1. Project 14: Android based Object Detection and Classification: Modeling a Child's Learning of What's Hot and Cold

2. Should this project be considered for the Best Project award? No

3. Should this project be considered for the top 3 project awards? No

4. On a scale of 1 to 10, how would you rate the overall organization/clarity
of the project report? 7

5. On a scale of 1 to 10, how would you rate the overall project idea? 6

6. On a scale of 1 to 10, how would you rate the overall research
contribution of the project idea, methodology and/or results?  6


* Overall, is the project report clear, concise, and well-organized?
Overall, the project report is sufficiently organized and clear. There is a lot materials covered and detailed. The report does an excellent job explaining and clarifying each step in the experimental setup and methodology. The project report flows well between the sections and the language used is concise. 


* How does the project idea and methodology fit within the framework
of Developmental Robotics?
The project idea is very ambitious. Modeling the learning process of a child is quite an undertaking and the project also looks to use the android platform to illustrate this learning process. The methodology of using SOM has been done before, but not on the android. Therefore, this project looks at the feasibility of using the android platform for SOM research. This approach fit within the framework of Developmental Robotic by furthering the tools available for robotic researchers. 


* Describe what you like BEST about the project?
I really like the level of details given about the project. The team does an excellent job planning, analyzing, and organizing the project. The team also gives explanations for different approaches, problems, and solutions as they progress through the project. The visual components do a great job clarifying the methods and final product of the project. Overall, I would consider this project a great success.


* Describe what you like LEAST about the project?
I think the use of the arduino could have been dropped. This would have allowed the team to make further progress in optimizing the android product. I did not really understand the benefits in using the arduino. The project report could be modified to address this. There were a couple misspelling in the report. The team needs to fix those. 


* Do the methods, results and contributions of the final project
correspond to what was presented in the initial project proposal?
The project report acknowledges the changes between the final project and the initial project proposal. This answered many of the methods, results, and contributions expected from the readers. The team does a great job addressing the high level approach of the embodiment principle, the technical limitations, and characteristics of the input images. These are valid changes to consider and helped improve the focus of the project.


* Are there any major details left out with regards to the methods,
algorithms, or experimental design described in the report?
I would have liked more analysis and discussion on extended testing using the final android product. However, I do understand the time and technical constraints. For the Results section, the team should add more content and visual components to confirm that the android platform works. Maybe use simpler images in the platform so that the readers can clearly see the differences between the number of iterations used and the resulting percent organization.


* Do the experimental results reported in the paper demonstrate success?
The experimental results did report success, but I am confused by how the team measure percent organization. There could a section detail what the value means and how that helps illustrate the success of the final product. 


* Do you have any suggestions for improvement and future work?
The project noted substantial learning of the SOM and android development platform. If given more time, I believe the team could have improved the SOM capabilities and improved the GUI. I remembered I had trouble discerning the GUI during the demonstration in class. The team does a great job of recognizing these weaknesses in the report and has identified them for future work.


* How close is the final project report to being publishable as a
conference or journal paper (consider the research papers that were
part of the course reading)? What would it take to get there?
The final project report is somewhat close to publishable. There are some visual components used in the report that needs to be simplified and better explained. There are also some areas in the paper like the arduino that should be dropped given that the project is primarily interested in the android product. This would narrow the focus of the project and allow better organization of the project. 	The presentation of the report is good. I really liked the IEEE two-column format.