sushantkumar007007
Assistant Professor at Faculty of Science and Engineering, University of Groningen, Netherlands. Former Postdoc researcher Chalmers | University of Gothenburg
University of Groningen, Netherlands. Groningen, Netherlands
Pinned Repositories
BCV-Predictor
BCV-Predictor: A bug count vector predictor of a successive version of the software system
DBDNN-Estimator
DBDNN-Estimator: A cross-project number of faults estimation technique
Design-Pattern-Recognition-using-Large-Language-Models-
This repository is the replication package for a study about design pattern recognition using large language models (LLMs).
DNNAttention
DNNAttention: A Deep Neural Network and Attention based architecture forCross Project Defect Number Prediction
Input-Prioritization-for-DL-systems
This work compares test input prioritization techniques of different types in terms of their effectiveness and efficiency. In particular, we consider surprise adequacy, autoencoder- based, and similarity-based input prioritization approaches in the example of testing a DL image classification algorithm applied on MNIST, Fashion-MNIST, CIFAR-10, and STL-10 datasets. We use a modified APFD (Average Percentage of Fault Detected) as the test input prioritization performance measure to operationalize the effectiveness.
Just-In-Time-defect-prediction
Just-In-Time defect prediction using deep learning in cross-project settings.
mosesdecoder
Moses, the machine translation system
SDC-Estimator-An-Effectual-Software-Defect-Count-Estimation-Technique
This is s prediction model to predict number of bugs in the new software system. We utilized Long and Short Term Memory (LSTM) along with Attention layer architecture in our proposed model. We used seven software projects and their existing versions from the PROMISE repository.
search-rug.github.io
SEARCH group website
TransDPR-Design-Pattern-Recognition-Using-Programming-Language-Models
Design Pattern Recognition methods have limitations, such as the reliance on semantic information, limited recognition of novel or modified pattern versions, and other factors. We present an introductory DPR technique by using a Programming Language Model called TransDPR.
sushantkumar007007's Repositories
sushantkumar007007/DNNAttention
DNNAttention: A Deep Neural Network and Attention based architecture forCross Project Defect Number Prediction
sushantkumar007007/SDC-Estimator-An-Effectual-Software-Defect-Count-Estimation-Technique
This is s prediction model to predict number of bugs in the new software system. We utilized Long and Short Term Memory (LSTM) along with Attention layer architecture in our proposed model. We used seven software projects and their existing versions from the PROMISE repository.
sushantkumar007007/BCV-Predictor
BCV-Predictor: A bug count vector predictor of a successive version of the software system
sushantkumar007007/DBDNN-Estimator
DBDNN-Estimator: A cross-project number of faults estimation technique
sushantkumar007007/Design-Pattern-Recognition-using-Large-Language-Models-
This repository is the replication package for a study about design pattern recognition using large language models (LLMs).
sushantkumar007007/Input-Prioritization-for-DL-systems
This work compares test input prioritization techniques of different types in terms of their effectiveness and efficiency. In particular, we consider surprise adequacy, autoencoder- based, and similarity-based input prioritization approaches in the example of testing a DL image classification algorithm applied on MNIST, Fashion-MNIST, CIFAR-10, and STL-10 datasets. We use a modified APFD (Average Percentage of Fault Detected) as the test input prioritization performance measure to operationalize the effectiveness.
sushantkumar007007/Just-In-Time-defect-prediction
Just-In-Time defect prediction using deep learning in cross-project settings.
sushantkumar007007/mosesdecoder
Moses, the machine translation system
sushantkumar007007/TransDPR-Design-Pattern-Recognition-Using-Programming-Language-Models
Design Pattern Recognition methods have limitations, such as the reliance on semantic information, limited recognition of novel or modified pattern versions, and other factors. We present an introductory DPR technique by using a Programming Language Model called TransDPR.
sushantkumar007007/DS-Generator-A-Novel-Deep-Learning-Architecture-to-Generate-Data-of-upcoming-Sequence
This repository contains the implementation of DS-Generator, a novel deep learning architecture designed to generate the next data sequence using its previous sequences. Our method is demonstrated on eight PROMISE repository projects and aims to reduce software testing and development costs by predicting future sequences of bug & software metrics.