Search

Existing face recognition methods cannot effectively eliminate the influence of corrupted features caused by occlusion. As the features flow deeper, the corrupted features get entangled with the effective features used for identity classification, which affects the recognition results. To address the problem, this paper designs an occluded face recognition method based on segmentation and multi-stage mask learning strategy. The model consists of three components: occlusion detection and segmentation, feature extraction, and mask learning unit. The proposed method only needs one end-to-end process to learn feature masks and deep occlusion-robust features without relying on additional occlusion detectors. The mask learning units take different sizes of occlusion segmentation representations and facial features of different stages as input, generate corresponding feature masks for different stages of feature extraction, and effectively eliminate the influence of corrupted features caused by occlusion at each stage of feature extraction through mask operations. Finally, a feature pyramid is constructed to fuse features of different stages for identity classification. Experimental results show that the proposed method can effectively improve the accuracy of occluded face recognition. The accuracy on the occluded LFW dataset and the real masked datasets MFR2 and Mask_whn reach 98.77%, 96.70% and 81.53%, respectively, which has an accuracy improvement of 2.04, 0.48 and 4.44 percentage points compared with the existing mainstream methods.

Aiming at the problems in the field of Android malicious family detection,such as insufficient code visualization method construction information,large classification effect affected by the number of data sets and low classification accuracy,an Android malicious family classification method based on multi feature file synthetic image and Xception improved model is proposed.Fir-stly,three feature files corresponding to RGB multi-channel are selected to synthesize color images.Then,the improved Xception model introduces the focal loss function to alleviate the negative impact caused by the uneven distribution of samples.Finally,the attention mechanism is integrated into the improved model to extract the image features of malicious code from different dimensions,which improves the classification effect of the model.Experimental results show that the malicious code images synthesized by the proposed method contain richer features,have higher accuracy than the mainstream malicious family classification methods,and have better classification effect for unbalanced data sets.

The electric network frequency (ENF), often referred to as the industrial heartbeat, plays a crucial role in the power system. In recent years, it has found applications in multimedia evidence identification for court proceedings and audio–visual temporal source identification. This paper introduces an ENF region classification model named UniTS-SinSpec within the UniTS framework. The model integrates the sinusoidal activation function and spectral attention mechanism while also redesigning the model framework. Training is conducted using a public dataset on the open science framework (OSF) platform, with final experimental results demonstrating that, after parameter optimization, the UniTS-SinSpec model achieves an average validation accuracy of 97.47%, surpassing current state-of-the-art and baseline models. Accurate classification can significantly aid in ENF temporal source identification. Future research will focus on expanding dataset coverage and diversity to verify the model's generality and robustness across different regions, time spans, and data sources. Additionally, it aims to explore the extensive application potential of ENF region classification in preventing crimes such as telecommunications fraud, terrorism, and child pornography. [ABSTRACT FROM AUTHOR]

Depolymerization of the cellulose part in lignocellulose to glucose is a significant step for lignocellulose valorization. As one of the main by‐products of agricultural biomass in crop‐producing filed, valorization of corn straw has attracted considerable attention. In this study, a two‐step depolymerizing strategy of high‐pressure CO2−H2O pretreatment and oxidation‐hydrolysis was applied for selective depolymerization of the cellulose component of corn straw to glucose production. Most part of the hemicellulose component could be removed through high‐pressure CO2−H2O pretreatment in the presence of low concentration of acetic acid, and then as high as 32.2 % yield of glucose was achieved in water at 170 °C for 6 h without additional catalyst. The active acid sites generated during the partial oxidation of hydroxymethyl groups to carboxyl groups on glucose units of cellulose was shown to be crucial for the efficient valorization of corn straw for glucose production. [ABSTRACT FROM AUTHOR]

The isomerization of glucose to fructose is an important process in the conversion of biomass into valuable fuels and chemicals. Development of efficient catalyst for this reaction has attracted much attention. In this study, Sn‐Beta zeolites with rich silanols were synthesized for glucose isomerization by solid‐state ion‐exchange method, where Si‐Beta zeolites with different amounts of silanols were applied as the precursors. It is confirmed that open Sn sites show much higher catalytic performance than closed Sn sites for glucose isomerization (about 2.1 times). The silanol amount in Si‐Beta not only affects the formation of framework Sn sites in Sn‐Beta but also influences the isomerization reaction. More silanols in the catalyst can promote the 1,2‐H shift in isomerization and reduce the side reactions of formation of mannose and C3 products. Over 3Sn‐Beta‐3h with rich silanols, 64 % of fructose yield was obtained. Furthermore, the prepared Sn‐Beta catalyst is stable and recyclable. High fructose yield and facile synthesis method of Sn‐Beta reported in this work will contribute to the development of biomass and sugar industry. [ABSTRACT FROM AUTHOR]

Background: Ischemic stroke (IS) is one of the leading causes of death and disability worldwide. The narrow therapeutic window (within 4.5 h) and severe hemorrhagic potential limits therapeutic efficacy of recombinant tissue type plasminogen activator (rt-PA) intravenous thrombolysis for patients. Xingnao Kaiqiao (XNKQ) acupuncture is an integral part of traditional Chinese medicine, specifically designed to address acute ischemic stroke by targeting key acupoints such as Shuigou (GV26) and Neiguan (PC6). In this study, we explored the therapeutic potential of XNKQ acupuncture in extending the time window for thrombolysis and interrogated the molecular mechanisms responsible for this effect. Methods: The effect of extending the thrombolysis window by acupuncture was evaluated via TTC staining, neuronal score evaluation, hemorrhagic transformation assay, and H&E staining. RNA sequencing (RNA-seq) technology was performed to identify the therapeutic targets and intervention mechanisms of acupuncture. Evans blue staining and transmission electron microscopy were used to assess blood–brain barrier (BBB) integrity. Immunofluorescence staining and co-immunoprecipitation were performed to evaluate the level of autophagy and apoptosis and validate their interactions with BBB endothelial cells. Results: Acupuncture alleviated infarction and neurological deficits and extended the thrombolysis window to 6 h. The RNA-seq revealed 16 potential therapeutic predictors for acupuncture intervention, which related to suppressing inflammation and restoring the function of BBB and blood vessels. Furthermore, acupuncture suppressed BBB leakage and preserved tight junction protein expression. The protective effect was associated with regulation of the autophagy–apoptosis balance in BBB endothelial cells. Acupuncture intervention dissociated the Beclin1/Bcl-2 complex, thereby promoting autophagy and reducing apoptosis. Conclusion: XNKQ acupuncture could serve as an adjunctive therapy for rt-PA thrombolysis, aiming to extend the therapeutic time window and mitigate ischemia–reperfusion injury. Acupuncture suppressed BBB disruption by regulating the autophagy–apoptosis balance, which in turn extended the therapeutic window of rt-PA in IS. These findings provide a rationale for further exploration of acupuncture as a complementary candidate co-administered with rt-PA. [ABSTRACT FROM AUTHOR]

With the proliferation of urban video surveillance systems, the abundance of surveillance video data has emerged as a pivotal asset for enhancing public safety. Within these video archives, the identification of abnormal human actions carries profound implications for security incidents. Nevertheless, existing surveillance systems primarily rely on conventional algorithms, leading to both missed incidents and false alarms. To address the challenge of automating multi-object surveillance video analysis, this study introduces a comprehensive method for the detection and recognition of multi-object abnormal actions. This study comprises a two-stage framework: the coarse detection stage employs an enhanced YOWOv2E model for spatio-temporal action detection, while the precise detection stage utilizes a two-stream network for precise action classification. In parallel, this paper presents the PSA-Dataset to address the current limitations in the field of abnormal action detection. Experimental results, collected from both public datasets and a self-built dataset, illustrate the effectiveness of the proposed method in identifying a wide spectrum of abnormal actions. This work offers valuable insights for automating the analysis of human actions in videos pertaining to public security. [ABSTRACT FROM AUTHOR]