Differences

This shows you the differences between two versions of the page.

--- projects [2020/08/01 17:00] – aan
+++ projects [2020/08/17 17:27] (current) – aan
@@ Line 4: / Line 4: @@
 Below is a list of 4080/4088 projects proposed by faculty members. More projects may be added once they come in (normally in August). Please contact the supervisor directly you are in interested in a project. You can also contact faculty members individually to discuss possible projects. Click [[http://eecs.lassonde.yorku.ca/community/faculty-members/|here]] to see a list of faculty members, their research areas and their contact information.
+====== Characterizing, Understanding, and Detecting Software Bugs in Machine Learning Frameworks ======
+**Course:** EECS4080
+**Supervisor:** Song Wang
+**Contact:** <wangsong@yorku.ca>
+Today, machine learning and its applications has been integrated into every part of our society. With the development and evolution of information technologies such as smartphones, self-driving cars, and robotics, the dependence of our society on machine learning systems continues to grow, which makes the impact and cost of bugs in these intelligent systems increase dramatically. Building reliable and secure machine learning systems has become an increasingly critical challenge for software developers. Thus, characterizing and understanding the root cause of software bugs in ML frameworks is critical to detecting and repairing buggy behavior.
+This project will first conduct an empirical study to analyze and summarize unique characteristics of software bugs collected from four typical ML frameworks (PyTorch, TensorFlow, CNTK, and Theano). Based on the findings from the empirical study, we will further propose actionable guidelines for designing and exploring new software bug detection approaches to find new bugs on machine learning frameworks and their applications.
+**Required skills:** General EECS4313 and EECS3311 prerequisites;
+**Recommended skills:** Solid programming skills with Python and Java.
+====== Image Processing for Social Coding ======
+**Course:** EECS4088 (Capstone Project)
+**Supervisor:** Maleknaz Nayebi
+**Contact:** <mnayebi@yorku.ca>
+Software developers are increasingly sharing images in social coding environments such as stack overflow, GitHub, Bugzilla, and Slack. This growth is parallel to the general growth of in visual interactions in general purpose online social networks like Instagram, Facebook, and Pinterest. Developers' shared images are meaningful and provide complementary information compared to their associated text. These images extensively help in understanding the change requests, questions, or the responses submitted. Relying on these observations, we are working on automatically processing these images by first forming a database similar to ImageNet for software domain and then applying the text detection object detection and automated captioning techniques on these data. We will work with software teams and software developers to evaluate the usefulness of our methods and results. The project includes:
+(i) Forming and structuring a dataset of crowd labelled images for software related images,
+(ii) Mining content and objects within developers’ shared images,
+(iii) Automatic captioning the images to describe the content.
+**Required skills:** Good knowledge of Python, Good knowledge on Machine learning, Good knowledge of image processing, Ability to work independently, Ability to communicate clearly.
+====== Release Management for Mobile Apps ======
+**Course:** EECS4080
+**Supervisor:** Maleknaz Nayebi
+**Contact:** <mnayebi@yorku.ca>
+Release planning problem is addressing the question of what functionality should be included in any version and when that version should be released to different segments of users. Proper decision about the functionality of evolving software product releases is critical for the success or failure of a product.  The rise in popularity of mobile devices has led to a parallel growth in the size of the app store market, intriguing several research studies and commercial platforms on mining app stores. App store reviews are used to analyze different aspects of app development and evolution. This led into the concept of user driven release management. This project includes:
+(i) Evaluating the applicability of four state of the art release management tools for mobile apps,
+(ii) Testing and enhancing the prototype tools for these four release management techniques.
+**Required skills:** Good knowledge of Python, Ability to manage Git and Jupiter Notebooks, Good knowledge on Machine learning, Ability to work independently, Ability to communicate clearly.
 ====== Estimating emotional state from a speech audio signal ======
+**Course:** EECS4080/4088
 **Supervisor:** Michael Jenkin
@@ Line 21: / Line 71: @@
 ====== Automatic classification of Eurasian Water-Milfoil from sonar and visual data ======
+**Course:** EECS4080/4088
 **Supervisor:** Michael Jenkin
@@ Line 36: / Line 88: @@
 ====== A framework for VR-based vestibular assessment tools ======
+**Course:** EECS4080/4088
 **Supervisor:** Michael Jenkin