Multimodal Social Media Fake News Detection Based on Similarity Inference and Adversarial Networks

As social networks become increasingly complex, contemporary fake news often includes textual descriptionsof events accompanied by corresponding images or videos. Fake news in multiple modalities is more likely tocreate a misleading perception among users. While early research primarily focused on text-based features forfake news detection mechanisms, there has been relatively limited exploration of learning shared representationsin multimodal (text and visual) contexts. To address these limitations, this paper introduces a multimodal modelfor detecting fake news, which relies on similarity reasoning and adversarial networks. The model employsBidirectional Encoder Representation from Transformers (BERT) and Text Convolutional Neural Network (Text-CNN) for extracting textual features while utilizing the pre-trained Visual Geometry Group 19-layer (VGG-19) toextract visual features. Subsequently, the model establishes similarity representations between the textual featuresextracted by Text-CNN and visual features through similarity learning and reasoning. Finally, these features arefused to enhance the accuracy of fake news detection, and adversarial networks have been employed to investigatethe relationship between fake news and events. This paper validates the proposed model using publicly availablemultimodal datasets from Weibo and Twitter. Experimental results demonstrate that our proposed approachachieves superior performance on Twitter, with an accuracy of 86%, surpassing traditional unimodalmodalmodelsand existing multimodal models. In contrast, the overall better performance of our model on the Weibo datasetsurpasses the benchmark models across multiple metrics. The application of similarity reasoning and adversarialnetworks in multimodal fake news detection significantly enhances detection effectiveness in this paper. However,current research is limited to the fusion of only text and image modalities. Future research directions should aimto further integrate features fromadditionalmodalities to comprehensively represent themultifaceted informationof fake news.

Chinese Clinical Named Entity Recognition Using Multi-Feature Fusion and Multi-Scale Local Context Enhancement

Chinese Clinical Named Entity Recognition(CNER)is a crucial step in extracting medical information and is of great significance in promoting medical informatization.However,CNER poses challenges due to the specificity of clinical terminology,the complexity of Chinese text semantics,and the uncertainty of Chinese entity boundaries.To address these issues,we propose an improved CNER model,which is based on multi-feature fusion and multi-scale local context enhancement.The model simultaneously fuses multi-feature representations of pinyin,radical,Part of Speech(POS),word boundary with BERT deep contextual representations to enhance the semantic representation of text for more effective entity recognition.Furthermore,to address the model’s limitation of focusing just on global features,we incorporate Convolutional Neural Networks(CNNs)with various kernel sizes to capture multi-scale local features of the text and enhance the model’s comprehension of the text.Finally,we integrate the obtained global and local features,and employ multi-head attention mechanism(MHA)extraction to enhance the model’s focus on characters associated with medical entities,hence boosting the model’s performance.We obtained 92.74%,and 87.80%F1 scores on the two CNER benchmark datasets,CCKS2017 and CCKS2019,respectively.The results demonstrate that our model outperforms the latest models in CNER,showcasing its outstanding overall performance.It can be seen that the CNER model proposed in this study has an important application value in constructing clinical medical knowledge graph and intelligent Q&A system.

A Non-Parametric Scheme for Identifying Data Characteristic Based on Curve Similarity Matching

For accurately identifying the distribution charac-teristic of Gaussian-like noises in unmanned aerial vehicle(UAV)state estimation,this paper proposes a non-parametric scheme based on curve similarity matching.In the framework of the pro-posed scheme,a Parzen window(kernel density estimation,KDE)method on sliding window technology is applied for roughly esti-mating the sample probability density,a precise data probability density function(PDF)model is constructed with the least square method on K-fold cross validation,and the testing result based on evaluation method is obtained based on some data characteristic analyses of curve shape,abruptness and symmetry.Some com-parison simulations with classical methods and UAV flight exper-iment shows that the proposed scheme has higher recognition accuracy than classical methods for some kinds of Gaussian-like data,which provides better reference for the design of Kalman filter(KF)in complex water environment.

Structural similarity of lithospheric velocity models of Chinese mainland

Existing lithospheric velocity models exhibit similar structures typically associated with the first-order tectonic features,with dissimilarities due to different data and methods used in model generation.The quantification of model structural similarity can help in interpreting the geophysical properties of Earth's interior and establishing unified models crucial in natural hazard assessment and resource exploration.Here we employ the complex wavelet structural similarity index measure(CW-SSIM)active in computer image processing to analyze the structural similarity of four lithospheric velocity models of Chinese mainland published in the past decade.We take advantage of this method in its multiscale definition and insensitivity to slight geometrical distortion like translation and scaling,which is particularly crucial in the structural similarity analysis of velocity models accounting for uncertainty and resolution.Our results show that the CW-SSIM values vary in different model pairs,horizontal locations,and depths.While variations in the inter-model CW-SSIM are partly owing to different databases in the model generation,the difference of tomography methods may significantly impact the similar structural features of models,such as the low similarities between the full-wave based FWEA18 and other three models in northeastern China.We finally suggest potential solutions for the next generation of tomographic modeling in different areas according to corresponding structural similarities of existing models.

A Situational Awareness Method for Initial Insulation Fault of Distribution Network Based on Multi-Feature Index Comprehensive Evaluation

Most ground faults in distribution network are caused by insulation deterioration of power equipment.It is difficult to find the insulation deterioration of the distribution network in time,and the development trend of the initial insulation fault is unknown,which brings difficulties to the distribution inspection.In order to solve the above problems,a situational awareness method of the initial insulation fault of the distribution network based on a multi-feature index comprehensive evaluation is proposed.Firstly,the insulation situation evaluation index is selected by analyzing the insulation fault mechanism of the distribution network,and the relational database of the distribution network is designed based on the data and numerical characteristics of the existing distribution management system.Secondly,considering all kinds of fault factors of the distribution network and the influence of the power supply region,the evaluation method of the initial insulation fault situation of the distribution network is proposed,and the development situation of the distribution network insulation fault is classified according to the evaluation method.Then,principal component analysis was used to reduce the dimension of the training samples and test samples of the distribution network data,and the support vector machine(SVM)was trained.The optimal parameter combination of the SVM model was found by the grid search method,and a multi-class SVM model based on 1-v-1 method was constructed.Finally,the trained multi-class SVM was used to predict 6 kinds of situation level prediction samples.The results of simulation examples show that the average prediction accuracy of 6 situation levels is above 95%,and the perception accuracy of 4 situation levels is above 96%.In addition,the insulation maintenance decision scheme under different situation levels is able to be given when no fault occurs or the insulation fault is in the early stage,which can meet the needs of power distribution and inspection for accurately sensing the insulation fault situation.The correctness and effectiveness of this method are verified.

Investigation on mechanical properties regulation of rock-like specimens based on 3D printing and similarity quantification

3D printing is widely adopted to quickly produce rock mass models with complex structures in batches,improving the consistency and repeatability of physical modeling.It is necessary to regulate the mechanical properties of 3D-printed specimens to make them proportionally similar to natural rocks.This study investigates mechanical properties of 3D-printed rock analogues prepared by furan resin-bonded silica sand particles.The mechanical property regulation of 3D-printed specimens is realized through quantifying its similarity to sandstone,so that analogous deformation characteristics and failure mode are acquired.Considering similarity conversion,uniaxial compressive strength,cohesion and stress–strain relationship curve of 3D-printed specimen are similar to those of sandstone.In the study ranges,the strength of 3D-printed specimen is positively correlated with the additive content,negatively correlated with the sand particle size,and first increases then decreases with the increase of curing temperature.The regulation scheme with optimal similarity quantification index,that is the sand type of 70/140,additive content of 2.5‰and curing temperature of 81.6℃,is determined for preparing 3D-printed sandstone analogues and models.The effectiveness of mechanical property regulation is proved through uniaxial compression contrast tests.This study provides a reference for preparing rock-like specimens and engineering models using 3D printing technology.

Numerical Simulation of the Settling Flux of Biodeposition in a Bay with Cage Culture Through Similarity Theory and a Simplified Pollution Source

The settling flux of biodeposition affects the environmental quality of cage culture areas and determines their environmental carrying capacity.Simple and effective simulation of the settling flux of biodeposition is extremely important for determining the spatial distribution of biodeposition.Theoretically,biodeposition in cage culture areas without specific emission rules can be simplified as point source pollution.Fluent is a fluid simulation software that can simulate the dispersion of particulate matter simply and efficiently.Based on the simplification of pollution sources and bays,the settling flux of biodeposition can be easily and effectively simulated by Fluent fluid software.In the present work,the feasibility of this method was evaluated by simulation of the settling flux of biodeposition in Maniao Bay,Hainan Province,China,and 20 sampling sites were selected for determining the settling fluxes.At sampling sites P1,P2,P3,P4,P5,Z1,Z2,Z3,Z4,A1,A2,A3,A4,B1,B2,C1,C2,C3 and C4,the measured settling fluxes of biodeposition were 26.02,15.78,10.77,58.16,6.57,72.17,12.37,12.11,106.64,150.96,22.59,11.41,18.03,7.90,19.23,7.06,11.84,5.19 and 2.57 g d^(−1)m^(−2),respectively.The simulated settling fluxes of biodeposition at the corresponding sites were 16.03,23.98,8.87,46.90,4.52,104.77,16.03,8.35,180.83,213.06,39.10,17.47,20.98,9.78,23.25,7.84,15.90,6.06 and 1.65 g d^(−1)m^(−2),respectively.There was a positive correlation between the simulated settling fluxes and measured ones(R=0.94,P=2.22×10^(−9)<0.05),which implies that the spatial differentiation of biodeposition flux was well simulated.Moreover,the posterior difference ratio of the simulation was 0.38,and the small error probability was 0.94,which means that the simulated results reached an acceptable level from the perspective of relative error.Thus,if nonpoint source pollution is simplified to point source pollution and open waters are simplified based on similarity theory,the setting flux of biodeposition in the open waters can be simply and effectively simulated by the fluid simulation software Fluent.

Similarity evaluation model for the internal defect detection of strip steel

An internal defect meter is an instrument to detect the internal inclusion defects of cold-rolled strip steel.The detection accuracy of the equipment can be evaluated based on the similarity of the multiple detection data obtained for the same steel coil.Based on the cosine similarity model and eigenvalue matrix model,a comprehensive evaluation method to calculate the weighted average of similarity is proposed.Results show that the new method is consistent with and can even replace artificial evaluation to realize the automatic evaluation of strip defect detection results.

Load-forecasting method for IES based on LSTM and dynamic similar days with multi-features

To fully exploit the rich characteristic variation laws of an integrated energy system(IES)and further improve the short-term load-forecasting accuracy,a load-forecasting method is proposed for an IES based on LSTM and dynamic similar days with multi-features.Feature expansion was performed to construct a comprehensive load day covering the load and meteorological information with coarse and fine time granularity,far and near time periods.The Gaussian mixture model(GMM)was used to divide the scene of the comprehensive load day,and gray correlation analysis was used to match the scene with the coarse time granularity characteristics of the day to be forecasted.Five typical days with the highest correlation with the day to be predicted in the scene were selected to construct a“dynamic similar day”by weighting.The key features of adjacent days and dynamic similar days were used to forecast multi-loads with fine time granularity using LSTM.Comparing the static features as input and the selection method of similar days based on non-extended single features,the effectiveness of the proposed prediction method was verified.

A Review of Research on Handwritten Chinese Character Recognition with Multi-Feature Fusion

This paper analyzes the progress of handwritten Chinese character recognition technology,from two perspectives:traditional recognition methods and deep learning-based recognition methods.Firstly,the complexity of Chinese character recognition is pointed out,including its numerous categories,complex structure,and the problem of similar characters,especially the variability of handwritten Chinese characters.Subsequently,recognition methods based on feature optimization,model optimization,and fusion techniques are highlighted.The fusion studies between feature optimization and model improvement are further explored,and these studies further enhance the recognition effect through complementary advantages.Finally,the article summarizes the current challenges of Chinese character recognition technology,including accuracy improvement,model complexity,and real-time problems,and looks forward to future research directions.

A geographical similarity-based sampling method of non-fire point data for spatial prediction of forest fires

Understanding the mechanisms and risks of forest fires by building a spatial prediction model is an important means of controlling forest fires.Non-fire point data are important training data for constructing a model,and their quality significantly impacts the prediction performance of the model.However,non-fire point data obtained using existing sampling methods generally suffer from low representativeness.Therefore,this study proposes a non-fire point data sampling method based on geographical similarity to improve the quality of non-fire point samples.The method is based on the idea that the less similar the geographical environment between a sample point and an already occurred fire point,the greater the confidence in being a non-fire point sample.Yunnan Province,China,with a high frequency of forest fires,was used as the study area.We compared the prediction performance of traditional sampling methods and the proposed method using three commonly used forest fire risk prediction models:logistic regression(LR),support vector machine(SVM),and random forest(RF).The results show that the modeling and prediction accuracies of the forest fire prediction models established based on the proposed sampling method are significantly improved compared with those of the traditional sampling method.Specifically,in 2010,the modeling and prediction accuracies improved by 19.1%and 32.8%,respectively,and in 2020,they improved by 13.1%and 24.3%,respectively.Therefore,we believe that collecting non-fire point samples based on the principle of geographical similarity is an effective way to improve the quality of forest fire samples,and thus enhance the prediction of forest fire risk.

Relative Molecular Similarity in Compound Structures Modulating Neurodegenerative Apoptosis

Neurodegeneration is attributable to metabolic disturbances in the various cell types responsible for this condition, in respect of glucose utilisation and dysfunctional mitochondrial oxidative mechanisms. The properties of neurotoxins and antagonists that limit their action are well documented in disease models, whereas effective therapy is very limited. Cell apoptosis, a general marker of neurodegeneration, is also of therapeutic interest in the treatment of cancer. cGMP nucleotide influences apoptosis and has a role in maintaining equilibrium within cell redox parameters. The chemical structure of cGMP provides a comparative template for demonstrating relative molecular similarity within the structures of natural and synthetic compounds influencing tumour cell apoptosis. The present study uses computational software to investigate molecular similarity within the structures of cGMP and compounds that modulate cell apoptosis in experimental models of diabetic peripheral neuropathy (DPN), Parkinson’s and multiple sclerosis. Differential molecular similarity demonstrated in neurotoxin and antagonist structures implicate metabolite impairment of cGMP signaling function as a common mechanism in the initial phases of these neurodegenerative conditions.

Research on Facial Fatigue Detection of Drivers with Multi-feature Fusion

In order to solve the shortcomings of current fatigue detection methods such as low accuracy or poor real-time performance,a fatigue detection method based on multi-feature fusion is proposed.Firstly,the HOG face detection algorithm and KCF target tracking algorithm are integrated and deformable convolutional neural network is introduced to identify the state of extracted eyes and mouth,fast track the detected faces and extract continuous and stable target faces for more efficient extraction.Then the head pose algorithm is introduced to detect the driver’s head in real time and obtain the driver’s head state information.Finally,a multi-feature fusion fatigue detection method is proposed based on the state of the eyes,mouth and head.According to the experimental results,the proposed method can detect the driver’s fatigue state in real time with high accuracy and good robustness compared with the current fatigue detection algorithms.

SA-Model:Multi-Feature Fusion Poetic Sentiment Analysis Based on a Hybrid Word Vector Model

Sentiment analysis in Chinese classical poetry has become a prominent topic in historical and cultural tracing,ancient literature research,etc.However,the existing research on sentiment analysis is relatively small.It does not effectively solve the problems such as the weak feature extraction ability of poetry text,which leads to the low performance of the model on sentiment analysis for Chinese classical poetry.In this research,we offer the SA-Model,a poetic sentiment analysis model.SA-Model firstly extracts text vector information and fuses it through Bidirectional encoder representation from transformers-Whole word masking-extension(BERT-wwmext)and Enhanced representation through knowledge integration(ERNIE)to enrich text vector information;Secondly,it incorporates numerous encoders to remove text features at multiple levels,thereby increasing text feature information,improving text semantics accuracy,and enhancing the model’s learning and generalization capabilities;finally,multi-feature fusion poetry sentiment analysis model is constructed.The feasibility and accuracy of the model are validated through the ancient poetry sentiment corpus.Compared with other baseline models,the experimental findings indicate that SA-Model may increase the accuracy of text semantics and hence improve the capability of poetry sentiment analysis.

Cytotoxicity of Cholesterol Oxides and the Consequences of Relative Molecular Similarity to cGMP Nucleotide

Cholesterol and cholesterol oxides impact on the functional properties of cells, in respect of the intracellular and extracellular distribution of compounds across cell membranes, carcinogenesis and drug resistance. Abnormal levels of cholesterol oxides and steroids in cancerous tissues promote interest in steroid receptor cross-talk during cell-signalling and the steroid metabolome of cancer patients. The research literature links the cytotoxic properties of oxysterols to interference with the NO/cGMP pathway. cGMP participates in cell-signalling and has a molecular structure that relates to cancer-inducing and cancer-preventing agents. This study uses a molecular modelling approach to compare the structures of cholesterol oxides to cGMP. Cholesterol and cholesterol oxide structures fit to a cGMP structural template in several ways, some of which are replicated by corticosteroids and gonadal steroid hormones. The results of this study support the concept that cholesterol oxides modulate cell apoptosis and autophagy via the NO/cGMP pathway and in conjunction with steroid hormones participate in modulating regulation of cell function by cGMP.

Species richness and similarity of the flora on four lajedos in Boa Nova, Bahia, Brazil

The municipality of Boa Nova,in northeastern Brazil,is in an ecotone zone between the Caatinga and Atlantic Forest phytogeographic domains.The transition phytophysiognomy is seasonal forest and known locally as mata de cipó.In these phytophysiognomies there are lajedos,which are rock outcrops colonized by vegetation welladapted to extreme microclimatic variation and vegetation diversity is affected by the vegetation types of the surrounding areas.Due to the singularity of these environments and the relevance of floristic studies for conservation,this work aimed to identify the species richness and compare the similarity of the flora on four rock outcrops in Boa Nova.The flora was surveyed during exploratory walks along lajedos between 2016 and 2019.In total,162 species were identified on the Boa Nova outcrops.The flora has a composition and structure similar to semiarid outcrops,as well as endemic species that also occur in surrounding phytophysiomies.Despite the proximity,a similarity index revealed there is floristic dissimilarity between the areas.Nine new occurrences were recorded for the region,five species are threatened with extinction(Aosa gilgiana,Ficus cyclophylla,Hippeastrum stigmovittatum,Pleroma caatingae and Trixis pruskii),and 43 species are common in anthropogenic areas.This reinforces the importance of actions to conserve these areas.

Multi-Feature Fusion Book Recommendation Model Based on Deep Neural Network

The traditional recommendation algorithm represented by the collaborative filtering algorithm is the most classical and widely recommended algorithm in the practical industry.Most book recommendation systems also use this algorithm.However,the traditional recommendation algorithm represented by the collaborative filtering algorithm cannot deal with the data sparsity well.This algorithm only uses the shallow feature design of the interaction between readers and books,so it fails to achieve the high-level abstract learning of the relevant attribute features of readers and books,leading to a decline in recommendation performance.Given the above problems,this study uses deep learning technology to model readers’book borrowing probability.It builds a recommendation system model through themulti-layer neural network and inputs the features extracted from readers and books into the network,and then profoundly integrates the features of readers and books through the multi-layer neural network.The hidden deep interaction between readers and books is explored accordingly.Thus,the quality of book recommendation performance will be significantly improved.In the experiment,the evaluation indexes ofHR@10,MRR,andNDCGof the deep neural network recommendation model constructed in this paper are higher than those of the traditional recommendation algorithm,which verifies the effectiveness of the model in the book recommendation.

Multi-Features Disease Analysis Based Smart Diagnosis for COVID-19

Coronavirus 2019(COVID-19)is the current global buzzword,putting the world at risk.The pandemic’s exponential expansion of infected COVID-19 patients has challenged the medical field’s resources,which are already few.Even established nations would not be in a perfect position to manage this epidemic correctly,leaving emerging countries and countries that have not yet begun to grow to address the problem.These problems can be solved by using machine learning models in a realistic way,such as by using computer-aided images during medical examinations.These models help predict the effects of the disease outbreak and help detect the effects in the coming days.In this paper,Multi-Features Decease Analysis(MFDA)is used with different ensemble classifiers to diagnose the disease’s impact with the help of Computed Tomography(CT)scan images.There are various features associated with chest CT images,which help know the possibility of an individual being affected and how COVID-19 will affect the persons suffering from pneumonia.The current study attempts to increase the precision of the diagnosis model by evaluating various feature sets and choosing the best combination for better results.The model’s performance is assessed using Receiver Operating Characteristic(ROC)curve,the Root Mean Square Error(RMSE),and the Confusion Matrix.It is observed from the resultant outcome that the performance of the proposed model has exhibited better efficient.

Deep Learning-Based Program-Wide Binary Code Similarity for Smart Contracts

Recently,security issues of smart contracts are arising great attention due to the enormous financial loss caused by vulnerability attacks.There is an increasing need to detect similar codes for hunting vulnerability with the increase of critical security issues in smart contracts.Binary similarity detection that quantitatively measures the given code diffing has been widely adopted to facilitate critical security analysis.However,due to the difference between common programs and smart contract,such as diversity of bytecode generation and highly code homogeneity,directly adopting existing graph matching and machine learning based techniques to smart contracts suffers from low accuracy,poor scalability and the limitation of binary similarity on function level.Therefore,this paper investigates graph neural network to detect smart contract binary code similarity at the program level,where we conduct instruction-level normalization to reduce the noise code for smart contract pre-processing and construct contract control flow graphs to represent smart contracts.In particular,two improved Graph Convolutional Network(GCN)and Message Passing Neural Network(MPNN)models are explored to encode the contract graphs into quantitatively vectors,which can capture the semantic information and the program-wide control flow information with temporal orders.Then we can efficiently accomplish the similarity detection by measuring the distance between two targeted contract embeddings.To evaluate the effectiveness and efficient of our proposed method,extensive experiments are performed on two real-world datasets,i.e.,smart contracts from Ethereum and Enterprise Operation System(EOS)blockchain-based platforms.The results show that our proposed approach outperforms three state-of-the-art methods by a large margin,achieving a great improvement up to 6.1%and 17.06%in accuracy.

Attribute Reduction for Information Systems via Strength of Rules and Similarity Matrix

An information system is a type of knowledge representation,and attribute reduction is crucial in big data,machine learning,data mining,and intelligent systems.There are several ways for solving attribute reduction problems,but they all require a common categorization.The selection of features in most scientific studies is a challenge for the researcher.When working with huge datasets,selecting all available attributes is not an option because it frequently complicates the study and decreases performance.On the other side,neglecting some attributes might jeopardize data accuracy.In this case,rough set theory provides a useful approach for identifying superfluous attributes that may be ignored without sacrificing any significant information;nonetheless,investigating all available combinations of attributes will result in some problems.Furthermore,because attribute reduction is primarily a mathematical issue,technical progress in reduction is dependent on the advancement of mathematical models.Because the focus of this study is on the mathematical side of attribute reduction,we propose some methods to make a reduction for information systems according to classical rough set theory,the strength of rules and similarity matrix,we applied our proposed methods to several examples and calculate the reduction for each case.These methods expand the options of attribute reductions for researchers.