Details

Subject(s)

• Artificial intelligence—Congresses [Browse]

Editor

• Shetty D., Pushparaj [Browse]
• Shetty, Surendra [Browse]

Series

• Advances in Intelligent Systems and Computing [More in this series]
• Advances in Intelligent Systems and Computing ; v.1386 [More in this series]

Bibliographic references

Includes bibliographical references.

Source of description

Description based on print version record.

Contents

• Intro
• Preface
• Contents
• About the Editors
• Smart Environment and Network Issues
• Machine Learning-Based Ensemble Network Security System
• 1 Introduction
• 2 Related Work
• 3 Dataset Description
• 4 Proposed Work
• 4.1 First LOD (LOD-1)
• 4.2 Second LOD (LOD-2)
• 5 Experimental Setup and Results
• 5.1 NB Classifier
• 5.2 LR Classifier
• 5.3 K-NN Classifier
• 5.4 DT Classifier
• 6 Conclusion and Future Scope
• References
• Machine Learning-Based Air Pollution Prediction
• 3 Framework and System Design
• 3.1 Implementation Details
• 3.2 Dataset Details
• 3.3 Algorithms
• 4 Experimental Set-up and Results
• 5 Conclusion and Future Scope
• Crop and Fertilizer Recommendation System Based on Soil Classification
• 3 Proposed Work
• 3.1 SVM Algorithm
• 4 Experimental Results and Analysis
• 4.1 Comparison of SVM with k-NN and Decision Tree
• 5 Conclusion
• Human Activity Classification Using Deep Convolutional Neural Network
• 2 Literature Survey
• 3 Proposed Model
• 4 Results and Discussion
• Intelligent IoT-Based Product Dispenser and Billing System
• 3 Proposed System
• 3.1 System Control Flow
• 3.2 Recommendation Algorithm
• 3.3 System Architecture
• 3.4 Recommendation System
• Models Predicting PM 2.5 Concentrations-A Review
• 2 Objectives of Various Research Articles
• 2.1 Machine Learning Models
• 2.2 Statistical Models/ Time Series Model/Chemical Models
• 3 Region and Data
• 4 Data Processing Method
• 5 Methodology/Algorithms
• 5.1 Neural Networks
• 5.2 XGBoost and Random Forest
• 5.3 Support Vector Machines.
• 5.4 Decision Tree Regression and MLP Regression
• 5.5 LSTM
• 5.6 Time Series Model
• 5.7 NAXRX, GWR, EZN
• 5.8 Weather Research and Forecasting Model with Chemistry (WRF-Chem)
• 5.9 Wavelet Transform
• 5.10 Differential Evolution (DE)
• 6 Conclusion
• Performance Analysis of Modified TCP New Reno for MANETs
• 2 Result Analysis for TCP New Reno
• 2.1 Performance Parameters for Existing TCP New Reno
• 2.2 Result Analysis for Congestion Window Set to 80%-TCP New Reno Modified Window (MW
• 3 Improvement Over Existing Method
• 4 Conclusion
• Smart Health and Pattern Recognition
• Identification of Helmets on Motorcyclists and Seatbelt on Four-Wheeler Drivers
• 3 Proposed Methodology
• 4 Results and Discussions
• 6 Future Work
• Prediction of Autism in Children with Down's Syndrome Using Machine Learning Algorithms
• 1.1 Issues and Challenges
• 1.2 Objectives
• 1.3 Architecture of the Proposed Study
• 3 Study Area and Methodology
• 3.1 Collection of Data
• 3.2 Data Cleaning
• 3.3 Implementation Process to Build a Model (Module 1 Dataset Using UCI Repository)
• 3.4 Implementation Process to Build a Model (Module 2 Real-Time Dataset)
• 4 Conclusion and Future Work
• Speech Emotion Recognition Using K-Nearest Neighbor Classifiers
• 2 Framework
• 3 KNN Classifiers
• 4 Simulation Results
• Object Detection and Voice Guidance for the Visually Impaired Using a Smart App
• 2 Background
• 3 The Proposed System
• 4 System Architecture and Implementation
• 4.1 Methodology
• 4.2 Description of the Process
• 5 Results
• 6 Test cases
• 7 Conclusion
• References.
• Application to Aid Hearing and Speech Impaired People
• 3 Summary of Literature Review with Research Gaps
• 4 Dataset Description
• 5 Methodology
• 6 Results and Discussion
• Variants of Fuzzy C-Means on MRI Modality for Cancer Image Archives
• 2 Methodology
• 2.1 Fuzzy Approaches for MRI Segmentation
• 3 Empirical Evaluation
• 4 Summary
• A Review on Effectiveness of AI and ML Techniques for Classification of COVID-19 Medical Images
• 2 Literature Review
• 3 Conclusion
• Medical Image Encryption Using SCAN Technique and Chaotic Tent Map System
• 2 SCAN Method
• 2.1 Chaotic Map
• 2.2 Tent Map
• 3 Proposed Method
• 4 Performance Analysis for Proposed Work
• 4.1 Histogram Analysis
• 4.2 Entropy
• 4.3 Mean Square Error
• 4.4 Number of Pixel Change Rate (NPCR)
• 4.5 Peak Signal to Noise Ratio (PSNR)
• 4.6 Unified Average Changed Intensity (UACI)
• 4.7 Experimental Results
• Utilization of Dark Data from Electronic Health Records for the Early Detection of Alzheimer's Disease
• 2 Review of Literature
• 3.1 Data Collection
• 3.2 Data Preprocessing
• 3.3 Machine Learning Classifiers
• 4 Results
• 5 Conclusions
• 6 Future Scope
• Brain Tumor Segmentation Using Capsule Neural Network
• 3 Dataset
• 4 Preprocessing
• 5 Evaluation Metrics
• 6 Results
• Forgery Detection and Image Recommendation Systems
• Using Machine Learning for Image Recommendation in News Articles
• 2.1 Data Collection
• 2.2 Structuring the Data
• 2.3 Training the Model
• 2.4 Generating Training Data.
• 2.5 Training Neural Networks
• 2.6 Image Selection Process
• 2.7 Query Generator Component
• 3 Results
• An Approach to Noisy Synthetic Color Image Segmentation Using Unsupervised Competitive Self-Organizing Map
• 2 Proposed Methodology for Noisy Synthetic Image Clustering
• 3 Experimental Outcomes and Discussions
• Building Dataset and Deep Learning-Based Inception Model for the Character Classification of Tigalari Script
• 2 Tigalari Script
• 3 Preparation of Dataset
• 4 Literature Review
• 6 Results and Evaluation
• Handwritten Character Recognition Using Deep Convolutional Neural Networks
• 3 Convolutional Neural Networks
• 4 Proposed CNN Architecture
• 5 Results and Discussion
• 6 Conclusions
• Implementing Face Search Using Haar Cascade
• 3 Methodology
• 3.1 Face Detection
• 3.2 Face Recognition
• 3.3 Converting the Frames into Video
• 3.4 Algorithm
• 4 Implementation Details
• 4.1 The Scale Invariant Detector
• 4.2 The Modified AdaBoost Algorithm
• 4.3 The Cascaded Classifier
• 6 Conclusion and Future Work
• Deep Learning Photograph Caption Generator
• 4 Methodology
• Streaming of Multimedia Data Using SCTP from an Embedded Platform
• 2 System Specifications
• 2.1 Hardware Specifications
• 2.2 Software Specifications
• 3 Communication Protocols
• 3.1 Transmission Control Protocol (TCP)
• 3.2 Stream Control Transmission Protocol (SCTP)
• 4 Design and Implementation
• 4.1 Block Diagram
• 4.2 Flow Chart.
• 5 Experimental Results
• A Fast Block-Based Technique to Detect Copy-Move Forgery in Digital Images
• 4 Experimental Results
• 5 Conclusion and Discussion
• Bottlenecks in Finite Impulse Response Filter Architectures on a Reconfigurable Platform
• 2 Architectures for FIR Filter
• 2.1 Conventional Architecture (Direct Form and Transposed Form)
• 2.2 Multiplier-Less Architecture
• 2.3 Pipelined Architecture
• 2.4 Parallel Architecture
• 3 Requirements of FIR Filter: A Reconfigurable Platform Perspective
• 3.1 Filter Order
• 3.2 Precession of Data to Represent the Sample/Coefficients
• 3.3 Data Type to Represent the Signal
• 3.4 Sample Rate
• 3.5 Filter Coefficients
• 4.1 Simulation Results
• 4.2 RTL Implementation
• 4.3 Comparative Analysis
• Copy-Move Image Forgery Detection Using Discrete Cosine Transforms
• 2 Proposed Technique
• 3.1 Performance Evaluation
• Sentiment Classification and Data Analysis
• A Detail Analysis and Implementation of Haar Cascade Classifier
• 1 Introduction and Methodology
• 2 Cascading Classifiers
• 3 To Create the Haar Cascade Files
• 4 Results and Conclusion
• Sentiment Analysis of Twitter Posts in English, Kannada and Hindi languages
• 2.1 Related Work
• 3.1 Model Training
• 3.2 Classification
• 4.1 Dataset
• 4.2 Preprocessing
• 4.3 Bag of Words Model
• 4.4 Dataset to Vector Transform
• 5.1 Results for English Dataset
• 5.2 Results for Hindi Dataset
• 5.3 Results for Kannada Dataset
• 6 Conclusion and Future Work.

Show 217 more Contents items

ISBN

• 981-16-3342-8
• 981-16-3341-X

OCLC

1285783892

Statement on language in description

Princeton University Library aims to describe library materials in a manner that is respectful to the individuals and communities who create, use, and are represented in the collections we manage. Read more...