Please contact Prof. Mohammed Hamdaqa (mhamdaqa@polymtl.ca) or Prof. Zorhreh Sharafi (zohreh.sharafi@polymtl.ca) for any questions.
| Title | Presenter | Affiliation | |
| P1 | Binary Code Similarity Detection for Obfuscated Java Android Applications | Misheelt Munkhjargal | Concordia University |
| P2 | Experimental Platform for trustworthy Human-Machine Teaming | Laila EL Moujtahid | AI Redefined |
| P3 | Assessment of library documentation quality: A metric-based approach | Afiya Fahmida Sarah | University of Alberta |
| P4 | Prompt-based Learning For Log Level Suggestion | Yi Wen Heng | Concordia University |
| P5 | Deployment Strategies for Edge AI | Jaskirat Singh | Queens University |
| P6 | SLocator: Localizing the Origin of SQL Queries in Database-Backed Web Applications | Wei Liu | Concordia University |
| P7 | On lightweight dynamic batching techniques for avoiding redundant CI practices | Divya Madhav Kamath | Queen’s University |
| P8 | Post-Deployment Model Recycling | Harsh Patel | Queen’s University |
| P9 | A Deep Dive into bug reports with Stack Traces in Production-like scenarios | Lorena Barreto Simedo Pacheco | Concordia University |
| P10 | Streamlining Build System Maintenance: A Recommendation System for Build System Configuration | Shenyu Zheng | Queen’s University |
| P11 | Employing Code Change Information for Enhanced Fault Localization | Md Nakhla Rafi | Concordia University |
| P12 | Planning task executions in distributed machine learning systems | Yu Shi | Queen’s University |
| P13 | Artificial Intelligence for HealthCare in Africa: Emerging Challenges | Gael Kamdem De Teyou | Bright-Medicals |
| P14 | Artificial Intelligence for HealthCare in Africa: Emerging Challenges | Paulina Stevia Nouwou Mindom | Polytechnique Montréal |
| P15 | A Multiplex Network Framework Based Recommendation Systems for Technology Intelligence | Foutse Yuehgoh | Conservatoir National des Arts et Métier (CNAM)/ Devinci Research Center (DVRC) |
| P16 | Understanding Contributors Profiles of Popular ML Libraries | Jiawen Liu | Queen’s University |
| P17 | Co-changed method identification with Learning to Rank | Yiping Jia | Queen’s University |
| P18 | Protecting IoT-based applications using security patterns and Machine Learning-based self-adaptation | Saeid Jamshidi | Polytechnique Montréal |
| P19 | Detection and Evaluation of Bias Inducing Features in Machine learning | Moses Openja | Polytechnique Montréal |
| P20 | Towards Lifelong Learning for Software Analytics Models: Empirical Study on Brown Build and Risk Prediction | Doriane Olewicki | Queen’s University |
| P21 | Vulnet: Towards Improving Vulnerability Management in the Maven Ecosystem | Zeyang Ma | Concordia University |
| P22 | JIT Bug Prediction using Graph-Anonymised Git Graphs | Akshat Malik | Queen’s University |
| P23 | Towards Responsible Design Patterns for Machine Learning Pipelines | Saud Alharbi | Polytechnique Montréal |
| P24 | Mutation Testing of Deep Reinforcement Learning Based on Real Faults | Vahid Majdinasab | Polytechnique Montréal |
| P25 | An Empirical Study on the Characteristics of Code Clone Quality | Chunli Yu | Queen’s University |
| P26 | MLRefactoScanner – Detecting Refactoring-Related Commits in Python-Based Machine Learning Projects: A Machine Learning Assisted Prototype | Shayan Noei | Queen’s University |
| P27 | An Exploratory Study in Detecting CVE Bugs using Clone Detectors | Yinghang Ma | York University |
| P28 | Artificial Intelligence (AI) For Empowering Women Against Violence | Laila Mahmoud Daw Abodinar | Polytechnique Montréal |
| P29 | Techniques for Creating a dataset of Automated Generated Code | Pouya Fathollahzadeh | Queen’s University |
| P30 | Bug Characterization in Machine Learning-based Systems | Mohammadmehdi Morovati | Polytechnique Montréal |
| P31 | Tracing Optimization for Performance Modelling and Regression Detection | Kaveh Shahedi | Polytechnique Montréal |
| P32 | Improving the Effectiveness of Tests Generated by LLMs Using Mutation Testing | Arghavan Moradi Dakhel | Polytechnique Montréal |
| P33 | What Causes Exceptions in Machine Learning Applications? Mining Machine Learning-Related Stack Traces on Stack Overflow | Amin Ghadesi | Polytechnique Montréal |
| P34 | Predicting Trust in Software Engineering Tasks using Machine Learning and Eye Gaze Analysis | Sara Yabesi | Polytechnique Montréal |
| P35 | The Trends and Challenges of Deep Learning Model Reuse: A Case Study of the HuggingFace Community | Mina Taraghi | Polytechnique Montréal |
| P36 | Enhancing Travel Recommendation Systems By Leveraging Personalized Data | Baharan Nouriinanloo | Polytechnique Montréal |
| P37 | Logging Requirement for Auditing Responsible Machine Learning Based Applications | Patrick loic Foalem | Polytechnique Montréal |
| P38 | Artificial Recovering Traceability Links between Release Notes and Related Software Artifacts | Sristy Sumana Nath | University of Saskatchewan |
| P39 | Do External Resources Matter in IR-based Bug Localization? – An Empirical Study | Shamima Yeasmin | University of Saskatchewan |
| P40 | A study of Cross-Language Similar Software Applications development and Maintenance | Kawser Wazed Nafi | University of Saskatchewan |
| P41 | An Empirical Study on the Usage of Automated Machine Learning Tools | Forough Majidi | Polytechnique Montréal |
Abstract: Anomaly detection plays an important role in management of modern large-scale distributed systems. Logs, which record system runtime information, are widely used for anomaly detection. However, Unsupervised anomaly detection algorithms face challenges in addressing complex systems, which generate vast amounts of multivariate time series data. Timely anomaly detection is crucial for managing these systems effectively and minimizing downtime. This proactive approach minimizes system downtime and plays a vital role in incident management for large-scale systems. To address these challenges, a method called Multi-Scale Convolutional Recurrent Encoder-Decoder (MSCRED) has been developed for detecting anomalies in CN PTC system logs. MSCRED leverages the power of multivariate time series data to perform anomaly detection and diagnosis. It creates multi-scale signature matrices that capture different levels of system statuses across various time steps. The method utilizes a convolutional encoder to capture inter-sensor correlations and a Convolutional Long-Short Term Memory (ConvLSTM) network with attention mechanisms to capture temporal patterns.
Abstract
Abstract: Language models such as RoBERTa, CodeBERT, and GraphCodeBERT have gotten much attention in the past three years for various Software Engineering tasks. Though these models are proven to have state-of-the-art performance for many SE tasks, such as code summarization, they often require to be fully fine-tuned for the downstream task. Is there a better way for fine-tuning these models that require training fewer parameters? Can we impose new information on the current models without pre-training them again? How do these models perform for different programming languages, especially low-resource ones with less training data available? How can we use the knowledge learned from other programming languages to improve the performance of low-resource languages? This talk will review a series of experiments and our contributions to answering these questions.
