Structural development defects essentially refer to code structure that violates object-oriented design principles. They make program maintenance challenging and deteriorate software quality over time. Various detecti...Structural development defects essentially refer to code structure that violates object-oriented design principles. They make program maintenance challenging and deteriorate software quality over time. Various detection approaches, ranging from traditional heuristic algorithms to machine learning methods, are used to identify these defects. Ensemble learning methods have strengthened the detection of these defects. However, existing approaches do not simultaneously exploit the capabilities of extracting relevant features from pre-trained models and the performance of neural networks for the classification task. Therefore, our goal has been to design a model that combines a pre-trained model to extract relevant features from code excerpts through transfer learning and a bagging method with a base estimator, a dense neural network, for defect classification. To achieve this, we composed multiple samples of the same size with replacements from the imbalanced dataset MLCQ1. For all the samples, we used the CodeT5-small variant to extract features and trained a bagging method with the neural network Roberta Classification Head to classify defects based on these features. We then compared this model to RandomForest, one of the ensemble methods that yields good results. Our experiments showed that the number of base estimators to use for bagging depends on the defect to be detected. Next, we observed that it was not necessary to use a data balancing technique with our model when the imbalance rate was 23%. Finally, for blob detection, RandomForest had a median MCC value of 0.36 compared to 0.12 for our method. However, our method was predominant in Long Method detection with a median MCC value of 0.53 compared to 0.42 for RandomForest. These results suggest that the performance of ensemble methods in detecting structural development defects is dependent on specific defects.展开更多
The dissertation studies the architecture of broadband intelligent network (BIN) and implementation of video conference based on ATM network and of multicast routing problem on video conference using BIN under the aid...The dissertation studies the architecture of broadband intelligent network (BIN) and implementation of video conference based on ATM network and of multicast routing problem on video conference using BIN under the aid of the important task Study of IN and B ISDN Integration (69896244) sponsored by National Natural Science Fund. A lot of points of view and solutions are present. The main contributions in the dissertation are as follows:\; (1) Design the new architecture of BIN and improve the architecture of BIN proposed by ITU T. It is easy to set up the connections of video conference using the new architecture of BIN.\; (2) Present the detailed scheme that BIN controls and implements video conference without specialized resource function, study the scheme of all the media on video conference transmitted and switched under the control of BIN, and discuss how to implement point to multipoint communications using BIN.\; (3) First present the scheme of implementing multicast routing algorithms on video conference using BIN.\; (4) Explicitly introduce a series of concepts including neighboring node, neighboring node set, neighboring edge, then propose an Adjustable Dynamic Multicast (ADM) routing algorithm which is suitable for video conference, analyze its performances, and prove the algorithm is appropriate and feasible.\; (5) Develop a degree constrained dynamic multicast (DADM) routing algorithm which can find less cost multicast routing tree. The results of simulation and experiments confirm that DADM algorithm can find the less cost multicast tree. Finally, analyze the relation between the size of degree constrained and value of multicast tree cost.\; (6) Present a delay constrained dynamic multicast routing algorithm suitable for video conference characteristic, and advise a series of schemes reducing the delay of transmitting all the media on videoconference.\; (7) First propose implementing the reliable multicast routing transport protocol using BIN, thereby ACK implosion problem can be solved. The protocol only requires finite memory and is scalable.展开更多
文摘Structural development defects essentially refer to code structure that violates object-oriented design principles. They make program maintenance challenging and deteriorate software quality over time. Various detection approaches, ranging from traditional heuristic algorithms to machine learning methods, are used to identify these defects. Ensemble learning methods have strengthened the detection of these defects. However, existing approaches do not simultaneously exploit the capabilities of extracting relevant features from pre-trained models and the performance of neural networks for the classification task. Therefore, our goal has been to design a model that combines a pre-trained model to extract relevant features from code excerpts through transfer learning and a bagging method with a base estimator, a dense neural network, for defect classification. To achieve this, we composed multiple samples of the same size with replacements from the imbalanced dataset MLCQ1. For all the samples, we used the CodeT5-small variant to extract features and trained a bagging method with the neural network Roberta Classification Head to classify defects based on these features. We then compared this model to RandomForest, one of the ensemble methods that yields good results. Our experiments showed that the number of base estimators to use for bagging depends on the defect to be detected. Next, we observed that it was not necessary to use a data balancing technique with our model when the imbalance rate was 23%. Finally, for blob detection, RandomForest had a median MCC value of 0.36 compared to 0.12 for our method. However, our method was predominant in Long Method detection with a median MCC value of 0.53 compared to 0.42 for RandomForest. These results suggest that the performance of ensemble methods in detecting structural development defects is dependent on specific defects.
文摘The dissertation studies the architecture of broadband intelligent network (BIN) and implementation of video conference based on ATM network and of multicast routing problem on video conference using BIN under the aid of the important task Study of IN and B ISDN Integration (69896244) sponsored by National Natural Science Fund. A lot of points of view and solutions are present. The main contributions in the dissertation are as follows:\; (1) Design the new architecture of BIN and improve the architecture of BIN proposed by ITU T. It is easy to set up the connections of video conference using the new architecture of BIN.\; (2) Present the detailed scheme that BIN controls and implements video conference without specialized resource function, study the scheme of all the media on video conference transmitted and switched under the control of BIN, and discuss how to implement point to multipoint communications using BIN.\; (3) First present the scheme of implementing multicast routing algorithms on video conference using BIN.\; (4) Explicitly introduce a series of concepts including neighboring node, neighboring node set, neighboring edge, then propose an Adjustable Dynamic Multicast (ADM) routing algorithm which is suitable for video conference, analyze its performances, and prove the algorithm is appropriate and feasible.\; (5) Develop a degree constrained dynamic multicast (DADM) routing algorithm which can find less cost multicast routing tree. The results of simulation and experiments confirm that DADM algorithm can find the less cost multicast tree. Finally, analyze the relation between the size of degree constrained and value of multicast tree cost.\; (6) Present a delay constrained dynamic multicast routing algorithm suitable for video conference characteristic, and advise a series of schemes reducing the delay of transmitting all the media on videoconference.\; (7) First propose implementing the reliable multicast routing transport protocol using BIN, thereby ACK implosion problem can be solved. The protocol only requires finite memory and is scalable.
