4.2 Label (re)ranking
- 4.3 Label Cut-Off/Thresholding
- 5 Experiment and Results
- 6 Conclusion
- References
- A Betweenness Centrality Guided Clustering Algorithm and Its Applications to Cancer Diagnosis
- 1 Introduction
- 2 Clustering Using Betweenness Centrality on Spanning Subgraph
- 3 Experimental Analysis
- 4 Conclusion and Future Scope
- References
- MahalCUSFilter: A Hybrid Undersampling Method to Improve the Minority Classification Rate of Imbalanced Datasets
- 1 Introduction
- 2 Related Work
- 2.1 Undersampling
- 3 Proposed Method
- 3.1 Motivation for the Proposed Method
- 3.2 Theoritical Background of Proposed Method
- 3.3 Framework for the Proposed Method
- 3.4 Results
- 4 Conclusions
- References
- Bezier Curve Based Continuous Medial Representation for Shape Analysis: A Theoretical Framework
- Abstract
- 1 Introduction
- 2 Proposed Methodology
- 3 Polygonal Approximation
- 4 Construction and Regularization of the Skeleton
- 5 Bezier Curve Description
- 6 Data Structure
- 7 Experimental Results
- 8 Conclusion
- Acknowledgements
- References
- Trust Distrust Enhanced Recommendations Using an Effective Similarity Measure
- 1 Introduction
- 2 Related Work
- 2.1 Collaborative Filtering
- 2.2 Trust Model
- 3 Trust Distrust Enhanced Recommendation Framework
- 4 Experiment Setup
- 4.1 Design of Experiments
- 4.2 Performance Evaluation
- 4.3 Experiments
- 4.4 Result
- 5 Conclusion
- References
- Language Identification Based on the Variations in Intonation Using Multi-classifier Systems
- Abstract
- 1 Introduction
- 2 Proposed Work
- 3 Implementation
- 4 Results and Discussion
- 5 Conclusion
- Acknowledgment
- References
- Cognitive Decision Making for Navigation Assistance Based on Intent Recognition
- 1 Introduction
- 2 Model of Intention Prediction
- 2.1 Features
- 2.2 Intention Recognition
- 2.3 Orientation and Distance
- 3 Implementation and Results
- 3.1 Navigation Path
- 3.2 Avoiding Obstacle
- 4 Analysis
- 5 Conclusion
- References
- Clinical Intelligence: A Data Mining Study on Corneal Transplantation
- Abstract
- 1 Introduction
- 2 Background
- 2.1 Cornea
- 2.2 Clinical Intelligence System
- 2.3 Related Work
- 3 Methods and Tools
- 4 Case Study
- 4.1 Business Understanding
- 4.2 Data Understanding
- 4.3 Data Preparation
- 4.4 Modeling
- 4.5 Evaluation
- 5 Discussion
- 6 Conclusions and Future Work
- Acknowledgement
- References
- High-Quality Medical Image Compression Using Discrete Orthogonal Cosine Stockwell Transform and Optimal Integer Bit Allocated Quantization
- Abstract
- 1 Introduction
- 2 Proposed Medical Image Codec
- 2.1 Designing of the Image Transformation Block for the Proposed Codec
- 2.2 Optimal Bit Allocated Quantization Block for the Proposed Codec
- 3 Results and Discussions
- 3.1 Time Complexity Analysis of the Proposed Medical Image Codec
- 4 Conclusions
- References
- Coprime Mapping Transformation for Protected and Revocable Fingerprint Template Generation
- 1 Introduction
- 1.1 Background
- 1.2 Existing Approaches
- 1.3 Contributions
- 2 Proposed Scheme
- 2.1 Pre-processing and Minutiae Extraction
- 2.2 Feature Extraction
- 2.3 Cancelable Template Generation
- 2.4 Matching
- 3 Experimental Results and Analysis
- 3.1 Validation of Parameter: Number of Sectors (s)
- 3.2 Performance
- 3.3 Baseline Comparison
- 3.4 Comparison with Existing Approaches
- 4 Security Analysis
- 4.1 Irreversibility Analysis
- 4.2 Revocability Analysis
- 4.3 Diversity Analysis
- 5 Conclusion
- References
- Supervised Asymmetric Metric Extraction: An Approach to Combine Distances
- 1 Introduction
- 2 Metric Approaches in Machine Learning
- 3 Supervised Asymmetric Metric Extraction
- 4 Biometric Applications
- 4.1 Datasets and Original Metrics
- 4.2 Learned Metrics
- 4.3 Performance Test
- 5 Conclusion
- References
- Interval-Valued Writer-Dependent Global Features for Off-line Signature Verification
- Abstract
- 1 Introduction
- 2 Proposed Method
- 2.1 Feature Computation
- 2.2 Selection of Writer-Dependent Features
- 2.3 Fixation of Feature Dimension and Threshold for Individual Writer
- 2.4 Clustering and Creation of Interval-Valued Feature Vector
- 2.5 Verification
- 3 Experimentation and Results
- 4 Comparative Analysis
- 5 Conclusion
- References
- Despeckling with Structure Preservation in Clinical Ultrasound Images Using Historical Edge Information Weighted Regularizer
- 1 Introduction
- 2 Proposed Approach
- 3 Experimental Analysis
- 3.1 Dataset
- 3.2 Result and Analysis
- 4 Conclusion
- References
- Fingerprint Image Quality Assessment and Scoring
- 1 Introduction
- 2 Related Work
- 3 Proposed Method
- 3.1 Block Quality Labeling
- 3.2 Fingerprint Quality Score Computation
- 4 Experimental Results
- 5 Conclusions
- References
- A Multi-objective Evolutionary Algorithm for Color Image Segmentation
- 1 Introduction
- 2 Proposed Approach
- 2.1 Representation of Individuals
- 2.2 Generation of Initial Segments
- 2.3 Objective Functions
- 2.4 Evolutionary Operators
- 3 Evaluation Criterion: Modified PRI
- 4 Experiments and Results
- 4.1 Experimental Setup
- 4.2 Results and Discussion
- 5 Conclusion
- References
- Face Recognition by RBF with Wavelet, DCV and Modified LBP Operator Face Representation Methods
- Abstract
- 1 Introduction
- 2 Face Representation
- 2.1 Wavelet Transformation
- 2.2 Wavelet Packet Transformation
- 2.3 Discriminative Common Vector
- 2.4 Proposed Local Binary Pattern
- 3 Recognition by Radial Basis Function Neural Network
- 3.1 Algorithm
- 4 Results and Discussions
- 5 Conclusion
- References
- DNN-HMM Acoustic Modeling for Large Vocabulary Telugu Speech Recognition
- 1 Introduction
- 2 IIIT-H Telugu Speech Corpus
- 3 System Overview
- 4 DNN-HMM Modeling
- 4.1 Deep Neural Networks
- 4.2 Ergodic HMMs
- 4.3 Training for DNN-HMM
- 4.4 Testing for DNN-HMM
- 5 Results and Discussion
- 6 Conclusion and Future Scope
- References
- Memetic Algorithm Based on Global-Best Harmony Search and Hill Climbing for Part of Speech Tagging
- Abstract
- 1 Introduction
- 2 Related Works
- 2.1 Traditional Approaches to Build POS Taggers
- 2.2 Metaheuristic Algorithms as an Approach to Build POS Taggers
- 2.3 Tagsets for Tagging Corpus and Tagged Corpus
- 3 Harmony Search Algorithm
- 4 Algorithm Proposed for the Tagging Problem
- 4.1 Part-of-Speech Tagging (POST) Problem
- 4.2 Part-of-Speech Tagging as an Optimization Problem
- 4.3 Global-Best Harmony Search Tagger
- 5 Experiments, Analyses, and Comparisons
- 5.1 Configuration
- 5.2 Results
- 6 Conclusions and Future Work
- Acknowledgements
- References
- A Study on Crossmodal Correspondence in Sensory Pathways Through Forced Choice Task and Frequency Ba ...
- Abstract
- 1 Introduction
- 2 Theory
- 3 Materials and Methods
- 3.1 Participants
- 3.2 Stimuli
- 3.3 Procedure
- 3.4 Analysis of Words
- 4 Results and Discussion
- 5 Conclusions
- References
- Point Process Modeling of Spectral Peaks for Low Resource Robust Speech Recognition
- 1 Introduction
- 2 Baseline HMM Recognizer
- 3 Spectral Peak Based Point Process Representation of Speech
- 3.1 Identification of Spectral Peaks
- 3.2 Removal of Spurious Spectral Peaks
- 4 Bankwise Segmentation of Spectral Peaks
- 5 Point Process Model Based Isolated Word Recognizer
- 6 Experimentation and Results
- 7 Conclusion
- References
- Significance of DNN-AM for Multimodal Sentiment Analysis
- 1 Introduction
- 2 Databases
- 2.1 Spanish Database
- 2.2 Hindi Database
- 3 Audio Sentiment Classification
- 3.1 DNNAM
- 4 Sentiment Analysis Using Text Features
- 5 Multimodal Sentiment Analysis
- 6 Summary and Conclusions
- References
- Pattern Based Information Retrieval Approach to Discover Extremist Information on the Internet
- Abstract
- 1 Introduction
- 2 Proposed Approach
- 2.1 General Scheme
- 2.2 "N-Gram Vs Sentence" Matrix Text Representation Model
- 2.3 Extracting Hidden Topics Using ONMF
- 2.4 Using N-Gram Based Topics for Keywords Extraction and Document's Relevance Estimation
- 3 Experimental Evaluation
- 4 Conclusions
- Acknowledgment
- References
- A Concept Driven Graph Based Approach for Estimating the Focus Time of a Document
- 1 Introduction
- 2 Related Work
- 3 Background
- 4 Our Approach
- 5 Experimental Setup
- 5.1 Datasets
- 5.2 Models Compared
- 5.3 Evaluation Metrics
- 6 Results
- 7 Conclusion
- References
- Query Morphing: A Proximity-Based Approach for Data Exploration and Query Reformulation
- Abstract
- 1 Introduction
- 1.1 Contribution and Outline
- 2 Literature Review
- 3 Query Morphing: A Data Exploration Approach
- 3.1 Proposed Approach
- 4 Design Issues and Analysis
- 5 Conclusion
- References
- WikiSeeAlso: Suggesting Tangentially Related Concepts (See also links) for Wikipedia Articles
- 1 Introduction
- 2 Background
- 3 WikiSeeAlso
- 3.1 Candidate Generation
- 3.2 Candidate Ranking
- 4 Empirical Evaluation
- 4.1 Datasets
- 4.2 Performance Measures
- 4.3 Implementation Details
- 4.4 Results
- 5 Discussion
- 5.1 Existing approaches
- 5.2 Empirical Comparison
- 5.3 Case Studies
- 6 Conclusions and Future Directions
- References
- Integrating Knowledge Encoded by Linguistic Phenomena of Indian Languages with Neural Machine Translation
- 1 Introduction
- 2 Related Work
- 3 System Architecture
- 4 Datasets and Resources
- 5 Experiments and Results
- 5.1 Building 110 Baseline NMT Systems for Indian Languages
- 5.2 Exploiting Linguistic Information to Aid NMT
- 6 Conclusion and Future Work
- References
- Partitioned-Based Clustering Approaches for Single Document Extractive Text Summarization
- Abstract
- 1 Introduction
- 2 Proposed Work
- 2.1 Pre-processing
- 2.2 Feature Extraction
- 2.3 Learning k in k-means
- 2.4 Clustering
- 2.5 Post-processing
- 3 Evaluation and Results
- 4 Conclusion
- References
- Arousal Prediction of News Articles in Social Media
- 1 Introduction
- 2 Related Work
- 3 Methodology
- 3.1 Finding the Posts of High Arousal
- 3.2 Generate the Candidate Features
- 3.3 Feature Selection
- 3.4 Arousal Based Post Classification
- 3.5 Determining the Topics of High Arousal
- 4 Evaluations
- 4.1 Experimental Setup
- 4.2 Effectiveness of Methods
- 4.3 Analyzing the Topics of High Arousal
- 5 Conclusion
- References
- Sentiment Analysis of Tweets in Malayalam Using Long Short-Term Memory Units and Convolutional Neural Nets
- 1 Introduction
- 2 Related Work
- 3 Background
- 3.1 Recurrent Neural Network or RNN
- 3.2 Long Short-Term Memory or LSTM
- 3.3 Convolutional Neural Network or CNN
- 3.4 Regularization via Dropout
- 3.5 Training and Softmax Classifier
- 4 Experiment and Evaluations
- 4.1 Dataset
- 4.2 Models
- 4.3 Result and Discussion
- 5 Conclusion and Future Work
- References
- Improved Community Interaction Through Context Based Citation Analysis
- 1 Introduction
- 1.1 Related Work
- 1.2 Contribution
- 2 Dataset Description
- 2.1 Field Tagging
- 2.2 Classification of Papers into Single Communities
- 3 Construction of the Citation Network
- 3.1 Preprocessing
- 3.2 Citation Network
- 3.3 Term Labelled Citation Network
- 4 Proposed Methodology
- 4.1 Tagging Papers with a Set of Keywords
- 4.2 Similarity of Term Sets
- 5 Community Network
- 6 Metrics Evaluation and Comparison
- 6.1 Detailed Analysis of the Transitions in Graph
- 7 Conclusion
- References
- Mining Informative Words from the Tweets for Detecting the Resources During Disaster
- 1 Introduction
- 2 Related Work
- 3 Proposed Method
- 3.1 Tweet Collection
- 3.2 Pre-processing of Tweets
- 3.3 Feature Extraction and Training Phase
- 3.4 Testing Phase
- 4 Experimental Results and Analysis
- 4.1 Data-Set
- 4.2 Performance Measures
- 5 Conclusion
- References
- An Ensemble Based Method for Predicting Emotion Intensity of Tweets
- 1 Introduction
- 2 Related Work
- 3 Problem Definition
- 4 Methodology
- 4.1 Convolution Neural Networks (CNN)
- 4.2 Extreme Gradient Boosting (XGBoost)
- 4.3 Support Vector Regression (SVR)
- 4.4 Ensemble
- 5 Experiments
- 5.1 Data
- 5.2 Evaluation Metrics
- 5.3 Results and Discussions
- 6 Conclusion
- References
- A Graph-Based Frequent Sequence Mining Approach to Text Compression
- 1 Introduction
- 2 Related Work
- 3 Flow of Proposed Graph-Based Text Compression
- 4 Frequent Sequence Mining-Based Text Compression Algorithm
- 5 Results and Discussions
- 6 Conclusion
- References
- ULR-Discr: A New Unsupervised Approach for Discretization
- 1 Introduction
- 2 Related Work
- 3 ULR-Discr Framework
- 3.1 A Brief Overview of ChiMerge and Chi2
- 3.2 The Proposed ULR-Discr Algorithm
- 3.3 Lex as a Tool for Numeric Discretization
- 4 The Used Statistics
- 4.1 Using the 2 statistic
- 4.2 Using the Distance of Manhattan
- 4.3 Using the Pearson Coefficient
- 5 Experimental Results
- 5.1 The Tested Datasets
- 5.2 Experimental Results for ULR-Discr
- 5.3 Comparing Different Variants of ULR-Discr with ZDisc
- 6 Conclusion
- References
- Identifying Terrorist Index (T+) for Ranking Homogeneous Twitter Users and Groups by Employing Citation Parameters and Vulnerability Lexicon
- Abstract
- 1 Introduction
- 2 Related Work
- 3 Dataset Preparation
- 3.1 Stage 1: Preparation of List of Seed Words (Seedlist)
- 3.2 Stage 2: List of Terrorist Code Words (Codelist)
- 3.3 Stage 3: Preparation of List of Current Terrorist Crimes Dates (Crimelist)
- 3.4 Stage 4: Dataset of Crawled Tweet Texts with Details
- 3.5 Stage 5: Dataset of Each Specific Tweet's Conversation Details
- 3.6 Stage 6: Dataset of Each Specific User's Timeline Details
- 4 Methodology
- 4.1 Homogeneous Group Formation
- 4.2 Citation Analysis of Twitter Users
- 4.2.1 Counts of Total Citations
- 4.2.2 Identification of Citation Indices (h-Index and i10-Index)
- 4.3 Preparation of Vulnerability Lexicon
- 4.3.1 Seed Word Lexicon Analysis
- 4.3.2 Code Word Lexicon Analysis
- 4.3.3 Parts-of-Speech (POS) Tags
- 4.3.4 Named Entity Tags
- 4.4 Ranking of Twitter Users
- 4.5 Ranking of Homogeneous Twitter Groups
- 5 Results and Analysis
- 5.1 Analysis of Users' Ranking
- 5.2 Analysis of Homogeneous Groups' Ranking
- 6 Conclusion and Future Work
- References
- Soft Metaphor Detection Using Fuzzy c-Means
- 1 Introduction
- 2 Related Work
- 3 Soft Metaphor Detection Using Fuzzy c-Means
- 3.1 Problem Representation
- 3.2 Feature Extraction
- 3.3 Fuzzy c-Means
- 3.4 Experiments and Results
- 4 Conclusion
- References
- A Study on CART Based on Maximum Probabilistic-Based Rough Set
- Abstract
- 1 Introduction
- 2 Theoretical Background
- 2.1 Pawlak's Rough Set Model [9, 13]
- 2.2 Bayesian Decision Theoretic Rough Set [1, 2, 8, 15]
- 2.3 Maximum Probabilistic Based Rough Set [7, 9, 18]
- 2.4 Decision Tree: CART [3, 10, 11, 17]
- 3 Implementation of MPBRS-Based CART
- 3.1 Processing Steps
- 3.2 Algorithm
- 3.3 Execution of CART and MPBRS-Based CART in R Environment
- 4 Experimental Results and Discussion
- 5 Conclusion
- References
- Portfolio Optimization in Dynamic Environments Using MemSPEAII
- 1 Introduction
- 2 Related Works
- 3 Portfolio Optimization
- 4 Proposed Method
- 4.1 Evolution Architecture
- 4.2 Trading Architecture
- 4.3 Memory Enhanced SPEAII
- 4.4 Choosing from Evolved Pareto Front
- 5 Experimental Setup
- 5.1 Data and Parameters
- 5.2 Walk Forward Testing
- 5.3 Comparative Study
- 6 Results and Discussions
- 7 Conclusion
- References
- Author Index
System requirements
File format: PDF
Copy protection: Watermark-DRM (Digital Rights Management)
System requirements:
- Computer (Windows; MacOS X; Linux): Use the free software Adobe Reader, Adobe Digital Editions, or any other PDF viewer of your choice (see eBook Help).
- Tablet/Smartphone (Android; iOS): Install the free app Adobe Digital Editions or another reading app for eBooks, e.g., PocketBook (see eBook Help).
- E-reader: Bookeen, Kobo, Pocketbook, Sony, Tolino and many more (only limited: Kindle).
The file format PDF always displays a book page identically on any hardware. This makes PDF suitable for complex layouts such as those used in textbooks and reference books (images, tables, columns, footnotes). Unfortunately, on the small screens of e-readers or smartphones, PDFs are rather annoying, requiring too much scrolling.
This eBook uses Watermark-DRM, a „soft” copy protection. This means that there are no technical restrictions to prevent illegal distribution. However, there is a personalised watermark embedded in the eBook that can be used to identify the purchaser of the eBook in the event of misuse and to provide evidence for legal purposes.
For more information, see our eBook Help page.