Source Projects Research Articles

Balanced Adversarial Tight Matching for Cross-Project Defect Prediction

Cross-project defect prediction (CPDP) is an attractive research area in software testing. It identifies defects in projects with limited labeled data (target projects) by utilizing predictive models from data-rich projects (source projects). Existing CPDP methods based on transfer learning mainly rely on the assumption of a unimodal distribution and consider the case where the feature distribution has one obvious peak. However, in actual situations, the feature distribution of project samples often exhibits multiple peaks that cannot be ignored. It manifests as a multimodal distribution, making it challenging to align distributions between different projects. To address this issue, we propose a balanced adversarial tight-matching model for CPDP. Specifically, this method employs multilinear conditioning to obtain the cross-covariance of both features and classifier predictions, capturing the multimodal distribution of the feature. When reducing the captured multimodal distribution differences, pseudo-labels are needed, but pseudo-labels have uncertainty. Therefore, we additionally add an auxiliary classifier and attempt to generate pseudo-labels using a pseudo-label strategy with less uncertainty. Finally, the feature generator and two classifiers undergo adversarial training to align the multimodal distributions of different projects. This method outperforms the state-of-the-art CPDP model used on the benchmark dataset.

Identifying good practices for detecting inter-regional linear functional connectivity from EEG

Aggregating voxel-level statistical dependencies between multivariate time series is an important intermediate step when characterising functional connectivity (FC) between larger brain regions. However, there are numerous ways in which voxel-level data can be aggregated into inter-regional FC, and the advantages of each of these approaches are currently unclear.In this study we generate ground-truth data and compare the performances of various pipelines that estimate directed and undirected linear phase-to-phase FC between regions. We test the ability of several existing and novel FC analysis pipelines to identify the true regions within which connectivity was simulated. We test various inverse modelling algorithms, strategies to aggregate time series within regions, and connectivity metrics. Furthermore, we investigate the influence of the number of interactions, the signal-to-noise ratio, the noise mix, the interaction time delay, and the number of active sources per region on the ability of detecting phase-to-phase FC.Throughout all simulated scenarios, lowest performance is obtained with pipelines involving the absolute value of coherency. Further, the combination of dynamic imaging of coherent sources (DICS) beamforming with directed FC metrics that aggregate information across multiple frequencies leads to unsatisfactory results. Pipelines that show promising results with our simulated pseudo-EEG data involve the following steps: (1) Source projection using the linearly-constrained minimum variance (LCMV) beamformer. (2) Principal component analysis (PCA) using the same fixed number of components within every region. (3) Calculation of the multivariate interaction measure (MIM) for every region pair to assess undirected phase-to-phase FC, or calculation of time-reversed Granger Causality (TRGC) to assess directed phase-to-phase FC. We formulate recommendations based on these results that may increase the validity of future experimental connectivity studies.We further introduce the free ROIconnect plugin for the EEGLAB toolbox that includes the recommended methods and pipelines that are presented here. We show an exemplary application of the best performing pipeline to the analysis of EEG data recorded during motor imagery.

Multi‐task deep neural networks for just‐in‐time software defect prediction on mobile apps

SummaryWith the development of smartphones, mobile applications play an irreplaceable role in our daily life, which characteristics often commit code changes to meet new requirements. This characteristic can introduce defects into the software. To provide immediate feedback to developers, previous researchers began to focus on just‐in‐time (JIT) software defect prediction techniques. JIT defect prediction aims to determine whether code commits will introduce defects into the software. It contains two scenarios, within‐project JIT defect prediction and cross‐project JIT defect prediction. Regardless of whether within‐project JIT defect prediction or cross‐project JIT defect prediction all need to have enough labeled data (within‐project JIT defect prediction assumes that have plenty of labeled data from the same project, while cross‐project JIT defect prediction assumes that have sufficient labeled data from source projects). However, in practice, both the source and target projects may only have limited labeled data. We propose the MTL‐DNN method based on multi‐task learning to solve this question. This method contains the data preprocessing layer, input layer, shared layers, task‐specific layers, and output layer. Where the common features of multiple related tasks are learned by sharing layers, and the unique features of each task are learned by the task‐specific layers. For verifying the effectiveness of the MTL‐DNN approach, we evaluate our method on 15 Android mobile apps. The experimental results show that our method significantly outperforms the state‐of‐the‐art single‐task deep learning and classical machine learning methods. This result shows that the MTL‐DNN method can effectively solve the problem of insufficient labeled training data for source and target projects.

Candidate project selection in cross project defect prediction using hybrid method

Cross Project Defect Prediction (CPDP) is a process that develops a defect prediction model on source projects and then applies the same model to the target project. Day by day, new software projects are being developed, so selecting an appropriate training project from existing projects and from new upcoming projects, to train a predictor model is a challenging task in CPDP. In the present study, we have proposed a hybrid selection method to select a candidate project from existing projects and a probabilistic method to select a candidate project from new projects. The proposed hybrid method is a weighted combination of the Collaborative filtering (CF) method and the Content Based (CB) method. The probabilistic method is based on a Naïve Bayes classifier and is used to predict the relation between the target project and the new target project. In the CF method, a usability score is generated for each project by making use of classification techniques, and the CB method calculates the matching score of candidate projects by using the K-dimensional tree. Finally, both the methods are combined by parallelized hybridization design, and weights for the proposed method are estimated with an empirical bootstrapping method. The score generated by the proposed hybrid technique is then used to identify the most suitable candidate project for the new project. The experimental results show that the suggestion list of the best three candidate projects is consistent when employing different classifiers. The recommendation performance is evaluated in terms of F-score and Mean Average Precision (MAP), and the proposed method has shown improved performance as compared to the existing methods in both terms.

Performance Evaluation of Convolutional Neural Network for Multi-Class in Cross Project Defect Prediction

Cross-project defect prediction (CPDP) is a practical approach for finding software defects in projects which have incomplete or fewer data. Improvements to the defect prediction accuracy of CPDP—such as the PROMISE repository, the correct classification of the source data, removing the noise, reducing the distribution gap, and balancing the output classes—are an ongoing challenge, as is the selection of an optimal feature set. This research paper aims to achieve a higher defect prediction accuracy for multi-class CPDP by selecting an optimal feature set through XGBoost combined with an automatic feature extraction using a convolutional neural network (CNN). This research type is explanatory, and this research method is controlled experimentation, for which the independent variable prediction accuracy was dependent upon two variables, XGBoost and CNN. The Softmax layer was added to the output layers of the CNN classifier to classify the output into multiple classes. In our experimentation with CPDP, we selected all 28 versions of the multi-class, in which 11 versions were selected as the source projects, against which we predicted 28 target versions with an average AUC of 75.57%. We validated this research paper’s results through the Wilcoxon test. Therefore, after removing the noise, class imbalances, and the data distribution gap, and treating the PROMISE dataset as multi-class, the optimal features selected through XGBoost and classified through the CNN can substantially increase the prediction accuracy in CPDP as evident from our exploratory data analysis (EDA).

A method for identifying references between projects in GitHub

• Extract links on issues, pull requests, and commits using patterns URL, Num and SHA. • Identify the change of project names and delete references between the same project. • In comparison with previous works, our method IREL identifies many more references. In open source software platforms, software projects do not usually develop in isolation, and they depend on each other and develop together. It is important to identify references between projects in software development activities, which may help projects identify cross-project bugs or attract new contributors from related projects. In this paper, we propose a method IREL to I dentify R eferences between projects by E xtracting L inks. We first extract links from descriptions and comments on issues, pull requests, and commits with three matching patterns. Then we identify changes in project names and replace the original project names with their new project names. Finally, we identify references between projects by selecting links with different source projects and target projects. We evaluate the performance based on datasets with 20,347,228 projects. Our method IREL obtains 934,322 references, 26.461 times as many as the method Reference Coupling and 16.483 times as many as the method Issue Units. Project PageRank scores based on references identified by our method IREL are more correlated with the number of stars of projects. Our method supports researchers to identify references better.

Cross-Project Software Refactoring Prediction Using Optimized Deep Learning Neural Network With the Aid of Attribute Selection

Cross-project refactoring prediction is prominent research that comprises model training from one project database and testing it for a database under a separate project. While performing the refactoring process on the cross project, software programs want to be restructured by modifying or adding the source code. However, recognizing a piece of code for predicting refactoring purposes is remained to be actual challenge for software designers. To date the entire refactoring procedure is highly dependent on the skills and software inventers. In this manuscript, a deep learning model is utilized to introduce a predictive model for refactoring to highlight classes that need to be refactored. Specifically, the deep learning technique is utilized along with the proposed attribute selection phases to predict refactoring at the class level. The planned optimized deep learning-based method for cross-project refactoring prediction is experimentally conducted on open- source project and accuracy found as 0.9648 as comparison to other mentioned state of the art.

Cross-Project Defect Prediction Based on Two-Phase Feature Importance Amplification.

As the typical application of computational intelligence in software engineering, cross-project defect prediction (CPDP) uses labeled data from other projects (source projects) for building models to predict the defects in the current projects (target projects), helping testers quickly locate the defective modules. But class imbalance and different data distribution among projects make CPDP a challenging topic. To address the above two problems, we propose a two-phase feature importance amplification (TFIA) CPDP model in this paper which can solve these two problems from domain adaptation phase and classification phase. In the domain adaptation phase, the differences in data distribution among projects are reduced by filtering both source and target projects, and the correlation-based feature selection with greedy best-first search amplifies the importance of features with strong feature-class correlation. In the classification phase, Random Forest works as the classifier to further amplify the importance of highly correlated features and establish a model which is sensitive to highly correlated features. We conducted both ablation experiments and comparison experiments on the widely used AEEEM database. Experimental results show that TFIA can yield significant improvement on CPDP. And the performance of TFIA CPDP model in all experiments is stable and efficient, which lays a solid foundation for its further application in practical engineering.

An Empirical Study of Training Data Selection Methods for Ranking-Oriented Cross-Project Defect Prediction.

Ranking-oriented cross-project defect prediction (ROCPDP), which ranks software modules of a new target industrial project based on the predicted defect number or density, has been suggested in the literature. A major concern of ROCPDP is the distribution difference between the source project (aka. within-project) data and target project (aka. cross-project) data, which evidently degrades prediction performance. To investigate the impacts of training data selection methods on the performances of ROCPDP models, we examined the practical effects of nine training data selection methods, including a global filter, which does not filter out any cross-project data. Additionally, the prediction performances of ROCPDP models trained on the filtered cross-project data using the training data selection methods were compared with those of ranking-oriented within-project defect prediction (ROWPDP) models trained on sufficient and limited within-project data. Eleven available defect datasets from the industrial projects were considered and evaluated using two ranking performance measures, i.e., FPA and Norm(Popt). The results showed no statistically significant differences among these nine training data selection methods in terms of FPA and Norm(Popt). The performances of ROCPDP models trained on filtered cross-project data were not comparable with those of ROWPDP models trained on sufficient historical within-project data. However, ROCPDP models trained on filtered cross-project data achieved better performance values than ROWPDP models trained on limited historical within-project data. Therefore, we recommended that software quality teams exploit other project datasets to perform ROCPDP when there is no or limited within-project data.

SWEA-Dataveg: A vegetation database for sub-Saharan Africa

SWEA-Dataveg is a vegetation-plot database collecting observations mainly in sub-Saharan Africa but also open to the rest of the African continent. To date this database contains more than 5,500 plot observations provided by 47 sources (projects, monographs, and articles). While the database is stored in PostgreSQL (including the PostGIS extension), the R-package “vegtable” implements a suitable exchange format. In this article we assess the current content of SWEA-Database and introduce its history and future as a repository of data for syntaxonomic assessments and macroecological research.

Multi-source cross-project software defect prediction based on deep integration

Cross-project defect prediction (CPDP), training a machine learning model by using training data from other projects, has attracted much attention in recent years. This approach provides a feasible way for small-scale or new developed project with insufficient training data to carry out defect prediction. This paper focus on the bottleneck issue of CPDP, poor accuracy, and propose a deep learning model integration-based approach (MTrADL) for CPDP. This paper consists of two main phases. First, the similarity between target project and source projects is measured by the modified maximum mean discrepancy (MMD) and the top K source projects with high similarity to the target project are selected as training data. Second, for the selected training data, this paper use convolutional neural network (CNN) to build the defect predictor. Each selected training data corresponds to one CNN predictor. Then, multiple predictors are integrated to get the final prediction result. To examine the performance of the proposed approach, this paper conduct experiments on 41 datasets of PROMISE and compare our approach with three state-of-the-art baseline approaches: a training data selection model (TDS), a two-stage transfer learning model (TPTL), and the multi-source transfer learning model (MTrA). The experimental results show that the average F1-score of our approach is 0.76. Across the 41 datasets, on average, MTrADL respectively improves these baseline models by 39.8%, 28.50%, and 10% in terms of F1-score.

Clarifying strategic alignment in the public procurement process

PurposeWhile the need for strategic alignment in public management has been recognized, there is a lack of conceptual clarity to support its application in practice. Focusing on the specific field of public procurement, this paper clarifies and illustrates how the concept of strategic alignment can be applied when strategizing the public procurement process.Design/methodology/approachThe current literature on strategic alignment in public procurement is critically reviewed to identify ambiguities that hamper its application in practice. Based on this review, an analytical framework is developed that conceptualizes strategic alignment as that between the procurement instruments used in a sourcing project and the corresponding higher-level strategies. The framework is empirically illustrated by applying it in a case study that reconstructs the procurement strategy for an innovation projectFindingsStrategic alignment in the public procurement process can be demonstrated by identifying, explicating and logically linking reasoning and trade-off decisions on competing priorities across multiple levels and dimensions of strategyOriginality/valueAlthough creating alignment between policy and public procurement practice is generally held to be important in the public management literature, it is only discussed on high levels of abstraction. This paper provides clarity by investigating alignment in greater detail.

A feature location approach for mapping application features extracted from crowd-based screencasts to source code

Crowd-based multimedia documents such as screencasts have emerged as a source for documenting requirements, the workflow and implementation issues of open source and agile software projects. For example, users can show and narrate how they manipulate an application’s GUI to perform a certain functionality, or a bug reporter could visually explain how to trigger a bug or a security vulnerability. Unfortunately, the streaming nature of programming screencasts and their binary format limit how developers can interact with a screencast’s content. In this research, we present an automated approach for mining and linking the multimedia content found in screencasts to their relevant software artifacts and, more specifically, to source code. We apply LDA-based mining approaches that take as input a set of screencast artifacts, such as GUI text and spoken word, to make the screencast content accessible and searchable to users and to link it to their relevant source code artifacts. To evaluate the applicability of our approach, we report on results from case studies that we conducted on existing WordPress and Mozilla Firefox screencasts. We found that our automated approach can significantly speed up the feature location process. For WordPress, we find that our approach using screencast speech and GUI text can successfully link relevant source code files within the top 10 hits of the result set with median Reciprocal Rank (RR) of 50% (rank 2) and 100% (rank 1). In the case of Firefox, our approach can identify relevant source code directories within the top 100 hits using screencast speech and GUI text with the median RR = 20%, meaning that the first true positive is ranked 5 or higher in more than 50% of the cases. Also, source code related to the frontend implementation that handles high-level or GUI-related aspects of an application is located with higher accuracy. We also found that term frequency rebalancing can further improve the linking results when using less noisy scenarios or locating less technical implementation of scenarios. Investigating the results of using original and weighted screencast data sources (speech, GUI, speech and GUI) that can result in having the highest median RR values in both case studies shows that speech data is an important information source that can result in having RR of 100%.

Conceptual Design of the Capture Superconducting Solenoid for Experimental Muon Source

The experimental muon source (EMuS) project foreseen for muon science and neutrino physics is utilizing a superconducting solenoid for muon and pion capture, and is proposed at the China Spallation Neutron Source (CSNS). For the optimal particles collection efficiencies, an adiabatic magnetic field from 5 to 2.2 T along the central axis of the solenoid is generated by the solenoid. The superconducting solenoid is composed of four windings and an iron yoke. The iron yoke is arranged for flux returning and magnetic field shielding. Two conductor options for the windings, the aluminum stabilized NbTi Rutherford cable and the NbTi monolith wire are compared from the mechanical structure and radiation performance. The results of the mechanical analysis from ANSYS show that the excitation stress is suitable. But the results of the radiation analysis from FLUKA Monte-Carlo show that the recovery of the Residual Resistivity Ratios (RRRs) is necessary for the stabilizers of the superconductor. The recovery cycle of the aluminum stabilizer and the monolith wire solenoids are three months and one year, respectively. However, the RRR of copper for the monolith wire solenoid will be less than 50, after 12 years continuous running, which is shorter than the EMuS lifetime of 30 years. Therefore, the aluminum stabilized NbTi Rutherford cables are chosen to fabricate the windings.

DyEnTRAM- Dynamically Enhanced Metadata based Approach for Bug Assignment

Background: In open source repositories, daily numerous bugs are reported and making manual triaging difficult as well as time consuming. Aim: In this paper, we proposed a Dynamically Enhanced Metadata based approach for bug assignment (DyEnTRAM). Unlike TRAM, that worked on additional metadata features which are selected by Feature Selection (FS) algorithms that empirically analyzed the feature value and top value features are selected for triaging. Methods: The work is focused to enhance the bug features as well as rational choice of FS algorithm to improve the accuracy of developer prediction. Approach validation is done on four open- source projects and three machine learning based classifiers namely: Naive-Bayes (NB), SVM and Decision-Tree (C4.5). This approach is only worked with highly ranked meta-data fields which are selected by FS algorithms. Result: This approach has shown better prediction accuracy over the Baseline, X2 and TRAM. Findings have shown F-Score improvements in DyEnTRAM over TRAM approach as much as 24.6%, 10.9%, 16.4%, and 18.2% for Eclipse, Netbean, Firefox and Freedesktop projects respectively. Conclusion: DyEn-TRAM approach effectively improved bug prediction accuracy on the chosen datasets as compared to TRAM, X2, and baseline.

Shut-Down Dose Rate Distribution Calculation in the Access Cell With Activated HFTM in the IFMIF-DONES Facility

International Fusion Materials Irradiation Facility–DEMOnstration Power Station (DEMO)-Oriented Neutron Source (IFMIF-DONES) is an accelerator-based d-Li neutron source that is aimed at the qualification of materials at the irradiation conditions of a DEMO fusion power reactor. It is being developed in the frame of EUROfusion’s Power Plant Physics and Technology (PPPT) work program. The intense neutron radiation produced in the liquid lithium target results in a strong activation of the test cell (TC) and its high flux test module (HFTM). This article presents the analyses performed within the Early Neutron Source (ENS) project of EUROfusion/PPPT directed to provide up-to-date estimates of the activity inventories and the decay heat production in the DONES TC facility. To this end, a series of coupled Monte Carlo N-Particle code (MCNP)+ McDelicious transport and FISPACT inventory calculations were performed using the 2017 DONES TC model and nuclear cross section data from the Joint Evaluated Fission and Fusion (JEFF)–3.1.2 data library. The article presents the shut-down dose rate maps generated by HFTM that was irradiated at the TC and later relocated to the access cell. Performed calculations used to addresses the issue of the radiation dose loads that are to be expected due to the activated components/systems including the HFTM. In addition to that, activation calculations of HFTM materials are also provided.

The Solar Wind Speed Expansion Factor [${v}$–$f _{\text{s}}$] Relationship at the Inner Boundary (18 $\text{R}_{\odot }$) of the Heliosphere

The accuracy of data-driven magnetohydrodynamics (MHD) models depends on accurate boundary conditions specified at the inner heliosphere. However, not all of the MHD parameters [$\boldsymbol{B}, \boldsymbol{v}, \rho , T$] are measurable close to the Sun at the present time, except the vector magnetic field [$\boldsymbol{B} $] at the photosphere. The solar wind speed [$\boldsymbol{v}$], which is probably most relevant to space-weather forecasting, is often modeled by the standard Wang–Sheeley (WS) formula, which is based on an inverse relationship between the solar wind speed [$\boldsymbol{v}$] at 1 AU and the expansion factor [$f_{\text{s}}$] estimated at 2.5 solar radii [$\text{R}_{ \odot }$], with the following generic form: ${v} = {v}_{1} + {v}_{2} f_{\text{s}}^{- \alpha }$ (where $\boldsymbol{v}$ is the solar wind speed at 18 $\text{R}_{\odot }$, $f_{\text{s}}$ is the magnetic-field expansion factor, and ${v}_{1}$, ${v}_{2}$, and $\alpha $ are three free parameters to be determined). While the WS formula uses “source projection” to determine the solar wind source, it does not treat the solar wind as plasma because it uses the solar wind speed observed at 1 AU to derive the empirical relationship. Thus, the resulting formula ignores the transport and acceleration of the solar wind as it propagates out into the heliosphere. The purpose of this study is to rectify this omission by using a numerical MHD simulation to find the optimal set of free parameters that relate the magnetic properties at the source surface to the plasma parameters at 1 AU. In addition to the expansion factor, conservation of mass [$\rho \boldsymbol{v}$], magnetic flux [$r ^{2} B$], and total pressure along the stream line are assumed to obtain the solar wind mass density, magnetic field, and temperature at 18 $\text{R}_{\odot }$. These parameters are used as the inner boundary conditions of our global three-dimensional MHD (G3DMHD) code to simulate solar wind plasma and field parameters out to ${\approx}\, 1~\mbox{AU}$. The simulation results are compared with the in-situ data from Wind to assess the accuracy. Such a procedure is repeated (880 times) to cover the three parameter regimes ($100 < {v}_{1} < 350~\mbox{km}\,\mbox{s}^{-1}$; $250 < {v}_{2} < 700~\mbox{km}\,\mbox{s}^{-1}$; and $0.2 < \alpha < 0.9$) to find the optimal set. The simulation is performed for the period of CR2082 [30 March 2019 to 27 April 2009]. It is found that $\boldsymbol{v} = 189 + 679 f_{\text{s}}^{-0.7}$ is the best formula to relate the solar wind speed at 18 $\text{R}_{\odot }$ to the expansion factor. Strictly speaking, this formula is most applicable for solar equatorial regions and near the times of solar minimum when there are few coronal mass ejection events.

ALTRA: Cross-Project Software Defect Prediction via Active Learning and Tradaboost

Cross-project defect prediction (CPDP) methods can be used when the target project is a new project or lacks enough labeled program modules. In these new target projects, we can easily extract and then measure these modules with software measurement tools. However, labeling these program modules is time-consuming, error-prone and requires professional domain knowledge. Moreover, directly using labeled modules in the other projects (i.e., the source projects) can not achieve satisfactory performance due to the large data distribution difference in most cases. In this article, to our best knowledge, we are the first to propose a novel method ALTRA, which can utilize both active learning and TrAdaBoost to alleviate this issue. In particular, we firstly use Burak filter to select similar labeled modules from the source project after analyzing the unlabeled modules in the target project. Then we use active learning to choose representative unlabeled modules from the target project and ask experts to label the type (i.e., defective or non-defective) of these modules. Later, we use TrAdaBoost to determine the weights of labeled modules in the source project and the target project, and then construct the model via weighted support vector machine. After selecting a small number of modules (i.e., only 5% modules) in the target project, we terminate the method ALTRA and return the final constructed model. To show the effectiveness of our proposed method ALTRA, we choose 10 large-scale open-source projects from different application domains. In terms of both F1 and AUC performance indicators, we find ALTRA can perform significantly better than seven state-of-the-art CPDP baselines. Moreover, we also show that the usage of Burak filter, the uncertainty active learning strategy, the class imbalanced learning method and TrAdaBoost are competitive in our proposed method ALTRA.

Comparison of axial and coronal acquisitions by non-contrast-enhanced renal 3D MR angiography using flow-in time-spatial labeling inversion pulse

ObjectiveWe evaluated image quality differences between axial and coronal non-contrast-enhanced renal three-dimensional (3D) magnetic resonance angiography (MRA) acquisitions, using time-spatial labeling inversion pulse (Time-SLIP) with flow-in balanced steady-state free precession (bSSFP).Materials and methodsAxial and coronal images were acquired in 128 subjects using non-contrast-enhanced 3D-MRA with Time-SLIP flow-in bSSFP on a clinical 1.5-T MRI system. Visualization of source and maximum intensity projection (MIP) images of renal arteries were compared between the axial and coronal acquisitions using a four-point scale. For quantitative analysis, vessel-to-background contrast ratios of aorta and renal arteries were calculated.ResultsBoth acquisitions yielded similarly excellent quality. In source image evaluation, coronal acquisitions showed significantly more motion degradation (p < 0.01) than did axial acquisitions. In MIP image evaluation, coronal acquisitions yielded superior image quality, less motion degradation, and better visualization of the number of renal branches than did axial acquisition. The renal artery to background signal contrast was greater in coronal than in axial acquisitions (p < 0.01).ConclusionCoronal acquisition provides superior contrast between the renal arteries and background and allows more persistent visualization than axial acquisitions in non-contrast-enhanced MRA using flow-in bSSFP with Time-SLIP. First-line screening of renal non-contrast-enhanced MRA should involve coronal acquisition.

Deep Transfer Bug Localization

Many projects often receive more bug reports than what they can handle. To help debug and close bug reports, a number of bug localization techniques have been proposed. These techniques analyze a bug report and return a ranked list of potentially buggy source code files. Recent development on bug localization has resulted in the construction of effective supervised approaches that use historical data of manually localized bugs to boost performance. Unfortunately, as highlighted by Zimmermann et al., sufficient bug data is often unavailable for many projects and companies. This raises the need for cross-project bug localization - the use of data from a project to help locate bugs in another project. To fill this need, we propose a deep transfer learning approach for cross-project bug localization. Our proposed approach named TRANP-CNN extracts transferable semantic features from source project and fully exploits labeled data from target project for effective cross-project bug localization. We have evaluated TRANP-CNN on curated high-quality bug datasets and our experimental results show that TRANP-CNN can locate buggy files correctly at top 1, top 5, and top 10 positions for 29.9, 51.7, 61.3 percent of the bugs respectively, which significantly outperform state-of-the-art bug localization solution based on deep learning and several other advanced alternative solutions considering various standard evaluation metrics.