Awareness-Based Recommendation Toward a New Preference

2015 ◽

pp. 219-241

Author(s):

Tomohiro Yamaguchi ◽

Takuma Nishimura ◽

Keiki Takadama

Keyword(s):

Interaction Design ◽

Design Research ◽

Learning System ◽

Human Intelligence ◽

Human Interface ◽

True Preference ◽

Heavy Users ◽

And Training ◽

And Robotics ◽

The Way

In mechatronics and robotics, one of the important issues is to design human interface. There are two issues on interaction design research. One is the way to education and training to adapt humans for operating the robots or interaction systems. Another one is the way to make interaction design adaptable for humans. This chapter research at the latter issue. This chapter describes the interactive learning system to assist positive change in the preference of a human toward the true preference; then evaluation of the awareness effect is discussed. The system behaves passively to reflect the human intelligence by visualizing the traces of his/her behaviors. Experimental results showed that subjects are divided into two groups, heavy users and light users, and that there are different effects between them under the same visualizing condition. They also showed that the system improves the efficiency for deciding the most preferred plan for both heavy users and light users.

Download Full-text

Awareness Based Recommendation

Human Performance Technology ◽

10.4018/978-1-5225-8356-1.ch010 ◽

2019 ◽

pp. 167-186

Author(s):

Tomohiro Yamaguchi ◽

Takuma Nishimura ◽

Keiki Takadama

Keyword(s):

Artificial Intelligence ◽

Interaction Design ◽

Interactive Learning ◽

Learning System ◽

Experimental Results ◽

Human Intelligence ◽

Human Interface ◽

True Preference ◽

Heavy Users ◽

And Robotics

In Artificial Intelligence and Robotics, one of the important issues is to design Human interface. There are two issues, one is the machine-centered interaction design to adapt humans for operating the robots or systems. Another one is the human-centered interaction design to make it adaptable for humans. This research aims at latter issue. This paper presents the interactive learning system to assist positive change in the preference of a human toward the true preference, then evaluation of the awareness effect is discussed. The system behaves passively to reflect the human intelligence by visualizing the traces of his/her behaviors. Experimental results showed that subjects are divided into two groups, heavy users and light users, and that there are different effects between them under the same visualizing condition. They also showed that the authors' system improves the efficiency for deciding the most preferred plan for both heavy users and light users.

Download Full-text

Awareness Based Recommendation

International Journal of Robotics Applications and Technologies ◽

10.4018/ijrat.2016010105 ◽

2016 ◽

Vol 4 (1) ◽

pp. 83-99

Author(s):

Tomohiro Yamaguchi ◽

Takuma Nishimura ◽

Keiki Takadama

Keyword(s):

Artificial Intelligence ◽

Interaction Design ◽

Interactive Learning ◽

Learning System ◽

Experimental Results ◽

Human Intelligence ◽

Human Interface ◽

True Preference ◽

Heavy Users ◽

And Robotics

In Artificial Intelligence and Robotics, one of the important issues is to design Human interface. There are two issues, one is the machine-centered interaction design to adapt humans for operating the robots or systems. Another one is the human-centered interaction design to make it adaptable for humans. This research aims at latter issue. This paper presents the interactive learning system to assist positive change in the preference of a human toward the true preference, then evaluation of the awareness effect is discussed. The system behaves passively to reflect the human intelligence by visualizing the traces of his/her behaviors. Experimental results showed that subjects are divided into two groups, heavy users and light users, and that there are different effects between them under the same visualizing condition. They also showed that the authors' system improves the efficiency for deciding the most preferred plan for both heavy users and light users.

Download Full-text

Awareness-Based Recommendation by Passively Interactive Learning

Novel Design and Applications of Robotics Technologies - Advances in Computational Intelligence and Robotics ◽

10.4018/978-1-5225-5276-5.ch009 ◽

2018 ◽

pp. 247-275

Author(s):

Tomohiro Yamaguchi ◽

Takuma Nishimura ◽

Shota Nagahama ◽

Keiki Takadama

Keyword(s):

Interaction Design ◽

Interactive Learning ◽

Learning System ◽

Future Research ◽

Research Directions ◽

Human Interface ◽

True Preference ◽

Heavy Users ◽

Future Research Directions ◽

And Robotics

In artificial intelligence and robotics, one of the important issues is to design human interface. There are two issues: One is the machine-centered interaction design. Another one is the human-centered interaction design. This research aims at the latter issue. This chapter presents the interactive learning system to assist positive change in the preference of a human toward the true preference. Then evaluation of the awareness effect is discussed. The system behaves passively to reflect the human intelligence by visualizing the traces of his/her behaviors. Experimental results showed that subjects are divided into two groups, heavy users and light users, and that there are different effects between them under the same visualizing condition. They also showed that the authors' system improves the efficiency for deciding the most preferred plan for both heavy users and light users. As future research directions, a probabilistic event and its basic recommendation way are discussed.

Download Full-text

Awareness-Based Recommendation

Engineering Creative Design in Robotics and Mechatronics - Advances in Mechatronics and Mechanical Engineering ◽

10.4018/978-1-4666-4225-6.ch006 ◽

2013 ◽

pp. 86-100

Author(s):

Tomohiro Yamaguchi ◽

Takuma Nishimura ◽

Keiki Takadama

Keyword(s):

Reinforcement Learning ◽

Interaction Design ◽

Interactive Learning ◽

Robot Learning ◽

Learning System ◽

Experimental Results ◽

Interactive System ◽

Human Intelligence ◽

True Preference ◽

Heavy Users

This chapter describes the interactive learning system to assist positive change in the preference of a human toward the true preference. First, an introduction to interactive reinforcement learning with human in robot learning is given; then, the need to estimate the human’s preference and to consider its changes by interactive learning system is described. Second, requirements for interactive system as being human adaptive and friendly are discussed. Then, the passive interaction design of the system to assist the awareness for a human is proposed. The system behaves passively to reflect the human intelligence by visualizing the traces of his/her behaviors. Experimental results show that subjects are divided into two groups, heavy users and light users, and that there are different effects between them under the same visualizing condition. They also show that the system improves the efficiency for deciding the most preferred plan for both heavy users and light users.

Download Full-text

Judges

10.1093/oso/9780198790884.003.0006 ◽

2018 ◽

Author(s):

Eva Steiner

Keyword(s):

Civil Servants ◽

High Ranking ◽

Administrative Courts ◽

And Training ◽

The Way

This chapter looks briefly at the way judges are recruited in France and how and to what degree this is reflected in their way of reasoning and style of argument. It outlines the requirements for admission to the profession of being a judge in France and the methods adopted for training them. This outline is confined to professional judges, but it should be noted that, in France, commercial and employment cases are adjudicated at the first instance by lay judges. Further, judges in the administrative courts are not included in the teaching and training processes provided for by the École Nationale de la Magistrature (ENM). Administrative judges are recruited from the pool of high-ranking civil servants, many of them trained at the prestigious ENA (École Nationale d'Administration).

Download Full-text

Organizing and Managing Data Analytics Teams for Procurement

The Oxford Handbook of Supply Chain Management ◽

10.1093/oxfordhb/9780190066727.013.2 ◽

2020 ◽

Author(s):

Benjamin Shao ◽

Robert D. St. Louis

Keyword(s):

Best Practices ◽

Business Strategy ◽

Data Analytics ◽

Team Members ◽

Procurement Process ◽

Using Data ◽

And Training ◽

Different Levels ◽

The Way

Many companies are forming data analytics teams to put data to work. To enhance procurement practices, chief procurement officers (CPOs) must work effectively with data analytics teams, from hiring and training to managing and utilizing team members. This chapter presents the findings of a study on how CPOs use data analytics teams to support the procurement process. Surveys and interviews indicate companies are exhibiting different levels of maturity in using data analytics, but both the goal of CPOs (i.e., improving performance to support the business strategy) and the way to interact with data analytics teams for achieving that goal are common across companies. However, as data become more reliably available and technologies become more intelligently embedded, the best practices of organizing and managing data analytics teams for procurement will need to be constantly updated.

Download Full-text

Testing the Suitability of Automated Machine Learning for Weeds Identification

AI ◽

10.3390/ai2010004 ◽

2021 ◽

Vol 2 (1) ◽

pp. 34-47

Author(s):

Borja Espejo-Garcia ◽

Ioannis Malounas ◽

Eleanna Vali ◽

Spyros Fountas

Keyword(s):

Machine Learning ◽

Plant Protection ◽

Crop Protection ◽

Identification Problem ◽

Learning System ◽

Classifier Ensembles ◽

Automated Machine Learning ◽

A New Technique ◽

Plant Seedlings ◽

And Training

In the past years, several machine-learning-based techniques have arisen for providing effective crop protection. For instance, deep neural networks have been used to identify different types of weeds under different real-world conditions. However, these techniques usually require extensive involvement of experts working iteratively in the development of the most suitable machine learning system. To support this task and save resources, a new technique called Automated Machine Learning has started being studied. In this work, a complete open-source Automated Machine Learning system was evaluated with two different datasets, (i) The Early Crop Weeds dataset and (ii) the Plant Seedlings dataset, covering the weeds identification problem. Different configurations, such as the use of plant segmentation, the use of classifier ensembles instead of Softmax and training with noisy data, have been compared. The results showed promising performances of 93.8% and 90.74% F1 score depending on the dataset used. These performances were aligned with other related works in AutoML, but they are far from machine-learning-based systems manually fine-tuned by human experts. From these results, it can be concluded that finding a balance between manual expert work and Automated Machine Learning will be an interesting path to work in order to increase the efficiency in plant protection.

Download Full-text