Pitch 1: Reduce the encounter of local minima in heuristic search space. In the heuristic search space of heuristic algorithms, there are areas where the nodes appear to be closer to the goal state, but when the algorithm encounters these areas, they actually wasted more resources to reach the goal. These areas are called local minima. Local minima tends to arise more when using distance to go as the heuristic value instead of cost to go, which is an aspect that this project plans to explore. Avoiding local minima and understanding the behavior can help improve the performance of heuristic search algorithms. Overall, this project will explore the problem of local minima with beam search. 

Risk: There is limited information on this topic and a lot of knowledge gaps that will need to be filled. 

Pitch 2: Facial expression recognition: classify facial expression using machine learning. Problem: help people in communication, analyze human’s emotion, help with the development of AI in supporting humans during their daily life. Dataset: CK+ : 48×48 pixels images in grayscale format; face cropped; emotions includes anger (45 samples), disgust (59 samples), fear (25 samples), happiness (69 samples), sadness (28 samples), surprise (83 samples), neutral (593 samples), contempt (18 samples). Tufts Face Database: multi-modal face image images with more than 100,000 images, 74 females and 38 males from different age groups. 

Risk: Finding a suitable machine learning algorithm, process image data.

Pitch 3: Sentiment analysis of online food review. When people buy products online, the one thing that they tend to look closely at are the reviews of the product. Having good reviews and understanding the needs of the customers through the review can help the business grow tremendously. A review usually comes in two parts: the rating and the reviews. Users, a lot of the time, mistakenly choose the wrong rating for the products, so the reviews are more reliable in most situations. This project aims to perform sentiment analysis on the reviews dataset, so it provides more accurate feedback on the products. Another aspect that this project can develop toward is that it can perform analysis on the negative languages on the recent reviews to let the businesses know what they should focus on improving. Amazon Fine Food Reviews dataset, which contains data over a 10 year period (1999 to 2012). Another plan to replace this dataset is using DoorDashAPI to collect reviews from the restaurants on DoorDash.

Risk: dataset is not recent and will keep looking for a more recent dataset.