Abstract ：

Accident detection in surveillance or dashcam videos is a common task in the field of traffic accident analysis by using videos. However, as accidents occur sparsely and randomly in the real world, the data records are more scarce than the training data for standard detection tasks such as object detection or instance detection. Moreover, the limited and diverse accident data makes it more difficult to model the accident pattern for fine-grained accident detection tasks analyzing the accident in detail. Extra prior information should be introduced in the tasks such as the common vision feature which could offer relatively effective information for many vision tasks. The big model could generate the common vision feature by training on abundant data and consuming a lot of computing time and resources. Even though the accident video data is special, the big model could also extract common vision features. Thus, in this paper, we propose to apply knowledge distillation to fine-grained accident detection which analyzes the spatial temporal existence and severity for solving the issues of complex computing (distillation to the small model) and keeping good performance under limited accident data. Knowledge distillation could offer extra general vision feature information from the pre-trained big model. Common knowledge distillation guides the student network to learn the same representations from the teacher network by logit mimicking or feature imitation. However, single-level distillation could only focus on one aspect of mimicking classification logit or deep features. Multiple tasks with different focuses are required for fine-grained accident detection, such as multiple accident classification, temporal-spatial accident region detection, and accident severity estimation. Thus in this paper, multiple-level distillation is proposed for the different modules to generate the unified video feature concerning all the tasks in fine-grained accident detection analysis. The various experimental results on a fine-grained accident detection dataset which provides more detailed annotations of accidents demonstrate that our method could effectively model the video feature for multiple tasks.

Keyword ：

knowledge distillation Video accident detection multiple-level distillation fine-grained accident detection

Cite：

Copy from the list or Export to your reference management。

Abstract ：

The COVID-19 pandemic overwhelmed national health care systems, not least in the context of hepatitis elimination. This study investigates the effects of the pandemic response on the incidence rate, mortality rate, and case fatality rate (CFR) for hepatitis C virus (HCV) cases in China. We extracted the number of hepatitis C cases and HCV-related deaths by month and year for 2015 to 2021 in China and applied two proportional tests to analyze changes in the average yearly incidence rates, mortality rates, and CFRs for 2015 to 2020. We used the autoregressive integrated moving average model to predict these three rates for 2020 based on 2015 to 2019 HCV data. The incidence of hepatitis C decreased by 7.11% and 1.42% (P < .001) in 2020 and 2021, respectively, compared with 2015 to 2019, while it increased by 6.13% (P < .001) in 2021 relative to 2020. The monthly observed incidence in 2020 was significantly lower (-26.07%) than predicted. Meanwhile, no differences in mortality rate or CFR were observed between 2021, 2020, and 2015 to 2019. Our findings suggest that nonpharmaceutical interventions and behavioral changes to mitigate COVID-19 could have reduced hepatitis C incidence and accelerated China's implementation of a plan to eliminate HCV infection.

Keyword ：

hepatitis C incidence HCV-elimination program COVID-19 nonpharmaceutical interventions mortality

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Neonicotinoid insecticides (NNIs) are extensively used in agricultural production in China due to their selective neurotoxicity towards target insects. In recent years, the rapid development of agriculture has increased the use and residue of NNIs. Consequently, the sediment environment, serving as the ultimate sink, is significantly impacted by NNIs. Upon release into the environment, NNIs can enter the human body through the food chain, posing potential ecological and human health risks. This study analyzed 79 sediment samples from two major river basins in North and South China, the Liaohe River basin in Liaoning Province and the Jianjiang River basin in Guangdong Province. The content, composition, distribution, and source of eight NNIs were analyzed, and assess the ecological and human health risks of the target compounds in these regions. The results indicated that the average concentration of NNIs in the sediments of the Jianjiang River basin (2.34 μg/kg) is slightly higher than that of the Liaohe River basin (2.32 μg/kg), and the sources of NNIs in the two areas were different, with differences in the sources of NNIs likely attributable to varying types of agricultural production. The risk assessment revealed that the ecotoxicological and public health risks were more pronounced in the Jianjiang River basin compared to the Liaohe River basin, underscoring the critical need for surveillance and management of hazardous substances like NNIs. The insights findings from this study can provide scientific guidance for the risk evaluation and environmental management of NNIs. © 2024 Elsevier B.V.

Keyword ：

Livestock Invertebrates

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Background and Objective: Preterm delivery is an important factor in the disease burden of the newborn and infants worldwide. Electrohysterography (EHG) has become a promising technique for predicting this condition, thanks to its high degree of sensitivity. Despite the technological progress made in predicting preterm labor, its use in clinical practice is still limited, one of the main barriers being the lack of tools for automatic signal processing without expert supervision, i.e. automatic screening of motion and respiratory artifacts in EHG records. Our main objective was thus to design and validate an automatic system of segmenting and screening the physiological segments of uterine origin in EHG records for robust characterization of uterine myoelectric activity, predicting preterm labor and help to promote the transferability of the EHG technique to clinical practice. Methods: For this, we combined 300 EHG recordings from the TPEHG DS database and 69 EHG recordings from our own database (Ci2B-La Fe) of women with singleton gestations. This dataset was used to train and evaluate U-Net, U-Net++, and U-Net 3+ for semantic segmentation of the physiological and artifacted segments of EHG signals. The model's predictions were then fine-tuned by post-processing. Results: U-Net 3+ outperformed the other models, achieving an area under the ROC curve of 91.4 % and an average precision of 96.4 % in detecting physiological activity. Thresholds from 0.6 to 0.8 achieved precision from 93.7 % to 97.4 % and specificity from 81.7 % to 94.5 %, detecting high-quality physiological segments while maintaining a trade-off between recall and specificity. Post-processing improved the model's adaptability by fine-tuning both the physiological and corrupted segments, ensuring accurate artifact detection while maintaining physiological segment integrity in EHG signals. Conclusions: As automatic segmentation proved to be as effective as double-blind manual segmentation in predicting preterm labor, this automatic segmentation tool fills a crucial gap in the existing preterm delivery prediction system workflow by eliminating the need for double-blind segmentation by experts and facilitates the practical clinical use of EHG. This work potentially contributes to the early detection of authentic preterm labor women and will allow clinicians to design individual patient strategies for maternal health surveillance systems and predict adverse pregnancy outcomes.

Keyword ：

Deep learning Uterine myoelectric activity Preterm delivery prediction Signal processing Semantic segmentation Electrohysterography

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Objective: The Rapid Serial Visual Presentation (RSVP) paradigm facilitates target identification in a rapid picture stream, which is applied extensively in military target surveillance and police monitoring. Most researchers concentrate on the single target RSVP-BCI whereas the study of dual-target is scarcely conducted, limiting RSVP application considerably. Methods: This paper proposed a novel classification model named Common Representation Extraction-Targeted Stacked Convolutional Autoencoder (CRE-TSCAE) to detect two targets with one nontarget in RSVP tasks. CRE generated a common representation for each target class to reduce variability from different trials of the same class and distinguish the difference between two targets better. TSCAE aimed to control uncertainty in the training process while requiring less target training data. The model learned a compact and discriminative feature through the training from several learning tasks so as to distinguish each class effectively. Results: It was validated on the World Robot Contest 2021 and 2022 ERP datasets. Experimental results showed that CRE-TSCAE outperformed the state-of-the-art RSVP decoding algorithms and the Average ACC was 71.25%, improving 6.5% at least over the rest. Conclusion: It demonstrated that CRE-TSCAE showed a strong ability to extract discriminative latent features in detecting the differences among two targets with nontarget, which guaranteed increased classification accuracy. Significance: CRE-TSCAE provided an innovative and effective classification model for dual-target RSVP-BCI tasks and some insights into the neurophysiological distinction between different targets.

Keyword ：

Rapid Serial Visual Presentation (RSVP) Brain modeling Classification algorithms Electroencephalography feature extraction Convolution Task analysis Feature extraction Training Autoencoder classification

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Safety helmet wearing detection based on video surveillance is an important means of safety monitoring in many industrial scenes. The training of safety helmet wearing detection models requires large and well-labeled dataset. However, the incidence of security violations is relatively low, which results in insufficient samples for training deep detection models. Safety helmet wearing detection is a common requirement in many scenarios such as construction sites, substations, and factory workshops. Aggregating data from multiple companies for model training would improve the performance of the detection model. Traditional centralized training methods are not feasible because aggregating data in centralized locations (such as the cloud) can raise concerns about data privacy and the high cost of data communication and storage. This paper proposes FedSH, a novel cloud-edge-based federated learning framework, which learns a shared global safety helmet wearing detection model in the cloud from multiple companies at the network edges and achieves data privacy protection by keeping company data locally. In addition, this paper designs reweighting mechanisms and applies transfer learning to address class imbalance and non-IID problems in the training data, so as to obtain an accurate and personalized detection model. Extensive experiments have been conducted on real surveillance video datasets. The experimental results demonstrate that FedSH outperforms the existing widely used federated learning methods with an accuracy improvement of at least 3.4%; the reduction in accuracy is within the range of 5% compared with centralized learning methods. FedSH effectively achieves a good balance between model performance, privacy protection, and communication efficiency. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

Keyword ：

Digital storage Electric substations Accident prevention Security systems Data privacy Learning systems Large datasets

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Surveillance videos are important for public security. However, current surveillance video tasks mainly focus on classifying and localizing anomalous events. Existing methods are limited to detecting and classifying the predefined events with unsatisfactory semantic understanding, although they have obtained considerable performance. To address this issue, we propose a new research direction of surveillance video-and-language understanding (VALU), and construct the first multimodal surveillance video dataset. We manually annotate the real-world surveillance dataset UCF-Crime with fine-grained event content and timing. Our newly annotated dataset, UCA (UCF-Crime Annotation)The dataset is provided at https://xuange923.github.io/Surveillance-Video-Understanding., contains 23,542 sentences, with an average length of 20 words, and its annotated videos are as long as 110.7 hours. Furthermore, we benchmark SOTA models for four multimodal tasks on this newly created dataset, which serve as new baselines for surveillance VALU. Through experiments, we find that mainstream models used in previously public datasets perform poorly on surveillance video, demonstrating new challenges in surveillance VALU. We also conducted experiments on multimodal anomaly detection. These results demonstrate that our multimodal surveillance learning can improve the performance of anomaly detection. All the experiments highlight the necessity of constructing this dataset to advance surveillance AI. © 2024 IEEE.

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Accidental falls pose a significant threat to the elderly population, and accurate fall detection from surveillance videos can significantly reduce the negative impact of falls. Although most fall detection algorithms based on video deep learning focus on training and detecting human posture or key points in pictures or videos, we have found that the human pose-based model and key points-based model can complement each other to improve fall detection accuracy. In this paper, we propose a preposed attention capture mechanism for images that will be fed into the training network, and a fall detection model based on this mechanism. We accomplish this by fusing the human dynamic key point information with the original human posture image. We first propose the concept of dynamic key points to account for incomplete pose key point information in the fall state. We then introduce an attention expectation that predicates the original attention mechanism of the depth model by automatically labeling dynamic key points. Finally, the depth model trained with human dynamic key points is used to correct the detection errors of the depth model with raw human pose images. Our experiments on the Fall Detection Dataset and the UP-Fall Detection Dataset demonstrate that our proposed fall detection algorithm can effectively improve the accuracy of fall detection and provide better support for elderly care.

Keyword ：

preposed attention dynamic key points decision fusion fall detection complementary correction

Cite：

Copy from the list or Export to your reference management。

Abstract ：

A collaborative truck-and-drone system (TDS) can perform various tasks, such as military surveillance, recon-naissance, logistic delivery, disaster search or rescue. In order to enhance the survivability of such a system and improve the probability of task success, the task can be aborted and a rescue procedure can then be activated when a certain condition relating to malfunction or incident management is satisfied. Multiple drones can work together to complete a task with high reliability once a single drone is unable to respond to complicated emergencies. To consider this challenge, this paper designs a joint optimisation model to consider task abortion when routes of trucks and drone cluster are assumed under random attacks. Additionally, the paper considers time windows of targets and the range of the truck for protecting drones in the routines of a TDS. To minimise the expected total cost due to trucks' destruction, drones' destruction and unvisited targets, we obtain the optimal truck-and-drone routing strategy. Some numerical examples on Solomon datasets are given to illustrate the applicability of the proposed abortion strategy, present the results of sensitivity analysis on the drone cluster, and then prove the effectiveness of the optimisation method.

Keyword ：

Drone cluster Reliability Truck protection Truck-drone routing Abortion strategy

Cite：

Copy from the list or Export to your reference management。

Abstract ：

The mobile cellular network provides internet connectivity for heterogeneous Internet of Things (IoT) devices. The cellular network consists of several towers installed at appropriate locations within a smart city. These cellular towers can be utilized for various tasks, such as e-healthcare systems, smart city surveillance, traffic monitoring, infrastructure surveillance, or sidewalk checking. Security is a primary concern in data broadcasting, particularly authentication, because the strength of a cellular network's signal is much higher frequency than the associated one, and their frequencies can sometimes be aligned, posing a significant challenge. As a result, that requires attention, and without information authentication, such a barrier cannot be removed. So, we design a secure and efficient information authentication scheme for IoT-enabled devices tomitigate the flaws in the e-healthcare system. The proposed protocol security shall check formally using the Real-or-Random (ROR) model, simulated using ProVerif2.03, and informally using pragmatic discussion. In comparison, the performance phenomenon shall tackle by the already result available in the MIRACL cryptographic lab.

Keyword ：

IoT-enable device e-healthcare authentication edge computing

Cite：

Copy from the list or Export to your reference management。