An Analysis Model of Learners’ Online Learning Status Based on Deep Neural Network and Multi-Dimensional Information Fusion

The learning status of learners directly affects the quality of learning.Compared with offline teachers,it is difficult for online teachers to capture the learning status of students in the whole class,and it is even more difficult to continue to pay attention to studentswhile teaching.Therefore,this paper proposes an online learning state analysis model based on a convolutional neural network and multi-dimensional information fusion.Specifically,a facial expression recognition model and an eye state recognition model are constructed to detect students’emotions and fatigue,respectively.By integrating the detected data with the homework test score data after online learning,an analysis model of students’online learning status is constructed.According to the PAD model,the learning state is expressed as three dimensions of students’understanding,engagement and interest,and then analyzed from multiple perspectives.Finally,the proposed model is applied to actual teaching,and procedural analysis of 5 different types of online classroom learners is carried out,and the validity of the model is verified by comparing with the results of the manual analysis.

Multimodal Sentiment Analysis Using BiGRU and Attention-Based Hybrid Fusion Strategy

Recently,multimodal sentiment analysis has increasingly attracted attention with the popularity of complementary data streams,which has great potential to surpass unimodal sentiment analysis.One challenge of multimodal sentiment analysis is how to design an efficient multimodal feature fusion strategy.Unfortunately,existing work always considers feature-level fusion or decision-level fusion,and few research works focus on hybrid fusion strategies that contain feature-level fusion and decision-level fusion.To improve the performance of multimodal sentiment analysis,we present a novel multimodal sentiment analysis model using BiGRU and attention-based hybrid fusion strategy(BAHFS).Firstly,we apply BiGRU to learn the unimodal features of text,audio and video.Then we fuse the unimodal features into bimodal features using the bimodal attention fusion module.Next,BAHFS feeds the unimodal features and bimodal features into the trimodal attention fusion module and the trimodal concatenation fusion module simultaneously to get two sets of trimodal features.Finally,BAHFS makes a classification with the two sets of trimodal features respectively and gets the final analysis results with decision-level fusion.Based on the CMU-MOSI and CMU-MOSEI datasets,extensive experiments have been carried out to verify BAHFS’s superiority.

Deep Bimodal Fusion Approach for Apparent Personality Analysis

Personality distinguishes individuals’ patterns of feeling, thinking,and behaving. Predicting personality from small video series is an excitingresearch area in computer vision. The majority of the existing research concludespreliminary results to get immense knowledge from visual and Audio(sound) modality. To overcome the deficiency, we proposed the Deep BimodalFusion (DBF) approach to predict five traits of personality-agreeableness,extraversion, openness, conscientiousness and neuroticism. In the proposedframework, regarding visual modality, the modified convolution neural networks(CNN), more specifically Descriptor Aggregator Model (DAN) areused to attain significant visual modality. The proposed model extracts audiorepresentations for greater efficiency to construct the long short-termmemory(LSTM) for the audio modality. Moreover, employing modality-based neuralnetworks allows this framework to independently determine the traits beforecombining them with weighted fusion to achieve a conclusive prediction of thegiven traits. The proposed approach attains the optimal mean accuracy score,which is 0.9183. It is achieved based on the average of five personality traitsand is thus better than previously proposed frameworks.

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.

Intelligent 6G Wireless Network with Multi-Dimensional Information Perception

Intelligence and perception are two operative technologies in 6G scenarios.The intelligent wireless network and information perception require a deep fusion of artificial intelligence(AI)and wireless communications in 6G systems.Therefore,fusion is becoming a typical feature and key challenge of 6G wireless communication systems.In this paper,we focus on the critical issues and propose three application scenarios in 6G wireless systems.Specifically,we first discuss the fusion of AI and 6G networks for the enhancement of 5G-advanced technology and future wireless communication systems.Then,we introduce the wireless AI technology architecture with 6G multidimensional information perception,which includes the physical layer technology of multi-dimensional feature information perception,full spectrum fusion technology,and intelligent wireless resource management.The discussion of key technologies for intelligent 6G wireless network networks is expected to provide a guideline for future research.

Application of evidence theory in information fusion of multiple sources in bayesian analysis

How to obtain proper prior distribution is one of the most critical problems in Bayesian analysis. In many practical cases, the prior information often comes from different sources, and the prior distribution form could be easily known in some certain way while the parameters are hard to determine. In this paper, based on the evidence theory, a new method is presented to fuse the information of multiple sources and determine the parameters of the prior distribution when the form is known. By taking the prior distributions which result from the information of multiple sources and converting them into corresponding mass functions which can be combined by Dempster-Shafer (D-S) method, we get the combined mass function and the representative points of the prior distribution. These points are used to fit with the given distribution form to determine the parameters of the prior distribution. And then the fused prior distribution is obtained and Bayesian analysis can be performed. How to convert the prior distributions into mass functions properly and get the representative points of the fused prior distribution is the central question we address in this paper. The simulation example shows that the proposed method is effective.

Optimal Unification of Static and Dynamic Features for Smartphone Security Analysis

Android Smartphones are proliferating extensively in the digital world due to their widespread applications in a myriad offields.The increased popularity of the android platform entices malware developers to design malicious apps to achieve their malevolent intents.Also,static analysis approaches fail to detect run-time behaviors of malicious apps.To address these issues,an optimal unification of static and dynamic features for smartphone security analysis is proposed.The proposed solution exploits both static and dynamic features for generating a highly distinct unified feature vector using graph based cross-diffusion strategy.Further,a unified feature is subjected to the fuzzy-based classification model to distinguish benign and malicious applications.The suggested framework is extensively experimentally validated through both qualitative and quantitative analysis and results are compared with the existing solutions.Performance evaluation over benchmarked datasets from Google Play Store,Drebin,Androzoo,AMD,and CICMalDroid2020 revealed that the suggested solution outperforms state-of-the-art methods.We achieve average detection accuracy of 98.62%and F1 Score of 0.9916.

Quantitative and comparative analysis of hyperspectral data fusion performance

Hyperspectral data fusion technique is the key to hyperspectral data processing in recent years. Many fusion methods have been proposed, but little research has been done to evaluate the performances of different data fusion methods. In order to meet the urgent need, quantitative correlation analysis(QCA) is proposed to analyse and compare the performances of different fusion methods directly from data before and after fusion. Experiment results show that the new method is effective and the results of comparison are in agreement with the results of application.

Physics Analysis and Optimization Studies for a Fusion Neutron Source Based on a Gas Dynamic Trap

To further investigate the fusion neutron source based on a gas dynamic trap （GDT）, characteristics of the GDT were analyzed and physics analyses were made for a fusion neutron source based on the GDT concept. The prior design of a GDT-based fusion neutron source was optimized based on a refreshed understanding of GDT operation. A two-step progressive development route of a GDT-based fusion neutron source was suggested. Potential applications of GDT are discussed. Preliminary analyses show that a fusion neutron source based on the GDT concept is suitable for plasma-material interaction research, fusion material and subcomponent testing, and capable of driving a proof-of-principle fusion fission hybrid experimental facility.

Feature Fusion Multi-View Hashing Based on Random Kernel Canonical Correlation Analysis

Hashing technology has the advantages of reducing data storage and improving the efficiency of the learning system,making it more and more widely used in image retrieval.Multi-view data describes image information more comprehensively than traditional methods using a single-view.How to use hashing to combine multi-view data for image retrieval is still a challenge.In this paper,a multi-view fusion hashing method based on RKCCA(Random Kernel Canonical Correlation Analysis)is proposed.In order to describe image content more accurately,we use deep learning dense convolutional network feature DenseNet to construct multi-view by combining GIST feature or BoW_SIFT(Bag-of-Words model+SIFT feature)feature.This algorithm uses RKCCA method to fuse multi-view features to construct association features and apply them to image retrieval.The algorithm generates binary hash code with minimal distortion error by designing quantization regularization terms.A large number of experiments on benchmark datasets show that this method is superior to other multi-view hashing methods.

Biomechanical Effects of Implant Materials on Posterior Lumbar Interbody Fusion: Comparison of Polyetheretherketone and Titanium Spacers Using Finite Element Analysis and Considering Bone Density

Few biomechanical data exist regarding whether the polyetheretherketone (PEEK) spacer or titanium spacer is better for posterior lumbar interbody fusion (PLIF). This study evaluated the biomechanical influence that these types of spacers with different levels of hardness exert on the vertebra by using finite element analysis including bone strength distribution. To evaluate the risk of spacer subsidence for PLIF, we built a finite element model of the lumbar spine using computed tomography data of osteoporosis patients. Then, we simulated PLIF in L3/4 and built models with the hardness of the interbody spacer set as PEEK and titanium. Bones around the spacer were subjected to different load conditions. Then, fracture elements and some stress states of the two modalities were compared. In both models of PLIF simulation, fracture elements and stress were concentrated in the bones around the spacer. Fracture elements and stress values of the model simulating the PEEK spacer were significantly smaller compared to those of the titanium simulation model. For PLIF of osteoporotic vertebrae, this suggested that the PEEK spacer is in a mechanical environment less susceptible to subsidence caused by microfractures of bone tissue and bone remodeling-related fusion aspects. Therefore, PEEK spacers are bio-mechanically more useful.

Self-tuning Information Fusion Kalman Predictor Weighted by Diagonal Matrices and Its Convergence Analysis

为有未知噪音统计的 multisensor 系统，使用现代时间系列分析方法，基于革新建模的动人的一般水准(麻省)的联机鉴定，并且基于为关联功能的矩阵方程的解决方案，噪音变化的评估者被获得，并且在线性最小的变化下面由斜矩阵加权的最佳的信息熔化标准，一个自我调节的信息熔化 Kalman 预言者被介绍，它认识到自我调节的 dec 基于动态错误系统，一个新集中分析方法为自我调节的 fuser 被介绍。在一条认识的集中的一个新概念被介绍，它是比有概率一的集中弱的。如果 MA 革新模型的参数评价是一致的，那么，自我调节的熔化 Kalman 预言者将在一条认识收敛到最佳的熔化 Kalman 预言者，这严格地被证明，或与概率一，以便它有 asymptotic optimality。它能减少计算负担，并且对实时应用合适。为追踪系统的一个目标的一个模拟例子显示出它的有效性。

Multimodality Medical Image Fusion Based on Pixel Significance with Edge-Preserving Processing for Clinical Applications

Multimodal medical image fusion has attained immense popularity in recent years due to its robust technology for clinical diagnosis.It fuses multiple images into a single image to improve the quality of images by retaining significant information and aiding diagnostic practitioners in diagnosing and treating many diseases.However,recent image fusion techniques have encountered several challenges,including fusion artifacts,algorithm complexity,and high computing costs.To solve these problems,this study presents a novel medical image fusion strategy by combining the benefits of pixel significance with edge-preserving processing to achieve the best fusion performance.First,the method employs a cross-bilateral filter(CBF)that utilizes one image to determine the kernel and the other for filtering,and vice versa,by considering both geometric closeness and the gray-level similarities of neighboring pixels of the images without smoothing edges.The outputs of CBF are then subtracted from the original images to obtain detailed images.It further proposes to use edge-preserving processing that combines linear lowpass filtering with a non-linear technique that enables the selection of relevant regions in detailed images while maintaining structural properties.These regions are selected using morphologically processed linear filter residuals to identify the significant regions with high-amplitude edges and adequate size.The outputs of low-pass filtering are fused with meaningfully restored regions to reconstruct the original shape of the edges.In addition,weight computations are performed using these reconstructed images,and these weights are then fused with the original input images to produce a final fusion result by estimating the strength of horizontal and vertical details.Numerous standard quality evaluation metrics with complementary properties are used for comparison with existing,well-known algorithms objectively to validate the fusion results.Experimental results from the proposed research article exhibit superior performance compared to other competing techniques in the case of both qualitative and quantitative evaluation.In addition,the proposed method advocates less computational complexity and execution time while improving diagnostic computing accuracy.Nevertheless,due to the lower complexity of the fusion algorithm,the efficiency of fusion methods is high in practical applications.The results reveal that the proposed method exceeds the latest state-of-the-art methods in terms of providing detailed information,edge contour,and overall contrast.

A Comprehensive Survey on Deep Learning Multi-Modal Fusion:Methods,Technologies and Applications

Multi-modal fusion technology gradually become a fundamental task in many fields,such as autonomous driving,smart healthcare,sentiment analysis,and human-computer interaction.It is rapidly becoming the dominant research due to its powerful perception and judgment capabilities.Under complex scenes,multi-modal fusion technology utilizes the complementary characteristics of multiple data streams to fuse different data types and achieve more accurate predictions.However,achieving outstanding performance is challenging because of equipment performance limitations,missing information,and data noise.This paper comprehensively reviews existing methods based onmulti-modal fusion techniques and completes a detailed and in-depth analysis.According to the data fusion stage,multi-modal fusion has four primary methods:early fusion,deep fusion,late fusion,and hybrid fusion.The paper surveys the three majormulti-modal fusion technologies that can significantly enhance the effect of data fusion and further explore the applications of multi-modal fusion technology in various fields.Finally,it discusses the challenges and explores potential research opportunities.Multi-modal tasks still need intensive study because of data heterogeneity and quality.Preserving complementary information and eliminating redundant information between modalities is critical in multi-modal technology.Invalid data fusion methods may introduce extra noise and lead to worse results.This paper provides a comprehensive and detailed summary in response to these challenges.

Research on Sarcasm Detection Technology Based on Image-Text Fusion

The emergence of new media in various fields has continuously strengthened the social aspect of social media.Netizens tend to express emotions in social interactions,and many people even use satire,metaphors,and other techniques to express some negative emotions,it is necessary to detect sarcasm in social comment data.For sarcasm,the more reference data modalities used,the better the experimental effect.This paper conducts research on sarcasm detection technology based on image-text fusion data.To effectively utilize the features of each modality,a feature reconstruction output algorithm is proposed.This algorithm is based on the attention mechanism,learns the low-rank features of another modality through cross-modality,the eigenvectors are reconstructed for the corresponding modality through weighted averaging.When only the image modality in the dataset is used,the preprocessed data has outstanding performance in reconstructing the output model,with an accuracy rate of 87.6%.When using only the text modality data in the dataset,the reconstructed output model is optimal,with an accuracy rate of 85.2%.To improve feature fusion between modalities for effective classification,a weight adaptive learning algorithm is used.This algorithm uses a neural network combined with an attention mechanism to calculate the attention weight of each modality to achieve weight adaptive learning purposes,with an accuracy rate of 87.9%.Extensive experiments on a benchmark dataset demonstrate the superiority of our proposed model.

Three dimensional passive underwater target motion analysis using correlated data fusion

In this paper a new method of passive underwater TMA (target motion analysis) using data fusion is presented. The findings of this research are based on an understanding that there is a powerful sonar system that consists of many types of sonar but with one own-ship, and that different target parameter measurements can be obtained simultaneously. For the analysis 3 data measurements, passive bearing, elevation and multipath time-delay, are used, which are divided into two groups: a group with estimates of two preliminary target parameter obtained by dealing with each group measurement independently, and a group where correlated estimates are sent to a fusion center where the correlation between two data groups are considered so that the passive underwater TMA is realized. Simulation results show that curves of parameter estimation errors obtained by using the data fusion have fast convergence and the estimation accuracy is noticeably improved. The TMA algorithm presented is verified and is of practical significance because it is easy to be realized in one ship.

Use of Nonlinear Finite Element Analysis of Bone Density to Investigate the Biomechanical Effect in the Bone around Intervertebral Cages in Posterior Lumbar Interbody Fusion

Preventing subsidence of intervertebral cages in posterior lumbar interbody fusion (PLIF) requires understanding its mechanism, which is yet to be done. We aimed to describe the mechanism of intervertebral cage subsidence by using finite element analysis through simulation of the osteoporotic vertebral bodies of an elderly woman. The data from computed tomography scans of L2-L5 vertebrae in a 72-year-old woman with osteoporosis were used to create 2 FE models: one not simulating implant placement (LS-INT) and one simulating L3/4 PLIF using polyetheretherketone (PEEK) cages (LS-PEEK). Loads and moments simulating the living body were applied to these models, and the following analyses were performed: 1) Drucker-Prager equivalent stress distribution at the cage contact surfaces;2) the distribution of damage elements in L2-L5 during incremental loading;and 3) the distribution of equivalent plastic strain at the cage contact surfaces. In analysis 1, the Drucker-Prager equivalent stress on the L3 and L4 vertebral endplates was greater for LS-PEEK than for LS-INT under all loading conditions and tended to be particularly concentrated at the contact surfaces. In analysis 2, compared with LS-INT, LS-PEEK showed more damage elements along the bone around the cages in the L3 vertebral body posterior to the cage contact surfaces, followed by the area of the L4 vertebral body posterior to the cage contact surfaces. In analysis 3, in the L3 inferior surface in LS-PEEK the distribution of equivalent plastic strain was visualized as gradually expanding along the cages from the area posterior to the cages to the area anterior to them with increased loading. These analyses suggested that in PLIF for osteoporotic vertebral bodies, the localized stress concentration generated by the use of PEEK cages may cause accumulation of microscopic damage in the fragile osteoporotic vertebral bodies around the cages, which may result in cage subsidence.

Fast Sentiment Analysis Algorithm Based on Double Model Fusion

Nowadays,as the number of textual data is exponentially increasing,sentiment analysis has become one of the most significant tasks in natural language processing(NLP)with increasing attention.Traditional Chinese sentiment analysis algorithms cannot make full use of the order information in context and are inefficient in sentiment inference.In this paper,we systematically reviewed the classic and representative works in sentiment analysis and proposed a simple but efficient optimization.First of all,FastText was trained to get the basic classification model,which can generate pre-trained word vectors as a by-product.Secondly,Bidirectional Long Short-Term Memory Network(Bi-LSTM)utilizes the generated word vectors for training and then merges with FastText to make comprehensive sentiment analysis.By combining FastText and Bi-LSTM,we have developed a new fast sentiment analysis,called FAST-BiLSTM,which consistently achieves a balance between performance and speed.In particular,experimental results based on the real datasets demonstrate that our algorithm can effectively judge sentiments of users’comments,and is superior to the traditional algorithm in time efficiency,accuracy,recall and F1 criteria.

Skill Analysis of Highly Skilled Worker in Optical Fiber Fusion Splicing

In this study, information related to optical fiber fusion splicing skills is consolidated by extracting explicit knowledge of the proficiency levels of skilled technicians in two ways. The first is to visually capture and quantify those skills by identifying differences in the skill levels of a nationally certified technician and a highly skilled expert technician using motion capture software, the other is to explore the relevance of the operation and thinking processes by interviewing the expert technician and then attempt to quantify empirical tacit knowledge by an analysis of mobile tracking views using motion capture software. The results show that a technician＇s ability to engage in ＂sensory thinking＂, such as the proper management of visual and tactile cues, is the most important component of his or her proficiency during optical fiber fusion splicing operations, and it was clear that operations were complemented when work path movements were reduced.

A Comparison of Weighing Methods Prior to Fusion Preparing Iron Samples for XRF Analysis

Sample preparation by fusion for XRF analysis is all about knowing the exact weights of the sample and the flux (sample-to-flux ratio). The whole analytical chain, including the weighing step in sample preparation prior to fusion, is of crucial importance to get precise and accurate x-ray fluorescence (XRF) results. Consequently, the weighing method will affect the quality of the analytical results given by the spectrometer. In this study, the effects of different weighing methods on the precision (RSD) of the obtained XRF results are compared to determine the best weighing method for sample preparation by fusion in terms of comparable precisions in the XRF results.