Artificial intelligence, machine learning and user interface design / Abhijit Banubakode [and five others].

Format:

Book

Author/Creator:

Banubakode, Abhijit, author.

Language:

English

Subjects (All):

Artificial intelligence.

Human--Computer Interaction.

Human.

Machine learning.

User interfaces (Computer systems).

Physical Description:

1 online resource (303 pages)

Edition:

First edition.

Place of Publication:

Singapore : Bentham Science Publishers, [2024]

Summary:

Artificial Intelligence, Machine Learning and User Interface Design is a forward-thinking compilation of reviews that explores the intersection of Artificial Intelligence (AI), Machine Learning (ML) and User Interface (UI) design. The book showcases recent advancements, emerging trends and the transformative impact of these technologies on digital experiences and technologies. The editors have compiled 14 multidisciplinary topics contributed by over 40 experts, covering foundational concepts of AI and ML, and progressing through intricate discussions on recent algorithms and models. Case studies and practical applications illuminate theoretical concepts, providing readers with actionable insights. From neural network architectures to intuitive interface prototypes, the book covers the entire spectrum, ensuring a holistic understanding of the interplay between these domains. Use cases of AI and ML highlighted in the book include categorization and management of waste, taste perception of tea, bird species identification, content-based image retrieval, natural language processing, code clone detection, knowledge representation, tourism recommendation systems and solid waste management. Advances in Artificial Intelligence, Machine Learning and User Interface Design aims to inform a diverse readership, including computer science students, AI and ML software engineers, UI/UX designers, researchers, and tech enthusiasts. ReadershipComputer science students, AI and ML software engineers, UI/UX designers, researchers, and tech enthusiasts.

Contents:

Cover

Title

Copyright

End User License Agreement

Contents

Preface

List of Contributors

Artificial Taste Perception of Tea Beverage Using Machine Learning

Amruta Bajirao Patil1 and Mrinal Rahul Bachute1,*

INTRODUCTION

USER EXPERIENCE (UX) EVALUATION

LITERATURE REVIEW

Metal Oxide Semiconductor (MOS) Sensors

Conducting Particle (CP) Sensors

Acoustic Wave Sensors

Potentiometric Sensor

Voltammetric Sensor

Commercial Solutions

Color and Image Sensors

PATENT REVIEW

BIBLIOMETRIC REVIEW

Tea Beverage

Artificial Taste Perception

Machine Learning (ML)

IMPLEMENTATION

Experiment Requirement

Proportion Sample Sets

Results

CONCLUDING REMARKS

REFERENCES

Significance of Evolutionary Artificial Intelligence: A Detailed Overview of the Concepts, Techniques, and Applications

Ashish Tripathi1,*, Rajnesh Singh1, Arun Kumar Singh2, Pragati Gupta1, Siddharth Vats3 and Manoj Singhal4

ARTIFICIAL INTELLIGENCE

Types of Artificial Intelligence

Weak Artificial Intelligence

Strong Artificial Intelligence

Reactive Artificial Intelligence

Limited Memory Artificial Intelligence

Theory-of-Mind Artificial Intelligence

Self-Aware Artificial Intelligence

Applications of Artificial Intelligence

Customer Service

Speech Recognition

Computer Vision

Recommendation Engines

Automated Stock Trading

EVOLUTIONARY COMPUTATION

STATE-OF-THE-ART DISCUSSION ON EVOLUTIONARY ARTIFICIAL INTELLIGENCE

STATE-OF-THE-ART APPLICATIONS OF EVOLUTIONARY MACHINE LEARNING

EVOLUTIONARY MACHINE LEARNING BASED CASE STUDIES

Case Studies

Case Studies in Companies

Case Studies in Healthcare

SIGNIFICANCE OF EVOLUTIONARY ARTIFICIAL INTELLIGENCE IN DECISION MAKING

Limitations of Current AI in Decision-making.

Role of Evolutionary Computation to Overcome the Limitations of AI

Evolutionary Computation with Artificial Intelligence

Evolutionary Artificial Intelligence in Solving the Real World Problems

Effective Web Interface Design

Online Personalization Shopping

Effective Marketing

Surveillance System

Agriculture and Food Security

CURRENT ISSUES WITH EVOLUTIONARY MACHINE LEARNING

CONCLUSION

Impact of Deep Learning on Natural Language Processing

Arun Kumar Singh1,*, Ashish Tripathi2, Sandeep Saxena2, Pushpa Choudhary2, Mahesh Kumar Singh3 and Arjun Singh1

FUNDAMENTAL CONCEPTS OF A DEEP NEURAL NETWORK

Concept of the Layers

Input Layer (xi)

Output Layer (Y)

Hidden Layer (wixi)

Neuron

Deep Learning Background

Convolutional Neural Networks

Benefits of Employing CNNs

Recurrent Neural Network

Natural Language Processing

Working Principle of NLP

Lexical Analysis

Syntactic Analysis/Syntax Analysis

Semantic Analysis

Discourse Integration

Pragmatic Analysis

Needs of NLP

Application of NLP can Solve

NLP LITERATURE REVIEW

Sentiment Analysis

Basic LSTM Model

Challenges in THE NLP

Syntactic Ambiguity Leads to Misunderstanding: Cases

Latest Trends in Natural Language Processing-

Future of Natural Language Processing (NLP)

NLP Challenges

Comparison with the New AI Models with NLP

A Review on Categorization of the Waste Using Transfer Learning

Krantee M. Jamdaade1, Mrutunjay Biswal1,* and Yash Niranjan Pitre1

RELATED WORKS

Machine Learning Techniques

Deep Learning Techniques

Internet of Things

Transfer Learning Techniques

METHODOLOGY USED

Survey

Design and Creation

VGG16

Inceptionv3

ResNet50

MobileNET

NASNetMobile

Xception

DATASET.

RESEARCH FINDINGS

ACKNOWLEDGEMENTS

Automated Bird Species Identification using Audio Signal Processing and Neural Network

Samruddhi Bhor1,*, Rutuja Ganage1, Hrushikesh Pathade1, Omkar Domb1 and Shilpa Khedkar1

RELATED WORK

BIRD CLASSIFICATION CHALLENGES

MLSP 2013

BirdCLEF 2016

NIPS4B 2013

PREVIOUS METHODOLOGIES

MSE Approach

Correlation Analysis

Frequency Shift Correlation Analysis

Shift in Frequency

Symmetry-based Correlation Analysis

MFCC Approach

HMM-based Modelling of Bird Vocalisation Elements

Segmentation and Estimation of Frequency Tracks

BACKGROUND ON CONVOLUTIONAL NEURAL NETWORK

Convolutional Layer

Fully Connected Layer

Dropout

Dense Layer

Activation Functions

RelU

Softmax Activation Function

Categorical Cross Entropy

Adam Optimizer

Sequential Model

ARCHITECTURE OF THE PROPOSED MODEL

Dataset

Preprocessing

Feature Extraction

Model Creation

RESULTS

Powering User Interface Design of Tourism Recommendation System with AI and ML

P.M. Shelke1, Suruchi Dedgaonkar1,* and R.N. Bhimanpallewar1

THE EVOLUTION OF TRAVEL RECOMMENDER SYSTEMS

The Collaborative Filtering (CF)

The Content Based Filtering (CB)

The Social Filtering (SF)

Demographic Filtering (DE)

Knowledge-based Filtering (KB)

Utility-based (UB) Filtering

Hybrid Recommendation (HR)

CHALLENGES IN CURRENT TRS SYSTEM

IMPORTANCE OF USER INTERFACE IN TRS

HOW DO AI AND MACHINE LEARNING IMPROVE UX?

Thin UI

Task Automation

Smart Systems

Visual Effects

Personalisation

Choice Architecture

Emotion Recognition

Chatbots

Recommendation Systems

CASE STUDY

Destination Recommendation System (DRS)

Methodology.

UI/UX Implementation to Improve User Engagement

AI/ML to Build the Recommendation System

ChatBot

Methodology

Performance

BENEFITS OF AI AND ML IN UX

UI/UX AND AI/ML PRODUCTS

UX Challenges for AI/ML Products

Theme 1: Trust &amp

Transparency

Theme 2: User Feedback &amp

Control

Theme 3: Value Alignment

Advancements by UI/UX and AI/ML Products

Exploring the Applications of Complex Adaptive Systems in the Real World: A Review

Ajinkya Kunjir1,*

BACKGROUND

Emergence

Adaptation

Self-Organization

Non-Linearity

Aggregation

Diversity

CAS VS ABM

Potential Applications of CAS

Manufacturing and Assembly Systems

Healthcare Organizations and Medical Service Delivery

Conceptualizing CAS for Medical Service Delivery

Military and Defense

Distributed Systems (Peer-to-Peer)

Internet of Things (IoT)

TOOLS FOR CAS MODELLING

Need for Visualization in CAS

Insights into Deep Learning and Non-Deep Learning Techniques for Code Clone Detection

Code Clones

Existing Frameworks and Benchmarks for CCD Tools

Target Functionality Selection

Time Complexity

COMPARATIVE STUDY OF CCD TECHNIQUES

Text-based Techniques

Token-based Techniques

Tree-based Techniques

Program Dependency Graph (PDG)

Metrics-based Techniques

Application Using Machine Learning to Predict Child's Health

Saurabh Kolapate1,*, Tejal Jadhav1 and Nikhita Mangaonkar1

SURVEY REPORT

ALGORITHM

Rule Based Algorithm

Rules can be Accessed by Following Factors

Properties of Rule-based Classifiers

How to Create a Rule

Features

Disease Detection and Cure

Vaccination Details.

Child Vaccination Reminder

Daily Facts

Daily Exercises

BMI Calculator

Healthy Tips

SCREENSHOTS

FUTURE SCOPE

Shifting from Red AI To Green AI

Samruddhi Shetty1, Nirmala Joshi1,* and Abhijit Banubakode2,3

METHODOLOGY

Rationale

Objective

Hypothesis

Hypothesis 1

Hypothesis 2

Hypothesis 3

Conceptual Framework

Artificial Intelligence AI-definition

AI Adoption

Red AI

Green AI

Sustainability SDGs Categories Bifurcation

Sample Design

SAMPLE RESULTS AND DISCUSSIONS

FURTHER ANALYSIS

Knowledge Representation in Artificial Intelligence - A Practical Approach

Vandana C. Bagal1,*, Archana L. Rane1, Debam Bhattacharya1, Abhijeet Banubakode2,3 and Vishwanath S. Mahalle3

LITERATURE SURVEY

INFERENCE RULE

AI Knowledge Cycle

Perception

Learning

Representation

Reasoning

Execution

Connectives

Rule 1

Rule 2

Rule 3

Rule 4

Rule 5

Rule 6

Rule 7

KNOWLEDGE REPRESENTATION

File Content-based Malware Classification

Mahendra Deore1,* and Chhaya S. Gosavi1

Malware: A Threat to the Network

MALWARE DETECTION

MALWARE DATASET

BLOCK DIAGRAM OF PROPOSED WORK

MACHINE LEARNING

Naive Bayes Classifier (NBC)

Decision Tree

Support Vector Machine (SVM)

Enhancing Efficiency in Content-based Image Retrieval System Using Pre-trained Convolutional Neural Network Models

Vishwanath S. Mahalle1,*, Narendra M. Kandoi1, Santosh B. Patil1, Abhijit Banubakode1,2 and Vandana C. Bagal3

PROPOSED CNN PRE-TRAINED MODEL FOR SIMILAR IMAGE RETRIEVAL

Pre-processing.

Deep Features Extraction using ResNet Pre-trained CNN.

Notes:

Includes bibliographical references.

Description based on publisher supplied metadata and other sources.

Description based on print version record.

ISBN:

981-5179-60-8

OCLC:

1435753969