|
|
|
|
|
|
|
|
|
1. |
Record Nr. |
UNINA9910629292403321 |
|
|
Titolo |
Living beyond data : toward sustainable value creation / / edited by Yukio Ohsawa |
|
|
|
|
|
|
|
Pubbl/distr/stampa |
|
|
Cham, Switzerland : , : Springer, , [2023] |
|
©2023 |
|
|
|
|
|
|
|
|
|
ISBN |
|
9783031115936 |
9783031115929 |
|
|
|
|
|
|
|
|
Descrizione fisica |
|
1 online resource (293 pages) |
|
|
|
|
|
|
Collana |
|
Intelligent Systems Reference Library ; ; v.230 |
|
|
|
|
|
|
Disciplina |
|
|
|
|
|
|
Soggetti |
|
|
|
|
|
|
Lingua di pubblicazione |
|
|
|
|
|
|
Formato |
Materiale a stampa |
|
|
|
|
|
Livello bibliografico |
Monografia |
|
|
|
|
|
Note generali |
|
|
|
|
|
|
Nota di contenuto |
|
Intro -- Foreword -- Preface: The Reason Why We Seek Living "Beyond Data" -- Contents -- Part I Thoughts and Communication for Living Beyond Data -- 1 Living Beyond Data with Feature Concepts -- 1.1 Introduction: Communications for Discovering Data Utilities -- 1.2 Feature Concepts for Connecting Stakeholders -- 1.3 Examples of Feature Concepts in Data Utilities -- 1.4 Discussion: Feature Concepts as Patters for Living Beyond Data -- 1.5 Conclusions -- References -- 2 Innovation for the Real-World Through Knowing Why -- 2.1 Introduction -- 2.2 Knowing, Uncertainty, and Innovation -- 2.2.1 Ways of Knowing in Innovation -- 2.2.2 Knowing why: Knowing in Situations of Uncertainty and Ambiguity -- 2.2.3 The Observer Problem in Research -- 2.3 Knowing why: Necessity and Capability -- 2.3.1 Necessity: Human Needs and Motivation -- 2.3.2 Capability: Theory-in-Action -- 2.4 Design Practices: Knowing why -- 2.4.1 Necessity: Need-Finding and Benchmarking -- 2.4.2 Capability: Prototyping and Evaluating -- 2.5 Conclusion -- References -- 3 Why Abductive Cognition Goes Beyond Just Learning from Data -- 3.1 Abductive Cognition Generates Knowledge Starting from Data -- 3.1.1 Abduction as Ignorance Preservation -- 3.1.2 Directly Reaching Truth Through Abduction -- 3.2 How Model-Based and Manipulative Abduction Creates Values ``In'' and ``Out'' of Data: The Eco-Cognitive Model (EC-Model) -- 3.2.1 An Example: Construals Create Epistemological |
|
|
|
|
|
|
|
|
|
Value ``In'' and ``Out'' of Data -- 3.3 Asking ``Why'' Means to Reach Beyond Data: Irrelevance and Implausibility Trigger Creativity -- 3.4 Beyond Learning from Data: Trans-Paradigmatic and Transepistemic Abductions -- 3.5 Can Models Computationally Derived from Data Provide Scientific Knowledge of Physical and Biological Systems?. |
3.6 Can Invasive Computational Learning from Big Data Jeopardize Human Creative Abduction in Science? -- 3.7 The Triumph of Shallow Massive Data-Driven Knowledge: Deep Learning and Locked Strategies -- 3.7.1 Reading Ahead -- 3.7.2 Locked Abductive Strategies Acting in a Fixed Scenario of Data Counteract the Maximization of Eco-Cognitive Openness -- 3.7.3 Locking Strategies Restricts Creativity -- 3.8 Conclusion -- References -- 4 Living Labs: A Device That Opens Exploration and Cognitive Generation to Society -- 4.1 Introduction -- 4.2 Overview of European ``Living Labs'' -- 4.2.1 Living Lab's Origins and Founding Intentions -- 4.2.2 Development History of Living Labs -- 4.2.3 Types of Living Labs, Scope of Activities and Methods -- 4.3 The Case of ``Living Labs'' -- 4.3.1 Botnia Living Lab-for Sustainable Smart Cities and Regions -- 4.3.2 HSBC Living Lab, Chalmers University of Technology -- 4.3.3 Trends in Japan -- 4.4 The Essential Features of a Living Labs -- 4.5 A Case Study of Living Labs Based on Its Essential Functions in Iwaki City, Japan -- 4.6 Conclusion -- References -- Part II Explore, Collect, and Use Data -- 5 Interpretability and Explainability in Machine Learning -- 5.1 Introduction -- 5.2 What Is Interpretable Machine Learning? -- 5.3 A Taxonomy of Interpretability Models -- 5.3.1 The Task-Related Latent Dimensions of Interpretability -- 5.3.2 The Method-Related Latent Dimensions of Interpretability -- 5.4 Key Issues of Explainable ML -- 5.5 Conclusion -- References -- 6 Interpretable GAM Models: Predicting Sepsis in ICU Patients -- 6.1 Introduction -- 6.2 Sepsis Prediction -- 6.2.1 Machine Learning in Healthcare -- 6.2.2 GAMs for Sepsis Prediction -- 6.2.3 Problem Definition -- 6.3 Data -- 6.3.1 Origin -- 6.3.2 Identifying Sepsis -- 6.3.3 Data Extraction -- 6.4 Methods -- 6.4.1 General Additive Models -- 6.4.2 Thresholds. |
6.5 Results -- 6.5.1 Model Evaluation -- 6.5.2 Model Comparison -- 6.5.3 Focus: upper G upper A squared upper MGA2M Results -- 6.6 Discussion -- 6.6.1 Implications -- 6.6.2 Limitations -- 6.6.3 Future Research -- 6.7 Conclusion -- References -- 7 Undesigned Data in Discovery Processes and Design of Their Interpretation -- 7.1 Introduction -- 7.2 Two Projects as Concrete Examples for Our Discussion -- 7.2.1 Discovering Interesting Travel Routes from Trajectory Data -- 7.2.2 Collecting and Unifying Syllabuses of Various Universities -- 7.3 Models of KDD Process -- 7.3.1 Two Models of KDD Process -- 7.3.2 Hypothesis Validation or Hypothesis Generation -- 7.4 Manipulating Undesigned Data -- 7.4.1 Designed Data and Undesigned Data -- 7.4.2 Undefined Data as Words in Mathematical Logic -- 7.4.3 Designing an Interpretation of Data -- 7.5 Improvement of the KDD Processes -- 7.6 Conclusion and Remarks -- References -- 8 Why Can We Obtain Such an Analysis? -- 8.1 Introduction -- 8.2 (Big) Data Society -- 8.3 Treatment of Data in the World -- 8.4 Abduction and Analogy -- 8.4.1 Philosophical Abduction -- 8.4.2 Computational Abduction -- 8.4.3 The Clause Management System (CMS) -- 8.4.4 Analogical Reasoning -- 8.4.5 Abductive Analogical Reasoning (AAR) -- 8.5 Data Managemant by Abduction and Analogy -- 8.6 Conclusions -- References -- Part III Insights from Cases -- 9 Positive Artificial Intelligence Meets Affective Walkability -- 9.1 Introduction -- 9.2 Positive Artificial Intelligence -- 9.3 Affective Walkability and Urban Design -- 9.4 Positively Intelligent Neighborhoods: A Call to Action -- 9.4.1 In-vitro Experimental Protocol -- 9.4.2 In-vivo Experimental |
|
|
|
|
|
|
|
|
Protocols -- 9.5 Conclusion -- References -- 10 Machine Tells Us New Potential Values-Physics, Perception, and Affective Evaluations -- 10.1 What Is This? Simple and Typical Data for Machine Learning. |
10.2 What's This Texture? Affective Data Could be Infinite -- 10.2.1 Texture Expression -- 10.2.2 Experiment Showing the Connection Between Texture and Words -- 10.3 Machine Understands Texture Expressed by Sound-Symbolic Words -- 10.4 Machine Helps to Capture Individual Affective Differences -- 10.5 Machine Generates New Sound-Symbolic Words -- 10.5.1 Method -- 10.5.2 Generating SSWs by Genetic Algorithm -- 10.5.3 Software Implementation -- 10.5.4 Performance Evaluation -- 10.6 Machine Tells Us New Potential Values -- References -- 11 Interactive Sensing and Sensing Interactions -- 11.1 Sensing Living Things and Things to Live With -- 11.1.1 System Outline -- 11.1.2 Area Recognition -- 11.1.3 Activity Recognition -- 11.1.4 Experiment -- 11.1.5 Conclusion -- 11.2 Collecting Human Interest from Interaction ch11SatospsShimokawara2015206 -- 11.2.1 Proposed Category Estimation Method for Chat Robot -- 11.2.2 Experiment -- 11.2.3 Analysis of Category Estimation -- 11.2.4 Summary -- 11.3 Collecting Common Sence from Interaction ch11Aoyagi2018 -- 11.3.1 Research Background -- 11.3.2 An Example of Seasons in a Chat Robot -- 11.3.3 Purpose of This Study -- 11.4 Proposed Method -- 11.4.1 Keywords -- 11.4.2 Template Sentences -- 11.4.3 Recovery Sentences -- 11.5 Experiment -- 11.5.1 The Process of the Experiment -- 11.5.2 Instruction to Subjects -- 11.6 Results and Discussion -- 11.6.1 Users' Responses to the Template Sentences -- 11.6.2 Users' Responses to the Recovery Sentences -- 11.6.3 Additional Experiment -- 11.6.4 Implementation of a System -- 11.6.5 Conclusion -- References -- 12 Simulation-Oriented Data Utilization to Analyze Human Behavior in Urban Traffic Systems -- 12.1 Introduction -- 12.2 Quantifying Value of Traffic System by Forward Analysis -- 12.2.1 Overview of Simulation Model -- 12.2.2 Utilization of Simulation Output Data. |
12.3 Estimating Unobservable Demand by Inverse Analysis -- 12.3.1 Estimation Methodology -- 12.3.2 Numerical Experiments -- 12.3.3 Value of Obtaining Data and Reducing Uncertainty -- 12.4 Conclusion -- References -- 13 Externalization of Unexplored Data with Data Origination: Case Analysis of Person-to-Object Contact Data During COVID-19 Pandemic -- 13.1 Introduction -- 13.2 Data Origination -- 13.3 Support Tools for Externalizing Unexplored Data: TEEDA and Variable Quest -- 13.3.1 TEEDA -- 13.3.2 Variable Quest -- 13.4 Unexplored Data Externalization and Analytical Process -- 13.5 Conclusion -- References -- Index. |
|
|
|
|
|
| |