Changes between Version 50 and Version 51 of Other/Summer/2023/Features
- Timestamp:
- Jul 20, 2023, 5:43:21 PM (12 months ago)
Legend:
- Unmodified
- Added
- Removed
- Modified
-
Other/Summer/2023/Features
v50 v51 2 2 === Introductions 3 3 4 '''Mayank Barad'''[[BR]]Rising Senior in Computer Engineering and Computer Science4 '''Mayank Barad'''[[BR]]Rising Senior pursuing BS in Computer Engineering and Computer Science 5 5 6 '''Daksh Khetarpaul'''[[BR]]Rising Junior in Computer Engineering6 '''Daksh Khetarpaul'''[[BR]]Rising Junior pursuing BS in Computer Engineering 7 7 8 8 9 '''Katherine Lew'''[[BR]]Rising Sophomore in Finance and Computer Scienc9 '''Katherine Lew'''[[BR]]Rising Sophomore pursuing BS in Finance and Computer Science 10 10 11 11 12 [[span(style=color: #A50000, '''Advisors''')]] - Dr Richard Howard, DrRichard Martin12 [[span(style=color: #A50000, '''Advisors''')]] - Dr. Richard Howard, Dr. Richard Martin 13 13 14 14 === Project Description … … 16 16 Neural networks have a long history of being used for classification, and more recently content generation, Example classifiers including, image classification between dogs and cats, text sentiment classification. Example generative networks include those for human faces, images, and text. Rather than classification or generation, this work explores using networks for feature analysis. Intuitively, features are the high level patterns that distinguish data, such as text and images, into different classes. Our goal is to explore bee motion datasets to qualitatively measure the ease or difficulty of reverse-engineering the features found by the neural networks. 17 17 18 === Week 1 18 === Week 1 Progress 19 19 20 * **Defin ing objectives: ** Neural Networks for Feature Analysis is related to Bee Hive Monitoring. While the Bee Hive Monitoring project seeks to determine whether changes in the earths's magnetic fields due to radio waves are affecting the way that bees behave, our project aims to explore the use of Neural Networks to detect these changes.20 * **Define objectives: ** Neural Networks for Feature Analysis and Hive Monitoring are interrelated. The Hive Monitoring project is based on the hypothesis that changes in the earth's magnetic fields due to radio waves are affecting bee behavior. Their goal is to determine if bees exposed to a magnetic field behave differently than un-exposed bees. Our goal is to explore the use of Neural Networks to detect these changes. 21 21 22 22 How effective are neural networks at detecting minute changes in bee behavior? 23 23 24 * **Set up : ** We set up Github and iLab accounts24 * **Set up software: ** We set up Github and iLab accounts to collaborate and run the machine learning behavioral detection code, respectively. 25 25 26 * **Research : ** We became familiar with neural networks, learning about26 * **Research neural networks: ** We researched neural networks to become familiar with the model. Looked into concepts like __, __, and __. 27 27 28 === Week 2 28 === Week 2 Progress 29 29 30 30 * Visited the beehive to observe the behavior of real bees … … 36 36 [[Image(unnamed.jpg, width=200, height=200)]] First Prototype -> [[Image(jitterbug.mov, width=200, height=200)]] Applying "Power Law" -> [[Image(powerbee2.mov, width=200, height=200)]] 37 37 38 === Week 3 38 === Week 3 Progress 39 39 40 40 * **Randomness Function:**We programmed a function that allows the user to adjust the degree of randomness of synthetic bee motion along a spectrum. 0.0 represents the "bee" moving in a completely random motion, and 1.0 represents the "bee" moving via a distinct non-random pattern like a clockwise circle. … … 48 48 [[Image(Screen Shot 2023-07-19 at 10.44.07 AM.png, width=400, height=125)]] [[Image(Screen Shot 2023-07-19 at 10.46.33 AM.png, width = 200, height = 100)]] 49 49 50 === Week 4/550 === Weeks 4 and 5 Progress 51 51 52 52 * **Validate results:** We discovered that there was a mistake in our training data, so last week's training results were null. There was a bias in the input data, and irrelevant learning happened. … … 56 56 * **Reformat tar files: ** We altered the program to reformat the training data. Instead of combining the frames of the random bee simulator into a video format, we compiled the data into a tar file, which consists of a png, a class, and a metadata file for each frame in the simulation. We will use these tar files as training data for the model. 57 57 58 === Week 6 58 === Week 6 Progress 59 59 60 60 * **Time Varying Features: ** In order to train the model to capture time varying features (and hence motion), we increased the channels while keeping the same kernel size. This works for small movements in the training data.
