Traffic knowledge is essential for safe, efficient, and regulation-compliant autonomous driving. While existing path planning methods often encode only partial traffic rules or focus on specific scenarios, they lack adaptability to diverse and dynamic environments. The Internet of Things (IoT) enables vehicles to access rich, real-time traffic knowledge, yet most IoT-based approaches emphasize long-distance route optimization and overlook local path planning. This paper proposes a traffic knowledge-augmented path planning model (KARS) that integrates a knowledge graph representation of traffic knowledge with a reachable set-based planning framework in IoT environments. The knowledge graph systematically encodes spatial, temporal, and speed constraints, while the reachable set method enables the planner to dynamically adapt to real-time traffic knowledge. KARS is evaluated in multi-constraint simulation environments with static, semi-dynamic, and dynamic traffic knowledge settings. Compared to representative baselines, it improves driving safety by increasing traffic success rates in complex environments, raises maximum driving speed to enhance operational efficiency, and produces smoother acceleration profiles for improved ride comfort. These results validate the effectiveness of combining traffic knowledge with reachable set planning for safe, efficient, and adaptable autonomous driving in IoT-enabled urban scenarios.

Risk assessment plays an essential role in the improvement of driving safety for intelligent vehicles. Current methods ignoring the predictive and personalized impact of driving policies weaken the effectiveness of risk assessment and lead to human-machine conflicts. By combining subjective cognition of drivers and objective risk metrics, a policy-oriented cognitive risk map (POCRM) is proposed in this paper to encode different driving policies in risk assessment for lane-changing scenarios. To obtain the objective safety metrics, insecurity quantification is built based on the fuzzy theory and fault tree analysis. The subjective cognition of drivers for different driving policies is modeled by deep successor representation and encoded in POCRM using deep reinforcement learning. Driving data collected from the public dataset for realistic traffic environment are used to evaluate the proposed POCRM. The experimental results show that the risk map can take into account future risks and provide driving advice that balances human-machine conflicts with safety in scenarios where drivers can or cannot correctly perceive risk.

Neuronal morphology is essential for studying brain functioning and understanding neurodegenerative disorders. As acquiring real-world morphology data is expensive, computational approaches for morphology generation have been studied. Traditional methods heavily rely on expert-set rules and parameter tuning, making it difficult to generalize across different types of morphologies. Recently, MorphVAE was introduced as the sole learning-based method, but its generated morphologies lack plausibility, i.e., they do not appear realistic enough and most of the generated samples are topologically invalid. To fill this gap, this paper proposes **MorphGrower**, which mimicks the neuron natural growth mechanism for generation. Specifically, MorphGrower generates morphologies layer by layer, with each subsequent layer conditioned on the previously generated structure. During each layer generation, MorphGrower utilizes a pair of sibling branches as the basic generation block and generates branch pairs synchronously. This approach ensures topological validity and allows for fine-grained generation, thereby enhancing the realism of the final generated morphologies. Results on four real-world datasets demonstrate that MorphGrower outperforms MorphVAE by a notable margin. Importantly, the electrophysiological response simulation demonstrates the plausibility of our generated samples from a neuroscience perspective. Our code is available at [https://github.com/Thinklab-SJTU/MorphGrower](https://github.com/Thinklab-SJTU/MorphGrower).

Federated learning (FL) is an edge learning framework that has received significant attention recently. However, the cost of communication has become a major challenge for FL as the number of edge devices grows and the complexity of training models increases. Besides, data samples across all edge devices are usually not independent and identically distributed (non-IID), posing additional challenges to the convergence and model accuracy of FL. Therefore, we propose a novel personalized FL framework based on deep coded over-the-air computation, named DipFL. In this framework, we design a deep AirComp aggregation (DACA) module for n-to-1 information aggregation. Besides, a joint source-channel coding (JSCC) module is designed based on the variational auto-encoder (VAE) model, which not only encodes the transmitted data, but also reduces the bias of local samples by introducing certain regularisation terms. In addition, we propose a personalized mix module that allows local models to be more personalized by mixing the global model and the local models. Simulation results confirm that the proposed DipFL framework is able to significantly reduce the amount of transmitted data, while improving FL performance especially at low signal-to-noise regimes.

Target detection in unmanned aerial vehicle application scenarios has other problems, such as dense targets. The existing unmanned aerial vehicle target detection model with high computational complexity makes it difficult to meet real-time unmanned aerial vehicle target detection, and the detection accuracy of small targets is low. To address these problems, we propose an improved YOLOv7 small target detection model based on context and pyramidal attention that can cope with dense unmanned aerial vehicle scenarios - CPA-YOLOv7. This model embeds our proposed lightweight multi-scale attentional feature spatial pyramid pooling module, which can better distinguish between small and large target features, reducing the computational effort while improving the detection accuracy of the model. Secondly, we design a contextual dynamic fusion attention module in the network to fuse global and local contextual information and dynamically assign features to multiple groups of channels; in the multi-scale fusion process, it effectively increases the characterization ability of small target features and enables the network to better focus on small target information. Finally, we improve Wise-Intersection-over-Union loss as the regression loss function, add a moderation factor to retain some of the high and low-quality sample weights to improve the regression accuracy of high-quality anchor frames, and use the dynamic non-monotonic focusing mechanism to increase the model's focus on ordinary quality anchor frames to improve the model's localization performance and robustness to low-quality samples. Numerous experimental results show that on the unmanned aerial vehicle datasets VisDrone2021-DET and AI-TOD, the mAP values of our model are 2.3% and 1.1% higher than those of the YOLOv7 model with fewer parameters introduced, and the computational speed reaches 146 frames per second (FPS), which can meet the real-time requirements of unmanned aerial vehicle detection.

For Chinese font images, when all their strokes are replaced by pattern elements such as flowers and birds, they become flower–bird character paintings, which are traditional Chinese art treasures. The generation of flower–bird painting requires professional painters’ great efforts. How to automatically generate these paintings from font images? There is a huge gap between the font domain and the painting domain. Although many image‐to‐image translation frameworks have been proposed, they are unable to handle this situation effectively. In this study, a novel method called font‐to‐painting network (F2PNet) is proposed for font‐to‐painting translation. Specifically, an encoder equipped with dilated convolutions extracts features of the font image, and then the features are fed into the domain translation module for mapping the font feature space to the painting feature space. The acquired features are further adjusted by the refinement module and utilised by the decoder to obtain the target painting. The authors apply adversarial loss and cycle‐consistency loss to F2PNet and further propose a loss term, which is called recognisability loss and makes the generated painting have font‐level recognisability. It is proved by experiments that F2PNet is effective and can be used as an unsupervised image‐to‐image translation framework to solve more image translation tasks.

Automation‐assisted cervical screening via liquid‐based cytology has achieved great success using segmentation and classification methods. This work tries to do abnormal region detection on field of view cervical cell images based on deep learning, which is a novel way to solve cervical cytological screening problem. Since some abnormal nuclei gather in groups, the proposed method chooses abnormal regions instead of abnormal nuclei as the detection targets in order to locate the abnormal regions for the further diagnosis of the pathologists. In this study, a novel abnormal region detection approach for cervical screening is proposed based on a size‐sensitive fully convolutional network (R‐FCN). Due to the regular feature distribution, a fewer‐layer convolutional neural backbone network is designed for more efficient feature extraction and less running time. In addition, a new measure named hit degree is defined to describe the degree how closely each detected region and the corresponding ground truth matches up. Experimental results show that an average precision of 93.2% is achieved for abnormal region detection in cervical smear images. The proposed method is promising for the development of computer‐aided systems in clinical cervical cytological screening.

Face recognition technique has been widely applied to personal identification systems due to its satisfying performance. However, its security may be a crucial issue, since many studies have shown that face recognition systems may be vulnerable in an adversarial environment, in which an adversary can camouflage as a legitimate user in order to mislead the system. Although face liveness detection methods have been proposed to distinguish real and fake faces, they are either time-consuming, costly, or sensitive to noise and illumination. This paper proposes a face liveness detection method with flash against 2D spoofing attack. Flash not only can enhance the differentiation between legitimate and illegitimate users, but it also reduces the influence of environmental factors. Two images are taken from a subject, one with flash and another without flash. Four texture and 2D structure descriptors with low computational complexity are used to capture information of the two images in our model. Advantages of our method include low installation cost of flash and no user cooperation required. A data set of 50 subjects collected under different scenarios is used in the experiments to evaluate the proposed method. The experimental results indicate that the proposed model performs better than existing liveness detection methods in different environmental scenarios. This paper confirms that the use of flash successfully improves face liveness detection in terms of accuracy, robustness, and running time.

Background: Handover is a common process in all software development projects. It is one of the most complex and diverse processes in software life cycle which could have a negative impact on software quality and progress. In open source software (OSS) development, handover is a more critical task due to poor planning. Objective: The goal of this work is to investigate whether we can automatically identify the handover process in OSS development. Furthermore, we aim to mine the process of handover and identify the factors and their influences on the duration of handover process. Method: We propose an ADC metric and an HDI algorithm to automatically identify the handover process and conduct a brief survey to evaluate it. We apply the Heuristic mining algorithm to discover the process maps of handover by mining Github repositories. To identify the factors from a large set of variables, we employ the Stepwise regression method. Results: We identified 63 pairs of handover within 44 projects from 314 most popular projects using our proposed method. Our survey received 21 responses. Conclusion: This study confirms that handover can be identified automatically. Although handover processes vary, developers follow a common work-flow during handover. The number of lines of code is positively correlated to the duration of handover process.