Traceability links between requirements and source code are crucial for maintaining software quality, yet traditional traceability methods exhibit critical limitations. Current methods predominantly rely on semantic similarity among artifacts, failing to account for link transitivity and the underlying rationale governing traceability link formation. To address these challenges, this study introduces HGTRTracer, a novel framework that integrates Large Language Models (LLMs) with Graph Neural Networks (GNNs) to advance traceability analysis. The proposed method innovatively incorporates attribution reasoning via LLMs to derive explicit “Reason nodes” that justify traceability links, with a Heterogeneous Graph Transformer (HGT) captures structural dependencies among nodes and edges to improve link prediction accuracy. Experiments conducted on 10 open-source projects demonstrate that HGTRTracer outperforms the state-of-the-art baseline (HGNNLink) by 12.90% in F1-score on average. Beyond performance gains, the framework enhances interpretability through its attribution-aware design, providing actionable insights for traceability decisions.

Defect detection is essential in modern industrial production for ensuring product quality. However, current methods struggle with small object and multi-scale detection, especially in complex backgrounds, due to limitations in feature extraction and fusion. To address these challenges, this paper introduces the bi-attention pyramid network for enhanced small defect detection in complex backgrounds, inspired by the channel and spatial attention mechanisms, as well as advanced fast single-stage detection neural networks. Firstly, this work develops an innovative bi-attention pyramid network and introduces a new feature fusion module, the bi-attention fusion block (bi-AFB), which to enhance the detection of small defects. Additionally, the integration of dynamic sampling to optimize the upsampling process and the incorporation of a large selective kernel into the backbone network expand the receptive field, thereby improving multi-scale detection and the utilization of background contextual information. Experimental results demonstrate that bi-APNet achieves state-of-the-art performance across three benchmarks, with minimal increases in model parameters, thereby validating the efficiency and superiority of the proposed architecture.

Current research on requirements-to-code traceability predominantly focuses on improving the performance of algorithms or models, while neglecting the quality of project artifacts themselves.Nevertheless, high-quality data can significantly improve the performance of a model, and disregarding data quality can be challenging to rectify even with sophisticated models.Often, high-quality data contributes substantially more to model performance enhancement than improvements to the model's structure itself.In real-world software development, requirements and code artifacts are the primary data sources for establishing traceability links.However, there is a lack of effective guidance on what factors of requirements and code artifacts are conducive to traceability.To address this issue, this study proposes five metrics that are verified to have a close impact on the requirementsto-code traceability: cyclomatic complexity, annotation ratio, co-occurrence ratio, noun-verb ratio, and noise ratio.Based on a systematic mapping study, we selected 11 open-source projects from 20 relevant publications to conduct experiments, and employed Spearman correlation analysis to validate the association between the proposed metrics and traceability.The experimental results show that the proposed five metrics can significantly affect the traceability of requirements-to-code, of which the cyclomatic complexity and the annotation ratio are more influential.

In the task of requirements-to-code traceability link recovery, the continues growth of software scale has led to diminishing differences between indices and more complex nonlinear relationships within the data. This results in the performance decline of the most widely used information retrieval methods and machine learning methods when handling this task. Therefore, we propose a requirement traceability method based on heterogeneous graph attention networks, named HANTracer. The model integrates the high-dimensional vectors generated by a pre-trained model as node features to deepen the dif-ferentiation between nodes and enhances node representations with contextual information learned from the graph structure. Additionally, it utilizes the properties of heterogeneous edges to construct various edge features, such as code calling, code inheritance, and text similarity relationships, aiding the model in understanding and utilizing the relationships between different types of data elements. By incorporating average pooling layers and multiple fully connected layers, the HANTracer model is further improved to enhance its ability to extract nonlinear features. Experimental results indicate that HANTracer achieves an average F1 performance higher than the state-of-the-art methods TAROT by 100.30% and DF4RT by 46.27% on seven real-world open source software (OSS) datasets, demonstrating significant performance advantages in large-scale and complex data environments.

In recent years, Prompt Learning, based on pre-training, prompting, and prediction, has achieved significant success in natural language processing (NLP). The current issue-commit link recovery (ILR) method converts the ILR into a classification task using pre-trained language models (PLMs) and dedicated neural networks. However, due to inconsistencies between the ILR task and PLMs, these methods not fully leverage the semantic information in PLMs. To imitate the above problem, we make the first trial of the new paradigm to propose a Multi-template prompt learning method with adversarial training for issue-commit link recovery (PromptLink), which transforms the ILR task into a cloze task through the template. Specifically, a Multi-template PromptLink is designed to enhance the generalisation capability by integrating various templates and adopting adversarial training to mitigate the model overfitting. Experiments are conducted on six open-source projects and comprehensively evaluated across six commonly measures. The results show that PromptLink achieves an average F1 of 96.10%, Precision of 96.49%, Recall of 95.92%, MCC of 94.04%, AUC of 96.05%, and ACC of 98.15%, significantly outperforming existing state-of-the-art methods on all measures. Overall, PromptLink not only enhances performance and generalisation but also emerges new ideas and methods for future research. The source code of PromptLink is available at https://figshare.com/s/6130d42ff464c579cdec.

Track-before-detect (TBD) and multi-sensor fusion are two popular methods of weak target detection which can improve the performance by increasing the number of measurements. In this paper, we combine these two methods, proposing a novel multi-sensor track-before-detect (MS-TBD) method for automotive platforms. It can utilize the information from both the spatial and temporal dimensions of the target by jointly processing the measurement from different radars. In particular, the traditional TBD method is often based on an implicit assumption: the presence of targets is unchanged in the sliding window. However, this assumption may not be applicable for automotive multi-sensor systems due to the time-varying fields of view (FOV). To solve the problems mentioned above, we first present an energy accumulation strategy for automotive multi-radar systems and then propose a multiple-hypothesis detection method with the adaptive threshold (AT). It is demonstrated by simulations that the proposed methods show superior performance.

The Bayesian inference has a two-step recursion structure, i.e., prediction and updating, which can be viewed as a dynamic reasoning process. Based on this elegant structure, various multi-target tracking (MTT) algorithms have been invented and successfully applied in many areas. On the other hand, Bayesian inference MTT algorithms are model-based methods that rely on models’ accuracy and first-order Markov assumption. In recent years, the MTT algorithms based on deep learning have received much attention due to their model-free property and the ability to learn from data, although they have issues such as over-fitting, generalization, etc. In this work, we propose a Transformer-based multi-target tracker whose architecture mimics the Bayesian inference, referred to as the Bayesian inference-based Transformer (BAIT) for MTT. To deal with the model mismatch issues, BAIT uses neural networks instead of the pre-assumed motion and observation models while retaining the excellent architecture of Bayesian inference. BAIT can recursively complete accurate predictions and updates via Transformer by refining the estimation of target states in a Bayesian inference-like manner. Thus, BAIT can be viewed as a combination of model-based and data-based methods. The simulation results show that, because of combining the advantages of Bayesian architecture with intelligent data association structure, BAIT is competitive in simple scenarios and achieves superior performance when the data association task becomes complicated.

The swarm targets have shown great potential for both military and civilian applications, driving a high demand for reliable trajectory generation and accurate activity recognition. In this paper, we propose a trajectory generation method and establish an end-to-end deep learning model for dynamic continuous activity recognition of swarm targets. First, we devise an activity transition model of the drone swarm based on a continuous-time Markov chain (CTMC). Subsequently, the minimum snap trajectory generation algorithm is employed to generate the trajectories. After that, to recognize the dynamic continuous activity of targets, we develop an end-to-end neural network model to extract spatial and temporal features for swarm targets detected by radar across multiple frames. Finally, we demonstrate the effectiveness and robustness of our proposed method through simulation results.

Unmanned aerial vehicle (UAV) swarms have been widely used in civil and military fields. UAV swarm has the characteristics of multi-scale irregularity in target distribution and small individual targets. This brings certain challenges to the traditional radar target detection algorithms and deep learning algorithms. Therefore, this paper proposes a novel point target detection approach for UAV swarm scene. For the multi-scale and irregular characteristics of target distribution within the UAV swarm, the detection box of each overall swarm target can be obtained by combining the multi-scale superposition and the feature pyramid (FPN) network structure. Subsequently, the thresholds of the detection cells inside the boxes are estimated by the background noise outside the detection boxes, so as to realize the detection of the point targets inside each swarm. Simulation results show that the proposed approach outperforms YOLOv7 and several classical constant false alarm rate(CFAR) detection algorithms in the radar field.

In recent years, increasing machine learning has been applied to Requirements Traceability Recovery (RTR). The performance of these approaches is not satisfactory. Besides, most of them perform well in recovering traceability links between specific artifacts but cannot maintain consistent performance in different scenarios. To alleviate this problem, we propose a novel approach based on Multi-Layered Gradient Boosting Decision Trees (mGBDT) for RTR which is called MLTracer. MLTracer stacks several GBDTs and learns hierarchical representations of artifact link features. Through layer-by-layer training, it adapts to the feature distribution in different scenarios to improve generalization ability. MLTracer is evaluated on five software projects and compared with six state-of-the-art approaches. The results indicate that MLTracer achieves an average F1 score of 0.6153, outperforming six baseline approaches across all datasets. It proves that MLTracer achieves state-of-the-art performance and has strong applicability in actual industry.

Optical Communication Simulation Task Allocation (OCSTA) constitutes an interdisciplinary quandary. This paper proposes a swarm intelligence approach harnessing a Discrete Dung Beetle Optimizer (DDBO) algorithm with a globally equilibrated strategy to offer a resolution avenue for this intricate conundrum. Firstly, we provide a comprehensive exposition of the mathematical model underpinning the OCSTA, which employs the spatial positioning of the population to articulate diverse allocation solutions. Then, a weighted random selection technique is used to generate initial solutions. Thirdly, a predator avoidance strategy is introduced to facilitate updates in the dung beetle position. Finally, the global equilibrium mechanism with the swap operator is exploited to harmonize the exploratory and exploitative capabilities, thereby further augmenting the quality of the solutions. We conducted several simulation experiments1across various distinct task load scenarios, and statistical tests are employed to evaluate the significant differences between the proposed algorithm and other state-of-the-art methods. The outcomes revealed that the DDBO solution yielded an improvement of approximately 15.8%, which underscores the competitiveness and robustness of solving the OCSTA.

Directed Acyclic Graphs (DAGs) are widely utilized across various domains for tasks such as graph algorithms, data flow analysis, program optimization, and machine learning. Representing DAGs using General-purpose Programming Languages (GPLs) or Data Serialization Formats (DSFs) can lead to complex and obscure expressions, making it challenging to comprehend and manage the codebase. Domain-Specific Languages (DSLs) offer a more tailored approach, but come with limitations and development overhead. This paper introduces the Open Customizable Modeling Language (OpenCML), a universal DAG modeling language specification that aims to provide a standardized and customizable framework for modeling and scripting DAGs. Evaluations demonstrate that OpenCML offers expressive power, customizability, and interoperability, simplifying the learning process and providing a powerful solution for DAG modeling and scripting.

Target detection in road clutter environment is a challenge for automotive radar. The performance of model-based methods degrades when the prior model is mismatched or the target energy is overwhelmed by the clutter. In contrast, deep learning methods can nonlinearly fit clutter distributions and extract deep features to identify targets from clutter backgrounds. Considering that the spatial-temporal feature in multi-frame data helps distinguish targets from clutter, we use the multi-frame data for detection. This paper proposes a multi-frame detection network for radar moving targets in clutter environment. First, we use transformer as the backbone to fit the large-scale clutter background by extracting the global spatio-temporal feature. Second, we proposed a multi-frame detection head to predict multi-frame bounding boxes in parallel by utilizing the spatio-temporal feature. Third, we proposed a segmentation-assisted refinement module to refine the objectness of bounding boxes, thus further suppressing the false alarms caused by clutter. Through experiments on simulation and measured datasets, the proposed method effectively reduces false alarms while maintaining a high detection probability. In addition, compared with the segmentation-based method, our method distinguishes adjacent targets more robustly.

Traceability refers to the potential for traces to be established (i.e., created and maintained) and used. Bug Traceability (BT) is critical for enhancing software quality, reducing maintenance costs, and boosting team efficiency. To explore the trends and advancements of BT, we conduct a systematic mapping study (SMS). We initially retrieve 4674 citations from 7 databases spanning 2014 to 2023, and 24 primary studies meet the rigorous selection criteria. Our study identifies 6 types of bug trace links, 8 traceability strategies, and 47 bug traceability recovery (BTR) techniques. Among them, 47 BTR techniques can be further classified into 6 categories. At the same time, we perform statistics on 113 datasets and 16 evaluation metrics used to assess the performance of BTR techniques proposed in the primary studies. In evaluating the overall quality of the primary studies, 8 dimensions are utilized to support technology transfer, categorizing the overall quality into 4 levels: poor, middle, good, and excellent, with 79% of primary studies evaluated at a good level. This study not only furnishes a clear definition of BT for scholarly reference, but also highlights that information retrieval (IR), machine learning (ML) and deep learning (DL) techniques are the mainstream techniques used for BTR.

Information Retrieval (IR), Machine Learning (ML), and Deep Learning (DL) have become mainstream methods for traceability link recovery. However, IR-based methods face the challenge of low precision, while DL-based methods require large-scale training data to achieve better performance. In this paper, we propose a novel model XWCoDe, which apply XGBoost combined with a weighted code dependency strategy to traceability link recovery domain. In order to refine the initial candidate links generated by the XGBoost model, the strategy only modifies low confidence candidate links and pioneers the use of graph embedding technology node2vec to calculate the importance of each code dependency relationship. The experimental results show that the average F1 score of XW CoDe on 4 datasets and 9 training/testing ratios is 12.93 % higher than the state-of-the-art method DF4RT.