Smart Urban Logistics: Improving Delivery Services by Computational Intelligence (Fuzzy Management Methods)

✍ Scribed by Jhonny Pincay Nieves

• Publisher: Springer
• Year: 2022
• Tongue: English
• Leaves: 180
• Category: Library

✦ Synopsis

Last-mile delivery in cities, where the main problems are the traffic situation and ensuring access to customers’ homes while maintaining their privacy, poses a substantial logistical challenge. This book explores how the service area of mobility, especially last-mile delivery, can be improved and smartified. It demonstrates how a design science method and a transdisciplinary approach have been used to create a traffic area analysis tool that can accommodate the uncertainty and incompleteness of geospatial data; a linguistic traffic merging tool; and a customer classifier. In terms of developing the optimization artifacts, the socio-economic and logistical aspects of cities were considered and fuzzy logic and nature-inspired swarm intelligence (fuzzy ant colony optimization) were applied as basic principles. Pursuing a transdisciplinary approach, the book offers both practical know-how from the industry and theoretical findings, making it a valuable asset for researchers and practitioners in the fields of mobility and logistics.

✦ Table of Contents

Foreword
Preface
Acknowledgments
Contents
List of Figures
List of Tables
List of Algorithms
Part I Motivation and Objectives
1 Introduction
1.1 Background and Motivation
1.2 Research Objectives and Questions
1.3 Methodology
1.3.1 Design Science Research
1.3.2 Transdisciplinary Research
1.4 Outline
1.5 Own Research Contribution
References
Part II Theoretical Background
2 Insights into Smart Cities and Smart Logistics
2.1 Smart Cities
2.1.1 Cognitive and Human-Smart Cities
2.1.2 Digital Ethics in Smart City Solutions
2.1.2.1 Legal Perspective
2.1.2.2 IT Perspective
2.1.2.3 Citizen Perspective
2.2 Smart Mobility and Smart Logistics
2.2.1 Current Research in Smart Logistics
2.2.2 Trends and Challenges
2.3 The Last-Mile Delivery
2.3.1 Last-Mile Issues
2.3.2 Last Mile at Swiss Post
2.4 Final Remarks
2.5 Further Readings
References
3 Computational Intelligence
3.1 Overview of Fuzzy Logic Approaches
3.1.1 Fuzzy Sets Theory
3.1.1.1 Types of Membership functions
3.1.1.2 Type-2 Fuzzy Sets
3.1.2 Linguistic Variables
3.1.3 Linguistic Summaries
3.1.4 Fuzzy Inference
3.1.4.1 Fuzzy Inference and Fuzzy Rules
3.1.4.2 Fuzzy Inference Systems
3.1.5 Design Criteria and Constraints for Fuzzy Systems
3.1.5.1 Design Criteria and Constraints for Fuzzy Sets
3.1.5.2 Design Criteria for Linguistic Variables
3.1.5.3 Design Criteria and Constraints for Fuzzy Rules
3.2 Swarm Intelligence
3.2.1 Basics of Swarm Intelligence
3.2.2 Ant Colony Optimization
3.2.3 Fuzzy Ant System Principles
3.2.4 Trends and Challenges in Swarm Intelligence Applications
3.2.4.1 Current Trends
3.2.4.2 Outlook and Challenges
3.3 Final Remarks
3.4 Further Readings
References
Part III Applications
4 Fuzzifying Geospatial Traffic Data to Convey Information
4.1 Critical Traffic Areas Identification
4.1.1 Conceptual Development
4.1.2 Type-2 Fuzzy Sets and Traffic Models
4.1.3 Framework and Artifact Design
4.1.3.1 Data Cleaner
4.1.3.2 Fuzzifier
4.1.3.3 Fuzzy Inference Engine
4.1.3.4 Visualizer
4.1.4 Implementation and Results
4.1.4.1 Fuzzification and Inference
4.1.4.2 Verification of the Design Criteria for Fuzzy Sets
4.1.4.3 Visualization
4.1.5 Summary and Lessons Learned
4.2 Linguistic Summarization of Traffic Data
4.2.1 Conceptual Development
4.2.2 Linguistic Summaries for Traffic
4.2.3 Framework and Artifact Design
4.2.3.1 Data Selection and Aggregation
4.2.3.2 Linguistic Summaries Mining
4.2.3.3 Visualization of Results
4.2.4 Implementation and Results
4.2.4.1 Linguistic Summaries Mining
4.2.4.2 Verification of the Design Criteria for Linguistic Variables
4.2.5 Visualization of Results
4.2.6 User's Evaluation
4.2.7 Summary and Lessons Learned
4.3 Final Remarks
4.4 Further Readings
References
5 Ethical Classification of Postal Customers
5.1 Conceptual Development
5.2 Modeling Customer's Characteristics
5.3 Methodology
5.3.1 Data Analysis
5.3.2 K-means Clustering
5.3.2.1 Feature Engineering
5.3.2.2 K-means Clustering
5.3.2.3 Visualization
5.3.3 Fuzzy Clustering
5.3.3.1 Feature Engineering and Cluster Validation
5.3.3.2 Visualization
5.3.4 Fuzzy Inference
5.3.4.1 Fuzzy Rules Definition
5.3.4.2 Visualization
5.4 Implementation and Results
5.4.1 Customer Classification with K-means Clustering
5.4.2 Customer Classification with Fuzzy Clustering
5.4.3 Customer Classification with Fuzzy Inference
5.4.3.1 Verification of the Design Criteria for Fuzzy Sets
5.5 Analysis of Results
5.6 Conclusions and Lessons Learned
5.7 Further Readings
References
Part IV Framework and Implementation
6 The Fuzzy Ant Routing (FAR) Conceptual Framework
6.1 Background
6.2 Outline of the Framework
6.3 Architecture and Component Interaction
6.3.1 Data Layer
6.3.2 Knowledge Layer
6.3.3 Intelligence Layer
6.3.4 Visualization Layer
6.4 Evaluation Design
6.4.1 Validity in Simulation
6.4.2 Simulation Setup
6.5 Further Readings
References
7 The FAR Artifact
7.1 Architecture and Introduction to the Artifact
7.1.1 Data Sources Description
7.1.1.1 Probe Data of Delivery Vehicles and Traffic Messages
7.1.1.2 History of Deliveries to Customers
7.1.2 Traffic Criticality
7.1.3 Customer Delivery Success
7.1.4 fas Algorithm Implementation
7.1.4.1 Encoding Geospatial Information with Geohashes
7.1.4.2 Data for Traffic and Customer Delivery
7.1.4.3 Distance and Pheromone Intensity
7.1.4.4 Fuzzy Rules Reasoning
7.1.4.5 Verification of the Design Criteria for Fuzzy Rules
7.1.4.6 Python Implementation
7.1.5 Web Interface
7.2 Evaluation
7.3 Analysis of Results and Lessons Learned
7.4 Further Readings
References
Part V Conclusions
8 Outlook and Conclusions
8.1 Summary
8.2 Alignment with Research Questions and Discussion
8.3 Future Research
8.4 Outlook and Conclusions
References
A Data Structures of Probe Data of Delivery Vehicles and Traffic Message Records Databases
B Python Implementation of the Critical Traffic Areas Identification Artifact
C Sample of Fuzzy Rules for the Customers' Presence at Home During the Mornings
D Python Implementation of the FAS Algorithm
Acronyms
Glossary