Search

Abstract Fusarium oxysporum (Schl.) f.sp. melonis, which causes muskmelon wilt disease, is a destructive filamentous fungal pathogen, attracting more attention to the search for effective fungicides against this pathogen. In particular, Silver nanoparticles (AgNPs) have strong antimicrobial properties and they are not easy to develop drug resistance, which provides new ideas for the prevention and control of muskmelon Fusarium wilt (MFW). This paper studied the effects of AgNPs on the growth and development of muskmelon, the control efficacy on Fusarium wilt of muskmelon and the antifungal mechanism of AgNPs to F. oxysporum. The results showed that AgNPs could inhibit the growth of F. oxysporum on the PDA and in the PDB medium at 100–200 mg/L and the low concentration of 25 mg/L AgNPs could promote the seed germination and growth of muskmelon seedlings and reduce the incidence of muskmelon Fusarium wilt. Further studies on the antifungal mechanism showed that AgNPs could impair the development, damage cell structure, and interrupt cellular metabolism pathways of this fungus. TEM observation revealed that AgNPs treatment led to damage to the cell wall and membrane and accumulation of vacuoles and vessels, causing the leakage of intracellular contents. AgNPs treatment significantly hampered the growth of mycelia in the PDB medium, even causing a decrease in biomass. Biochemical properties showed that AgNPs treatment stimulated the generation of reactive oxygen species (ROS) in 6 h, subsequently producing malondialdehyde (MDA) and increasing protective enzyme activity. After 6 h, the protective enzyme activity decreased. These results indicated that AgNPs destroy the cell structure and affect the metabolisms, eventually leading to the death of fungus.

Aluminum alloy possesses poor plastic deformation ability under quasi-static stamping (QS). Hence, the plastic deformation behavior and microstructure evolution of 5052 aluminum alloy in electromagnetic driven stamping (EMDS) and QS under different heat treatment conditions were investigated in this paper. Compared with QS, EMDS can respectively improve the strength and plasticity of 5052-O aluminum alloy by 0.9% and 12%, as well as 4.6% and 30% in 5052-H32 state. The enhancement effect of EMDS on 5052-H32 aluminum alloy is more obvious. This is due to the 5052-H32 aluminum alloy has more initial dislocations, which will promotes multi-system slip and cross-slip of dislocation at high strain rates. Microscopic analysis indicates that the 5052-H32 aluminum alloy in EMDS possessed a more uniform dislocation distribution and a higher grain refinement degree. For a higher forming height, the grain boundary, dislocation and texture exhibit more obvious effects on the strength of the materials. It provides a theoretical basis for the forming mechanism of 5052 aluminum alloy during EMDS under different heat treatment conditions.

Abstract Efficient animal detection is essential for biodiversity protection. Unmanned aerial vehicles (UAVs) have been widely used because of their low costs and minimal environmental intrusion. However, using UAVs for practical animal detection poses two challenges: (a) the UAV's fly highly to avoid disturbing animals, resulting in small object detection problems; (b) the limited processing power of UAVs makes large state‐of‐the‐art (SOTA) methods (e.g., You Only Look Once V7, YOLOv7) difficult to deploy. This work proposes the WILD‐YOLO based on YOLOv7 to deal with the two problems. To detect small objects, WILD‐YOLO improves upon YOLOv7 by adding a small object detection head in the head part. To enable real‐time animal detection in field environments with UAVs, the lighten FasterNet and GhostNet have been used to significantly reduce the model size. Compared to YOLOv7, WILD‐YOLO significantly reduces the number of parameters, making it suitable for lightweight deployment on UAVs. Additionally, comparisons with other lightweight models such as YOLOv7‐tiny, YOLOv5‐s, YOLOv4‐s and MobilenetV2 on the datasets are conducted. The experimental results demonstrate that this proposed WILD‐YOLO method outperforms other approaches and has great potential for effective detection of wildlife in complex environments encountered by UAVs.

Abstract CircRNAs are a class of highly stable noncoding RNAs that play an important role in the progression of many diseases, especially cancer. In this study, high-throughput sequencing was used to screen for abnormally expressed circRNAs, and we found that circGPC3 was overexpressed in HCC tissues. However, the underlying mechanism of circGPC3 in the development and metastasis of hepatocellular carcinoma (HCC) remains unknown. In our study, we found that circGPC3 was significantly upregulated in HCC tissues and cells and that its overexpression was positively correlated with overall survival, TNM stage and lymph node metastasis. In vivo and in vitro experiments showed that circGPC3 knockdown repressed HCC cell migration, invasion and proliferation and promoted apoptosis. Mechanistically, circGPC3 promoted HCC proliferation and metastasis through the miR-578/RAB7A/PSME3 axis. Our results demonstrate that circGPC3 contributes to the progression of HCC and provides an intervention target for HCC.

As the diversity and volume of images continue to grow, the demand for efficient fine-grained image retrieval has surged across numerous fields. However, the current deep learning-based approaches to fine-grained image retrieval often concentrate solely on the top-layer features, neglecting the relevant information carried in the middle layer, even though these information contains more fine-grained identification content. Moreover, these methods typically employ a uniform weighting strategy during hash code mapping, risking the loss of critical region mapping—an irreversible detriment to fine-grained retrieval tasks. To address the above problems, we propose a novel method for fine-grained image retrieval that leverage feature fusion and hash mapping techniques. Our approach harnesses a multi-level feature cascade, emphasizing not just top-layer but also intermediate-layer image features, and integrates a feature fusion module at each level to enhance the extraction of discriminative information. In addition, we introduce an agent self-attention architecture, marking its first application in this context, which steers the model to prioritize on long-range features, further avoiding the loss of critical regions of the mapping. Finally, our proposed model significantly outperforms existing state-of-the-art, improving the retrieval accuracy by an average of 40% for the 12-bit dataset, 22% for the 24-bit dataset, 16% for the 32-bit dataset, and 11% for the 48-bit dataset across five publicly available fine-grained datasets. We also validate the generalization ability and performance stability of our proposed method by another five datasets and statistical significance tests. Our code can be downloaded from https://github.com/BJFU-CS2012/MuiltNet.git.

Accurate and intelligent identification of rare and endangered individuals of flagship wildlife species, such as Amur tiger (Panthera tigris altaica), is crucial for understanding population structure and distribution, thereby facilitating targeted conservation measures. However, many mathematical modeling methods, including deep learning models, often yield unsatisfactory results. This paper proposes an individual recognition method for Amur tigers based on an improved InceptionResNetV2 model. Initially, the YOLOv5 model is employed to automatically detect and segment facial, left stripe, and right stripe areas from images of 107 individual Amur tigers, achieving a high average classification accuracy of 97.3%. By introducing a dropout layer and a dual-attention mechanism, we enhance the InceptionResNetV2 model to better capture the stripe features of individual tigers at various granularities and reduce overfitting during training. Experimental results demonstrate that our model outperforms other classic models, offering optimal recognition accuracy and ideal loss changes. The average recognition accuracy for different body part features is 95.36%, with left stripes achieving a peak accuracy of 99.37%. These results highlight the model’s excellent recognition capabilities. Our research provides a valuable and practical approach to the individual identification of rare and endangered animals, offering significant potential for improving conservation efforts.

Accurately estimating vegetation biomass in urban forested areas is of great interest to researchers as it is a key indicator of the carbon sequestration capacity necessary for cities to achieve carbon neutrality. The emerging vegetation biomass estimation methods that use AI technologies with remote sensing images often suffer from arge estimating errors due to the diversity of vegetation and the complex three-dimensional terrain environment in urban ares. However, the high resolution of Light Detection and Ranging (i.e., LiDAR) data provides an opportunity to accurately describe the complex 3D scenes of urban forests, thereby improving estimation accuracy. Additionally, deep earning foundation models have widely succeeded in the industry, and show great potential promise to estimate vegetation biomass through processing complex and arge amounts of urban LiDAR data efficiently and accurately. In this study, we propose an efficient and accurate method called 3D-CiLBE (3DCity Long-term Biomass Estimation) to estimate urban vegetation biomass by utilizing advanced deep earning foundation models. In the 3D-CiLBE method, the Segment Anything Model (i.e., SAM) was used to segment single wood information from a arge amount of complex urban LiDAR data. Then, we modified the Contrastive Language–Image Pre-training (i.e., CLIP) model to identify the species of the wood so that the classic anisotropic growth equation can be used to estimate biomass. Finally, we utilized the Informer model to predict the biomass in the ong term. We evaluate it in eight urban areas across the United States. In the task of identifying urban greening areas, the 3D-CiLBE achieves optimal performance with a mean Intersection over Union (i.e., mIoU) of 0.94. Additionally, for vegetation classification, 3D-CiLBE achieves an optimal recognition accuracy of 92.72%. The estimation of urban vegetation biomass using 3D-CiLBE achieves a Mean Square Error of 0.045 kg/m2, reducing the error by up to 8.2% compared to 2D methods. The MSE for biomass prediction by 3D-CiLBE was 0.06kg/m2 smaller on average than the inear regression model. Therefore, the experimental results indicate that the 3D-CiLBE method can accurately estimate urban vegetation biomass and has potential for practical application.

The 2024 aluminum alloys are used in a wide range of industrial applications, and improvement in their formability and serviceability is key in the manufacturing process. Electromagnetic forming (EMF) has proven to be an effective means of improving the formability of aluminum alloys. By combining EMF and heat treatment process, three samples of 2024 aluminum alloy were designed: Sample A (annealing + EMF + solid-solution + aging), Sample B (solid solution + EMF + aging), and Sample C (solid solution + pre-aging + EMF + aging). The effects of three heat treatment regimens on the properties and microstructure of 2024 aluminum alloy were studied by hardness test, intercrystalline corrosion, and exfoliation corrosion, as well as by microscopic characterization techniques including scanning electron microscopy and transmission electron microscopy. The results show that the dislocations-induced deformation could shorten the time to peak aging and led to the increase in peak strength. Sample C exhibited the highest strength and sample A exhibited the highest elongation and corrosion resistance. The microscopic results show that the differences in properties were mainly influenced by the distribution of precipitated phases and the width of the precipitation-free zone. The discrete and coarse grain boundary precipitations make sample A have excellent corrosion resistance. The fine and dense precipitated phases provide good strength for samples B and C, but also reduces the elongation. This research has important implications for rational formulation based on the combination of EMF and heat treatment processes for the fabrication of Al–Cu–Mg alloys. Conclusions: may be made more concise. They should focus on the mechanisms responsible for high strength or corrosion resistance rather than the values obtained that are shown in results.

Background: The rapid development of modern technologies renders a convenient and efficient solution to implement Electronic Health Records (EHRs) systems. The rapid growth of healthcare data has a distinctive attribute of digital transformations. The big datasets of healthcare, their complexity and their dynamic nature have posed severe challenges associated with the analysis, pre-processing, privacy, security, storage, usability and data exchange. Material and Methods: We have performed the Systematic Literature Review (SLR) and followed the Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) methodology. SLR refers to the methodology that discovers, analyses and accesses recent research literature related to the subject field. The research papers were searched from academic repositories like IEEE, WOS, Scopus and PubMed for the previous five years on March 2023. Results: The designed search string provides 199 research articles in total. We filter the research articles based on inclusion-exclusion strategies and quality assessment metrics. Six main criteria for research inclusion-exclusion for SLR are formulated. These works of literature insight into 1) the issues associated with interoperability and security of EHRs by using the Blockchain (BC) technology, 2) different frameworks and tools to improve privacy and security in the healthcare domain, 3) the open issues of using BC technology in the electronic healthcare domain, 4) the standardized ways to store EHRs, 5) various ways to handle the big data using the BC systems and 6) the usage of Federated Learning (FL) to preserve the privacy of EHRs in the healthcare domain. We acquired 46 research articles based on the criteria (inclusion-exclusion) that investigate the above-mentioned issues. Conclusion: The SLR will serve as the state-of-the-art (SOTA) for future researchers in the field of BC in healthcare. Additionally, the paper provides insights to the new researchers to revolutionize the healthcare domain by adopting the latest digitalized technologies. The proposed study identified various reflections. It analyzed the architectural mechanism that supports the security and interoperability of EHRs. Secondly, the study described different tools and frameworks to improve the privacy and security of EHRs using the BC. Thirdly, the open issues of storing and preserving the EHRs using BC in the healthcare system were determined. Fourth, it analyzed and provided a detailed view of using standardized ways for storing and handling big data by using the BC system. Lastly, the usage of FL to preserve the privacy of EHRs was analyzed.

It has been reported that the forming limit of materials can be improved during electromagnetic forming (EMF). However, the detailed mechanism of this phenomenon remains unclear. The effect of initial state on the EMF process of AA1060 is systematically investigated. AA1060-O and AA1060-H24 alloys are subjected to quasi-static (Q-S) stamping and EMF, respectively. Compared to the Q-S stamping, the forming limit and hardness of AA1060-H24 sheet are increased by 68.3% and 9.4% under EMF. However, the forming limit of AA1060-O sheet is not improved. It is found that both groups of aluminum alloys exhibit high dislocation density after Q-S stamping and the dislocation movement occurs via the plane slip mode. Moreover, dislocation cells and wavy slips are observed in AA1060-H24 sample after EMF. In the case of AA1060-O sample, the intragranular dislocation density is low without wavy slip. Therefore, the wavy slip mode may be the reason for improved forming limit under the influence of EMF. In addition, the textural strength of EMF sample is different from the Q-S deformation sample and EMF sample exhibits a higher Taylor factor value. The changes in grain size, dislocation density and texture strength alter the overall strength. The current study provides the theoretical basis for the mechanism of improved forming limit under the action of EMF.

Vibrio vulnificus is a facultative anaerobic, alkalophilic, halophilic, mesophilic, Gram-negative bacterium that can cause severe wound infection, sepsis and diarrhea. This paper reported a case of 85-year-old male patient infected with Vibrio vulnificus due to being stabbed by a sea shrimp. This patient also had diabetes with a long history of alcoholism. Due to bacterial pathogenicity and the patient's underlying diseases, his condition deteriorated rapidly. Based on the rapid diagnosis of Vibrio vulnificus using the next-generation sequencing（NGS）technology and blood culture method, as well as the selection of the most effective antibiotics via drug sensitivity test, this patient underwent precise antimicrobial treatment, thorough debridement and drainage within the shortest possible time, and thus the prognosis of this patient was greatly improved. In this paper, we have systematically explored the epidemiology, clinical features, diagnosis and treatment of Vibrio vulnificus infection, thus providing a practical reference for the clinicians to quickly identify and treat possible Vibrio vulnificus infection in diabetic patients after contacting with sea water or seafood.

Recently, researchers have extensively explored various methods for electronic medical record named entity recognition, including character-based, word-based, and hybrid methods. Nonetheless, these methods frequently disregard the semantic context of entities within electronic medical records, leading to the creation of subpar-quality clinical knowledge bases and obstructing the discovery of clinical knowledge. In response to these challenges, we propose a novel purpose-driven SoftLexicon-RoBERTa-BiLSTM-CRF (SLRBC) model for electronic medical records named entity recognition. SLRBC leverages the fusion of SoftLexicon and RoBERTa to incorporate the word lexicon information from electronic medical records into the character representations, enhancing the model’s semantic embedding representations. This purpose-driven approach helps achieve a more comprehensive representation and avoid common segmentation errors, consequently boosting the accuracy of entity recognition. Furthermore, we employ the classical BiLSTM-CRF framework to capture contextual information of entities more effectively. In order to assess the performance of SLRBC, a series of experiments on the public datasets of CCKS2018 and CCKS2019 were conducted. The experimental results demonstrate that SLRBC can efficiently extract entities from Chinese electronic medical records. The model attains F1 scores of 94.97% and 85.40% on CCKS2018 and CCKS2019, respectively, exhibiting outstanding performance in the extraction and utilization efficiency of clinical information.

Over the past few decades, the food industry has undergone revolutionary changes due to the impacts of globalization, technological advancements, and ever-evolving consumer demands. Artificial intelligence (AI) and big data have become pivotal in strengthening food safety, production, and marketing. With the continuous evolution of AI technology and big data analytics, the food industry is poised to embrace further changes and developmental opportunities. An increasing number of food enterprises will leverage AI and big data to enhance product quality, meet consumer needs, and propel the industry toward a more intelligent and sustainable future. This review delves into the applications of AI and big data in the food sector, examining their impacts on production, quality, safety, risk management, and consumer insights. Furthermore, the advent of Industry 4.0 applied to the food industry has brought to the fore technologies such as smart agriculture, robotic farming, drones, 3D printing, and digital twins; the food industry also faces challenges in smart production and sustainable development going forward. This review articulates the current state of AI and big data applications in the food industry, analyses the challenges encountered, and discusses viable solutions. Lastly, it outlines the future development trends in the food industry.

There has always been a concern about the hydrodynamic interaction between ships in a flow field. In this study, the RANS method is utilized, and the hydrodynamic interference between two KRISO Container Ships (KCS) operating in still water with identical parameters and sailing at the same speed is investigated. Overlapping grids are used to simulate ship motion, and the VOF method is used to simulate the free surface. A KCS ship model of 1:1 size without propeller is used in the study. In order to study the change principle of the Kelvin flow field created by a single ship, the resistance coefficient and the flow field surrounding the ship are first calculated for the monohull case. Then the influence of interference between two ships is examined at various speeds and intervals and compared with the monohull case. It is discovered that the resistance coefficient of the following ship is reduced in a certain speed interval under the influence of the leading ship, where the maximum reduction can be up to 24.3%. The reason for this phenomenon may be that the wave around the following ship is superimposed on the transverse wave behind the leading ship. When the height of the wave is suppressed, the following ship’s resistance is reduced.

Anthocyanins are widespread water-soluble pigments in the plant kingdom. Anthocyanin accumulation is activated by the MYB-bHLH-WD40 (MBW) protein complex. In Arabidopsis, the R2R3-MYB transcription factor PAP1 activates anthocyanin biosynthesis. While prior research primarily focused on seedlings, seeds received limited attention. This study explores PAP1’s genome-wide target genes in anthocyanin biosynthesis in seeds. Our findings confirm that PAP1 is a positive regulator of anthocyanin biosynthesis in Arabidopsis seeds. PAP1 significantly increased anthocyanin content in developing and mature seeds in Arabidopsis. Transcriptome analysis at 12 days after pollination reveals the upregulation of numerous genes involved in anthocyanin accumulation in 35S:PAP1 developing seeds. Chromatin immunoprecipitation and dual luciferase reporter assays demonstrate PAP1’s direct promotion of ten key genes and indirect upregulation of TT8, TTG1, and eight key genes during seed maturation, thus enhancing seed anthocyanin accumulation. These findings enhance our understanding of PAP1’s novel role in regulating anthocyanin accumulation in Arabidopsis seeds.

Under the strict carbon emission quota policy in China, the urban carbon price directly affects the operation of enterprises, as well as forest carbon sequestration. As a result, accurately forecasting carbon prices has been a popular research topic in forest science. Similar to stock prices, urban carbon prices are difficult to forecast using simple models with only historical prices. Fortunately, urban remote sensing images containing rich human economic activity information reflect the changing trend of carbon prices. However, properly integrating remote sensing data into carbon price forecasting has not yet been investigated. In this study, by introducing the powerful transformer paradigm, we propose a novel carbon price forecasting method, called MFTSformer, to uncover information from urban remote sensing and historical price data through the encoder–decoder framework. Moreover, a self-attention mechanism is used to capture the intrinsic characteristics of long-term price data. We conduct comparison experiments with four baselines, ablation experiments, and case studies in Guangzhou. The results show that MFTSformer reduces errors by up to 52.24%. Moreover, it outperforms the baselines in long-term accurate carbon price prediction (averaging 15.3%) with fewer training resources (it converges rapidly within 20 epochs). These findings suggest that the effective MFTSformer can offer new insights regarding AI to urban forest research.

Abstract Frying is a common food processing method because fried food is popular with consumers for its attractive colour and crisp taste. What’s concerning is that the complex physical and chemical reactions occurring during deep frying are harmful to the well-being of people. For this reason, researchers proposed various detecting methods to assess frying oil deterioration. Some studies design sensor probe, others utilize spectroscopic related methods. However, these methods all need the participating of professionals and expensive instruments. Some of the methods can only function on a fixed temperature. To fix the defects of the above models, in this study, we make use of recent advances in machine learning, specifically generative adversarial networks (GAN). We propose a GAN-based regression model to predict frying oil deterioration. First, we conduct deep frying experiments and record the values of indexes we choose under different temperature and frying time. After collecting the data, we build a GAN-based regression model and train it on the dataset. Finally, we test our model on the test set and analyze the experimental results. Our results suggest that the proposed model can predict frying oil deterioration without experiments. Our model can be applied to other regression problems in various research areas, including price forecasting, trend analysis and so on.

Abstract Rice quality affects social stability, consumer health, and corporate brand benefit. The traditional supply chain traceability management system is centralized, monopolized, asymmetric, and opaque. It is the main factor leading to frequent food safety incidents. This paper proposes a technological quality control system for rice supply chain to protect rice products quality and safety. Firstly, it adopts risk assessment and traceability mechanism to prevent the hazard factors in the production and processing. Then, to prevent spoiled food from endangering the consumers’ health and reduce food waste, it explores a shelf life model of rice products to predict the remaining shelf life of products. Finally, this paper constructs a decentralized traceability management system based on blockchain and IoT, which enables consumers to access the real information of rice products and helps supervisors to monitor the quality of products in the supply chain.

Hyperosmolarity of the renal medulla is essential for urine concentration and water homeostasis. However, how renal medullary collecting duct (MCD) cells survive and function under harsh hyperosmotic stress remains unclear. Using RNA-Seq, we identified SLC38A2 as a novel osmoresponsive neutral amino acid transporter in MCD cells. Hyperosmotic stress-induced cell death in MCD cells occurred mainly via ferroptosis, and it was significantly attenuated by SLC38A2 overexpression but worsened by Slc38a2-gene deletion or silencing. Mechanistic studies revealed that the osmoprotective effect of SLC38A2 is dependent on the activation of mTORC1. Moreover, an in vivo study demonstrated that Slc38a2-knockout mice exhibited significantly increased medullary ferroptosis following water restriction. Collectively, these findings reveal that Slc38a2 is an important osmoresponsive gene in the renal medulla and provide novel insights into the critical role of SLC38A2 in protecting MCD cells from hyperosmolarity-induced ferroptosis via the mTORC1 signalling pathway.

Drones are widely used for wildlife monitoring. Deep learning algorithms are key to the success of monitoring wildlife with drones, although they face the problem of detecting small targets. To solve this problem, we have introduced the SE-YOLO model, which incorporates a channel self-attention mechanism into the advanced real-time object detection algorithm YOLOv7, enabling the model to perform effectively on small targets. However, there is another barrier; the lack of publicly available UAV wildlife aerial datasets hampers research on UAV wildlife monitoring algorithms. To fill this gap, we present a large-scale, multi-class, high-quality dataset called WAID (Wildlife Aerial Images from Drone), which contains 14,375 UAV aerial images from different environmental conditions, covering six wildlife species and multiple habitat types. We conducted a statistical analysis experiment, an algorithm detection comparison experiment, and a dataset generalization experiment. The statistical analysis experiment demonstrated the dataset characteristics both quantitatively and intuitively. The comparison and generalization experiments compared different types of advanced algorithms as well as the SE-YOLO method from the perspective of the practical application of UAVs for wildlife monitoring. The experimental results show that WAID is suitable for the study of wildlife monitoring algorithms for UAVs, and SE-YOLO is the most effective in this scenario, with a mAP of up to 0.983. This study brings new methods, data, and inspiration to the field of wildlife monitoring by UAVs.

In a complicated forest environment, it is usual to install many ground-fixed devices, and patrol personnel periodically collects data from the device to detect forest pests and valuable wild animals. Unlike human patrols, UAV (Unmanned Aerial Vehicles) may collect data from ground-based devices. The existing UAV path planning method for fixed-point devices is usually acceptable for simple UAV flight scenes. However, it is unsuitable for forest patrol. Meanwhile, when collecting data, the UAV should consider the timeliness of the collected data. The paper proposes two-point path planning and multi-point path planning methods to maximize the amount of fresh information collected from ground-fixed devices in a complicated forest environment. Firstly, we adopt chaotic initialization and co-evolutionary algorithmto solve the two-point path planning issue considering all significant UAV performance and environmental factors. Then, a UAV path planning method based on simulated annealing is proposed for the multi-point path planning issue. In the experiment, the paper uses benchmark functions to choose an appropriate parameter configuration for the proposed approach. On simulated simple and complicated maps, we evaluate the effectiveness of the proposed method compared to the existing pathplanning strategies. The results reveal that the proposed ways can effectively produce a UAV patrol path with higher information freshness in fewer iterations and at a lower computing cost, suggesting the practical value of the proposed approach.

Silver nanoparticles (AgNPs) have raised public concern due to their widespread application in the field of agriculture, medicine, and environment and their potential toxic effects on humans and the environments. In this study, biosynthesis of nanosilver particles mediated by Trichoderma longibranchiatum using orthogonal experimental design (OED) was optimized. Silkworm larvae were exposed via the mulberry leaves to AgNPs to evaluate their toxic effects. The results showed that 2 mmol/L silver nitrate and 55 °C of reaction temperature at pH 7.0 for 24 h were the optimum values for AgNPs biosynthesis with the synthesis amount and antifungal activity of AgNPs as the indices. The characterization of the biosynthesized AgNPs was conducted using electron microscopy, energy dispersive X-ray analysis (EDS), UV/visible spectrophotometry, Fourier transform infrared spectroscopy (FTIR), and X-ray diffraction (XRD). The crystalline structured nanoparticles were spherical or polyhedral with a mean size ranging about 5–50 nm. FTIR showed that many functional group moieties (–OH, –CH3, –C–O, etc.) involved as a capping and reducing agent in AgNPs biosynthesis. After the larvae were fed with 50 mg/mL AgNPs, there were no obvious adverse effects on the growth of larvae and cocoon quality. Further supplement of AgNPs-B could promote the weight of larvae and the cocoon shell ratio. The data presented herein provided valuable information on a reliable eco-friendly, simple, low-cost biosynthesis of AgNPs and its biosafety evaluation which may contribute to its increased application in the future.

Identifying influential nodes is a key research topic in complex networks, and there have been many studies based on complex networks to explore the influence of nodes. Graph neural networks (GNNs) have emerged as a prominent deep learning architecture, capable of efficiently aggregating node information and discerning node influence. However, existing graph neural networks often ignore the strength of the relationships between nodes when aggregating information about neighboring nodes. In complex networks, neighboring nodes often do not have the same influence on the target node, so the existing graph neural network methods are not effective. In addition, the diversity of complex networks also makes it difficult to adapt node features with a single attribute to different types of networks. To address the above problems, the paper constructs node input features using information entropy combined with the node degree value and the average degree of the neighbor, and proposes a simple and effective graph neural network model. The model obtains the strength of the relationships between nodes by considering the degree of neighborhood overlap, and uses this as the basis for message passing, thereby effectively aggregating information about nodes and their neighborhoods. Experiments are conducted on 12 real networks, using the SIR model to verify the effectiveness of the model with the benchmark method. The experimental results show that the model can identify the influence of nodes in complex networks more effectively.

Social media is important for providing text information; however, due to its informal and unstructured nature, traditional named entity recognition (NER) methods face the challenge of achieving high accuracy when dealing with social media data. This paper proposes a new method for social media named entity recognition with data augmentation. First, we pre-train the language model by using a bi-directional encoder representation of the transformer (BERT) to obtain a semantic vector of the word based on the contextual information of the word. Then, we obtain similar entities via data augmentation methods and perform substitution or semantic transformation on these entities. After that, the input into the Bi-LSTM model is trained and then fused and fine-tuned to obtain the best label. In addition, our use of the self-attentive layer captures the essential information of the features and reduces the reliance on external information. Experimental results on the WNUT16, WNUT17, and OntoNotes 5.0 datasets confirm the effectiveness of our proposed model.

With the rapid development of social networks, users pay more and more attention to the protection of personal information. However, the transmission of users’ personal information through social networks will inevitably lead to privacy leakage and make users attacked. A large amount of privacy information can be inferred from the content and social traces published by users, which leads to the rise of privacy inference technology for users in social networks. Social relationship inference and attribute inference are two basic attacks on users’ privacy in social networks. This is the first systematic review of privacy inference attacks in social networks. The purpose of this retrospective study is to provide a global summary, summarizing the time trend of the topic, and show the evolution of the topic in the past 15 years. In addition, this paper discusses the trend and development of this topic and finally looks forward to future work. The contribution of our work is helpful for researchers to continue their research in this field.

Aspect-based sentiment analysis (ABSA) is a task in natural language processing (NLP) that involves predicting the sentiment polarity towards a specific aspect in text. Graph neural networks (GNNs) have been shown to be effective tools for sentiment analysis tasks, but current research often overlooks affective information in the text, leading to irrelevant information being learned for specific aspects. To address this issue, we propose a novel GNN model, MHAKE-GCN, which is based on the graph convolutional neural network (GCN) and multi-head attention (MHA). Our model incorporates external sentiment knowledge into the GCN and fully extracts semantic and syntactic information from a sentence using MHA. By adding weights to sentiment words associated with aspect words, our model can better learn sentiment expressions related to specific aspects. Our model was evaluated on four publicly benchmark datasets and compared against twelve other methods. The results of the experiments demonstrate the effectiveness of the proposed model for the task of aspect-based sentiment analysis.

The surface appearance of milk powders is a crucial quality property since the roughness of the milk powder determines its functional properties, and especially the purchaser perception of the milk powder. Unfortunately, powder produced from similar spray dryers, or even the same dryer but in different seasons, produces powder with a wide variety of surface roughness. To date, professional panelists are used to quantify this subtle visual metric, which is time-consuming and subjective. Consequently, developing a fast, robust, and repeatable surface appearance classification method is essential. This study proposes a three-dimensional digital photogrammetry technique for quantifying the surface roughness of milk powders. A contour slice analysis and frequency analysis of the deviations were performed on the three-dimensional models to classify the surface roughness of milk powder samples. The result shows that the contours for smooth-surface samples are more circular than those for rough-surface samples, and the smooth-surface samples had a low standard deviation; thus, milk powder samples with the smoother surface have lower Q (the energy of the signal) values. Lastly, the performance of the nonlinear support vector machine (SVM) model demonstrated that the technique proposed in this study is a practicable alternative technique for classifying the surface roughness of milk powders.

The research on image-classification-adversarial attacks is crucial in the realm of artificial intelligence (AI) security. Most of the image-classification-adversarial attack methods are for white-box settings, demanding target model gradients and network architectures, which is less practical when facing real-world cases. However, black-box adversarial attacks immune to the above limitations and reinforcement learning (RL) seem to be a feasible solution to explore an optimized evasion policy. Unfortunately, existing RL-based works perform worse than expected in the attack success rate. In light of these challenges, we propose an ensemble-learning-based adversarial attack (ELAA) targeting image-classification models which aggregate and optimize multiple reinforcement learning (RL) base learners, which further reveals the vulnerabilities of learning-based image-classification models. Experimental results show that the attack success rate for the ensemble model is about 35% higher than for a single model. The attack success rate of ELAA is 15% higher than those of the baseline methods.

Non-ferrous metallic materials are considered to be fundamental materials for manufacturing in-dustries, i [...]

It is estimated that 50,000-60,000 pregnant people in the United States (US) experience severe maternal morbidity (SMM). SMM includes life-threatening conditions, such as acute myocardial infarction, acute renal failure, amniotic fluid embolism, disseminated intravascular coagulation, or sepsis. Prior research has identified both rising rates through 2014 and wide racial disparities in SMM. While reducing maternal death and SMM has been a global goal for the past several decades, limited progress has been made in the US in achieving this goal. Our objectives were to examine SMM trends from 1998-2018 to identify factors contributing to the persistent and rising rates of SMM by race/ethnicity and describe the Black non-Hispanic/White non-Hispanic rate ratio for each SMM condition. We used a population-based data system that links delivery records to their corresponding hospital discharge records to identify SMM rates (excluding transfusion) per 10, 000 deliveries and examined the trends by race/ethnicity. We then conducted stratified analyses separately for Black and White birthing people. While the rates of SMM during the same periods steadily increased for all racial/ethnic groups, Black birthing people experienced the greatest absolute increase compared to any other race/ethnic group going from 69.4 in 1998-2000 to 173.7 per 10,000 deliveries in 2016-2018. In addition, we found that Black birthing people had higher rates for every individual condition compared to White birthing people, with rate ratios ranging from a low of 1.11 for heart failure during surgery to a high of 102.4 for sickle cell anemia. Obesity was not significantly associated with SMM among Black birthing people but was associated with SMM among White birthing people [aRR 1.18 (95% CI: 1.02, 1.36)]. An unbiased understanding of how SMM has affected different race/ethnicity groups is key to improving maternal health and preventing SMM and mortality among Black birthing people. SMM needs to be addressed as both a medical and public health challenge.

Biodegradable household garbage contains a large amount of nitrogen, which could be used as organic fertilizer to produce organic food and significantly reduce synthetic nitrogen fertilizers. There is limited information on how large the nitrogen reservoir of biodegradable household garbage is in a certain country or region. Here we took China as a case, analyzed the amount of biodegradable household garbage resources and their nitrogen reservoirs. It was noted that the biodegradable household garbage mainly included food waste, waste paper and wood chips, with the amount being 31.56, 29.55, and 6.45 × 106 t·a−1, respectively. Accordingly, the nitrogen reservoirs were 65.31 × 104, 6.80 × 104, and 3.81 × 104 t·a−1 in China. The nitrogen reservoir of food waste accounted for 86% of the total nitrogen reservoir of biodegradable household garbage, which was equivalent to 11% of the amount of actual absorption for synthetic nitrogen fertilizers (6.20 × 106 t·a−1) by agriculture plants in China. Our findings provided a scientific basis for the classification and utilization of biodegradable household garbage.

Food safety is essential to national economy and people's livelihood. A good food safety system is extremely important for maintaining social stability and providing scientific data for government decision. Big data provides a new approach to food safety. Through the integration of the data in the whole industrial chain, it will greatly improve the data analysis ability and help in discovering the potential valuable information. It could provide scientific decision-making suggestions for regulators, producers and consumers. It will provide a solution for timely warning of food safety incidents, the accurate traceability and accountability of food products. This paper will briefly introduce some existing big data platforms in food safety area. Then, it will discuss the challenges such as multi-sources data analysis, visualization and market mechanism. At the end of this paper, the future development trend of big data in food safety area is discussed.

Heterogeneous graph representation learning is to learn effective representations for nodes or (sub)graphs, which preserve node attributes and structural information. However, it is challenging to design a representation learning method for heterogeneous information networks (HINs) due to their diversity. Most of the existing HIN-oriented learning methods define a series of meta-paths. Then, they aggregate the representations learned from different meta-paths in the same hidden space. These methods do not consider semantic differences of different meta-paths, which leads to semantic confusion. And further affects the effectiveness of the learned representation. Given these issues, we introduce a Semantic Aware HIN Representation learning Network (SAHRN), which takes into account the semantics of different meta-paths. We mitigate the problem of semantic confusion by projecting nodes’ features into different hidden spaces separately according to different meta-paths. To further expand the scope of aggregation and enrich the aggregated information, we also design various variants of our model by adding layer aggregation. Extensive experiments on three standard HIN datasets show that SAHRN achieves consistent improvements compared to state-of-the-art graph representation learning methods. The experiments and analyses on each component of the model show the effectiveness of the proposed method. The source code is available on https://github.com/pingpingand/SAHRN.

Reading is an important skill for human beings to obtain information, whose acquisition is a major learning task for children. Especially, compared with single word reading, text reading requires an integration of multiple cognitive processes, which makes its underlying neural developmental mechanism not only extremely complicated but also remained poorly understood. Employing the graph theory analysis method, the present study explored the development of brain in the context of story reading from the perspective of connectomics. Forty-two primary school students and thirty-two adults read the stories in the functional magnetic resonance imaging (fMRI) experiment. We found that compared with children, adults had increased connectivity strength, nodal degree, and modular interactions for vision-related and semantics-related brain regions while decreased connectivity strength, nodal degree, and modular interactions for phonology-related brain regions. Brain-behavior association analysis suggested that the transmission to vision-related brain circuits would enhance the reading performance in adults, whereas phonology-related brain circuits played important roles in children’s reading before they develop into fluent readers. Collectivity, we highlight a shift from reliance on phonology-related networks to semantics-related and vision-related networks with age for text reading, which provides insights into the underlying neural signature of developmental cognitive mechanisms.

The traditional food supervision system has problems such as lack of industry chain and data fragmentation, which has caused the phenomenon of field regulation to be uncomprehensive in the existing regulatory system and the disposal of response lag. Combining the characteristics of blockchain such as distribution, transparent, and collegiality with the actual needs of regional autonomy, we propose the hierarchical multi-domain blockchain (HMDBC) network structure and the secondary-check mechanism, which can support timely correction and replacement of the malicious supervision nodes by regional nodes co-governance, auxiliary verification of supervision nodes, and arbitration of superior regions. In order to optimize the supervision nodes election, we proposed fuzzy comprehensive evaluation model of credibility, which can be used to objectively and fairly evaluate the comprehensive reputation of each node in that region by considering various influencing factors of node performance indicators. Furthermore, we designed the data block structure model, which can support the supervisor node replacement. Our system can perform automatic food quality detection and warning of substandard food in the entire industrial chain, with the use of smart contracts combined with the food industry standards. Finally, comparing the complexity of the traditional blockchain system with PBFT consortium, our system is more secure, with lower broadcast complexity.

In this study, a visual search task was conducted on children with comorbid attention deficit/hyperactivity disorder (ADHD) and developmental dyslexia (DD), children with pure ADHD, and typically developing children to explore the pathogenesis of comorbidity between ADHD and DD. Participants searched for the target character from five characters in each trial during the task. The distractors included orthographically similar characters, homophones, unrelated characters, and characters of a different color (i.e., red). Results showed that the clinical groups produced longer first fixation duration than the control group in all types of distractors. Children with ADHD comorbid DD were also more susceptible to characters with the distracting red color in gaze duration and total viewing time than were children with pure ADHD and healthy controls. The implication of comorbidity (ADHD + DD) on the pathogenesis was discussed. These results may be helpful for the diagnosis and treatment of ADHD with comorbid DD.

Food supply chain plays a vital role in human health and food prices. Food supply chain inefficiencies in terms of unfair competition and lack of regulations directly affect the quality of human life and increase food safety risks. This work merges Hyperledger Fabric, an enterprise-ready blockchain platform with existing conventional infrastructure, to trace a food package from farm to fork using an identity unique for each food package while keeping it uncomplicated. It keeps the records of business transactions that are secured and accessible to stakeholders according to the agreed set of policies and rules without involving any centralized authority. This paper focuses on exploring and building an uncomplicated, low-cost solution to quickly link the existing food industry at different geographical locations in a chain to track and trace the food in the market.

Significant progress has been made in generating counterfeit images and videos. Forged videos generated by deepfaking have been widely spread and have caused severe societal impacts, which stir up public concern about automatic deepfake detection technology. Recently, many deepfake detection methods based on forged features have been proposed. Among the popular forged features, textural features are widely used. However, most of the current texture-based detection methods extract textures directly from RGB images, ignoring the mature spectral analysis methods. Therefore, this research proposes a deepfake detection network fusing RGB features and textural information extracted by neural networks and signal processing methods, namely, MFF-Net. Specifically, it consists of four key components: (1) a feature extraction module to further extract textural and frequency information using the Gabor convolution and residual attention blocks; (2) a texture enhancement module to zoom into the subtle textural features in shallow layers; (3) an attention module to force the classifier to focus on the forged part; (4) two instances of feature fusion to firstly fuse textural features from the shallow RGB branch and feature extraction module and then to fuse the textural features and semantic information. Moreover, we further introduce a new diversity loss to force the feature extraction module to learn features of different scales and directions. The experimental results show that MFF-Net has excellent generalization and has achieved state-of-the-art performance on various deepfake datasets.

Many deepfake-image forensic detectors have been proposed and improved due to the development of synthetic techniques. However, recent studies show that most of these detectors are not immune to adversarial example attacks. Therefore, understanding the impact of adversarial examples on their performance is an important step towards improving deepfake-image detectors. This study developed an anti-forensics case study of two popular general deepfake detectors based on their accuracy and generalization. Herein, we propose the Poisson noise DeepFool (PNDF), an improved iterative adversarial examples generation method. This method can simply and effectively attack forensics detectors by adding perturbations to images in different directions. Our attacks can reduce its AUC from 0.9999 to 0.0331, and the detection accuracy of deepfake images from 0.9997 to 0.0731. Compared with state-of-the-art studies, our work provides an important defense direction for future research on deepfake-image detectors, by focusing on the generalization performance of detectors and their resistance to adversarial example attacks.

Text classification is a fundamental research direction, aims to assign tags to text units. Recently, graph neural networks (GNN) have exhibited some excellent properties in textual information processing. Furthermore, the pre-trained language model also realized promising effects in many tasks. However, many text processing methods cannot model a single text unit’s structure or ignore the semantic features. To solve these problems and comprehensively utilize the text’s structure information and semantic information, we propose a Bert-Enhanced text Graph Neural Network model (BEGNN). For each text, we construct a text graph separately according to the co-occurrence relationship of words and use GNN to extract text features. Moreover, we employ Bert to extract semantic features. The former part can take into account the structural information, and the latter can focus on modeling the semantic information. Finally, we interact and aggregate these two features of different granularity to get a more effective representation. Experiments on standard datasets demonstrate the effectiveness of BEGNN.

Plant diseases can harm crop growth, and the crop production has a deep impact on food. Although the existing works adopt Convolutional Neural Networks (CNNs) to detect plant diseases such as Apple Scab and Squash Powdery mildew, those methods have limitations as they rely on a large amount of manually labeled data. Collecting enough labeled data is not often the case in practice because: plant pathogens are variable and farm environments make collecting data difficulty. Methods based on deep learning suffer from low accuracy and confidence when facing few-shot samples. In this paper, we propose local feature matching conditional neural adaptive processes (LFM-CNAPS) based on meta-learning that aims at detecting plant diseases of unseen categories with only a few annotated examples, and visualize input regions that are ‘important’ for predictions. To train our network, we contribute Miniplantdisease-Dataset that contains 26 plant species and 60 plant diseases. Comprehensive experiments demonstrate that our proposed LFM-CNAPS method outperforms the existing methods.

A huge amount of data is being produced in the food industry, but the application of big data—regulatory, food enterprise, and food-related media data—is still in its infancy. Each data source has the potential to develop the food industry, and big data has broad application prospects in areas like social co-governance, exploit of consumption markets, quantitative production, new dishes, take-out services, precise nutrition and health management. However, there are urgent problems in technology, health and sustainable development that need to be solved to enable the application of big data to the food industry.

Food is a daily requirement for everyone, while production patterns are seasonal. Producing sufficient nutrients is becoming more difficult because water and soil resources are already stressed and are becoming increasingly strained by climate change. Improving food security requires expertise in various areas, including sophisticated climate models, genetics research, market and household behaviour modelling, political shock modelling, and comprehensive environmental research. Additionally, governments stockpile grains to enhance national food security. These reserves should engage in markets only according to clear and transparent regulations and within defined price ranges to facilitate market functioning. It increases the demand for better technology in public administration to boost the management and distribution capacity while concentrating on improved controls and transparent governance systems. Blockchain technology emerges as a promising technology to enhance visibility, transparency, and data integrity with an immutable distributed ledger to increase trust in the parties’ business transactions. This paper discusses blockchain technology and its potential role in strategic grain reserve management.

The Variational AutoEncoder (VAE) has made significant progress in text generation, but it focused on short text (always a sentence). Long texts consist of multiple sentences. There is a particular relationship between each sentence, especially between the latent variables that control the generation of the sentences. The relationships between these latent variables help in generating continuous and logically connected long texts. There exist very few studies on the relationships between these latent variables. We proposed a method for combining the Transformer-Based Hierarchical Variational AutoEncoder and Hidden Markov Model (HT-HVAE) to learn multiple hierarchical latent variables and their relationships. This application improves long text generation. We use a hierarchical Transformer encoder to encode the long texts in order to obtain better hierarchical information of the long text. HT-HVAE’s generation network uses HMM to learn the relationship between latent variables. We also proposed a method for calculating the perplexity for the multiple hierarchical latent variable structure. The experimental results show that our model is more effective in the dataset with strong logic, alleviates the notorious posterior collapse problem, and generates more continuous and logically connected long text.

After the General Data Protection Regulation (GDPR) was introduced, some organizations and big data companies shared data without conducting any privacy protection and compliance authentication, which endangered user data security, and were punished financially for this reason. This study proposes a blockchain-based GDPR compliance data sharing scheme, aiming to promote compliance with regulations and provide a tool for interaction between users and service providers to achieve data security sharing. The zero-knowledge Succinct Non-Interactive Arguments of Knowledge (zk-SNARK) algorithm is adopted for protecting data and ensure that the user’s private data can satisfy the individual requirements of the service provider without exposing user data. The proposed scheme ensures mutual authentication through the Proof of Authority consensus based on the Committee Endorsement Mechanism (CEM-PoA), and prevents nodes from doing evil using the reputation incentive mechanism. Theoretical analysis and performance comparison indicate that the scheme meets the confidentiality, availability, and other indicators. It has superiority in efficiency and privacy protection compared with other schemes.

High-strength 7075 aluminum alloy is widely used in the aerospace industry. The forming performance of 7075 aluminum alloy is poor at room temperature. Therefore, hot forming is mainly adopted. Electromagnetic forming is a high-speed forming technology that can significantly improve the forming limit of difficult-to-deform materials. However, there are few studies on electromagnetic hot forming of 7075-T6 aluminum alloy. In this study, the deformation behavior of 7075-T6 aluminum alloy in the temperature range of 25 °C to 400 °C was investigated. As the temperature increased, the sheet forming height first decreased, then increased. When the forming temperature is between 200 °C and 300 °C, η phase coarsening leads to a decrease in stress and hardness of the material. When the forming temperature is between 300 °C and 400 °C, continuous dynamic recrystallization of 7075 aluminum alloy occurs, resulting in grain refinement and an increase in stress and hardness. The results of numerical simulations and experiments all show that the forming height and deformation uniformity of the sheet metal are optimal at 400 °C, compared to 200 °C.

Blockchain-based applications are gaining traction in various application fields, including supply chain management, health care, and finance. The Internet of Things (IoT) is a critical component of these applications since it allows for data collection from the environment. In this work, we integrate the Hyperledger Fabric blockchain and IoT devices to demonstrate the access control and establish the root of trust for IoT devices. The Hyperledger Fabric is designed to be secure against unwanted access and use through encryption protocols, access restrictions, and cryptography algorithms. An attribute-based access control (ABAC) mechanism was created using Hyperledger Fabric components only to gain access to the IoT device. Single board computers based on the ARM architecture are becoming increasingly powerful and popular in automation applications. In this study, the Raspberry Pi 4 Model B based on ARM64 architecture is used as the IoT device. Because the ARM64 architecture is not supported by default, we build executable binaries and Docker images for the ARM64 architecture, using the Hyperledger Fabric source code. On an IoT device, we run the fabric node in native mode to evaluate the executable binaries generated for the ARM64 architecture. Through effective chaincode execution and testing, we successfully assess the Hyperledger fabric blockchain implementation and access control mechanism on the ARM64 architecture.

The world is facing an unprecedented socio-economic crisis caused by the novel coronavirus infection (COVID-19). The virus is also spreading through the import and export food supply chains. The Chinese authorities have discovered the COVID-19 virus in various imported frozen meat packages. Traceability plays a vital role in food quality and food safety. The Internet of Things (IoT) provides solutions to overseeing environmental conditions, product quality, and product traceability. These solutions are traditionally based on a centralized architecture, which does not guarantee tamper-proof data sharing. The blockchain is an emerging technology that provides tamper-proof data sharing in real-time. This article presents a blockchain-enabled supply chain architecture to ensure the availability of a tamper-proof audit trail. This tamper-proof audit trail helps to make sure that all safety measures are undertaken to minimize the risk of COVID-19 and other bacteria, fungi, and parasites being present in the frozen meat supply chain.

Forecasting the prices of hogs has always been a popular field of research. Such information has played an essential role in decision-making for farmers, consumers, corporations, and governments. It is hard to predict hog prices because too many factors can influence them. Some of the factors are easy to quantify, but some are not. Capturing the characteristics behind the price data is also tricky considering their non-linear and non-stationary nature. To address these difficulties, we propose Heterogeneous Graph-enhanced LSTM (HGLTSM), which is a method that predicts weekly hog price. In this paper, we first extract the historical prices of necessary agricultural products in recent years. Then, we utilize discussions from the online professional community to build heterogeneous graphs. These graphs have rich information of both discussions and the engaged users. Finally, we construct HGLSTM to make the prediction. The experimental results demonstrate that forum discussions are beneficial to hog price prediction. Moreover, our method exhibits a better performance than existing methods.