Research on the Impact of Digital Transformation on the Performance of Manufacturing Enterprises

To address the challenges faced by manufacturing enterprises in digital transformation,this paper analyzes the relationship between digital transformation and enterprise performance.Using panel data from domestic A-share-listed manufacturing enterprises from 2012 to 2022,two hypotheses were proposed.The analysis and verification revealed that digital transformation in manufacturing enterprises can enhance performance and reduce costs.Based on the impact of digital transformation on manufacturing enterprise performance,optimization suggestions are proposed to guide future digital transformation and performance improvement efforts in these enterprises.

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.

TECMH:Transformer-Based Cross-Modal Hashing For Fine-Grained Image-Text Retrieval

In recent years,cross-modal hash retrieval has become a popular research field because of its advantages of high efficiency and low storage.Cross-modal retrieval technology can be applied to search engines,crossmodalmedical processing,etc.The existing main method is to use amulti-label matching paradigm to finish the retrieval tasks.However,such methods do not use fine-grained information in the multi-modal data,which may lead to suboptimal results.To avoid cross-modal matching turning into label matching,this paper proposes an end-to-end fine-grained cross-modal hash retrieval method,which can focus more on the fine-grained semantic information of multi-modal data.First,the method refines the image features and no longer uses multiple labels to represent text features but uses BERT for processing.Second,this method uses the inference capabilities of the transformer encoder to generate global fine-grained features.Finally,in order to better judge the effect of the fine-grained model,this paper uses the datasets in the image text matching field instead of the traditional label-matching datasets.This article experiment on Microsoft COCO(MS-COCO)and Flickr30K datasets and compare it with the previous classicalmethods.The experimental results show that this method can obtain more advanced results in the cross-modal hash retrieval field.

Digital Twin-Assisted Knowledge Distillation Framework for Heterogeneous Federated Learning

In this paper,to deal with the heterogeneity in federated learning(FL)systems,a knowledge distillation(KD)driven training framework for FL is proposed,where each user can select its neural network model on demand and distill knowledge from a big teacher model using its own private dataset.To overcome the challenge of train the big teacher model in resource limited user devices,the digital twin(DT)is exploit in the way that the teacher model can be trained at DT located in the server with enough computing resources.Then,during model distillation,each user can update the parameters of its model at either the physical entity or the digital agent.The joint problem of model selection and training offloading and resource allocation for users is formulated as a mixed integer programming(MIP)problem.To solve the problem,Q-learning and optimization are jointly used,where Q-learning selects models for users and determines whether to train locally or on the server,and optimization is used to allocate resources for users based on the output of Q-learning.Simulation results show the proposed DT-assisted KD framework and joint optimization method can significantly improve the average accuracy of users while reducing the total delay.

A PERT-BiLSTM-Att Model for Online Public Opinion Text Sentiment Analysis

As an essential category of public event management and control,sentiment analysis of online public opinion text plays a vital role in public opinion early warning,network rumor management,and netizens’person-ality portraits under massive public opinion data.The traditional sentiment analysis model is not sensitive to the location information of words,it is difficult to solve the problem of polysemy,and the learning representation ability of long and short sentences is very different,which leads to the low accuracy of sentiment classification.This paper proposes a sentiment analysis model PERT-BiLSTM-Att for public opinion text based on the pre-training model of the disordered language model,bidirectional long-term and short-term memory network and attention mechanism.The model first uses the PERT model pre-trained from the lexical location information of a large amount of corpus to process the text data and obtain the dynamic feature representation of the text.Then the semantic features are input into BiLSTM to learn context sequence information and enhance the model’s ability to represent long sequences.Finally,the attention mechanism is used to focus on the words that contribute more to the overall emotional tendency to make up for the lack of short text representation ability of the traditional model,and then the classification results are output through the fully connected network.The experimental results show that the classification accuracy of the model on NLPCC14 and weibo_senti_100k public data sets reach 88.56%and 97.05%,respectively,and the accuracy reaches 95.95%on the data set MDC22 composed of Meituan,Dianping and Ctrip comment.It proves that the model has a good effect on sentiment analysis of online public opinion texts on different platforms.The experimental results on different datasets verify the model’s effectiveness in applying sentiment analysis of texts.At the same time,the model has a strong generalization ability and can achieve good results for sentiment analysis of datasets in different fields.

Research on the neutralization control of the RF ion micropropulsion system for the‘Taiji-1’satellite mission

To achieve the neutralization control requirements of the radio-frequency(RF)ion microthruster(μRIT)in the‘Taiji-1’satellite mission,we proposed an active neutralization control solution that is based on the carbon nanotube field emission technology.The carbon nanotube field emission neutralizer(CNTN)has the characteristics of light weight,small size,and propellantless,which is especially suitable for the neutralization control tasks of ion microthrusters.The Institute of Mechanics,Chinese Academy of Sciences,in collaboration with Tsinghua University,has successfully developed a CNTN to meet mission requirements.On the ground,the feasibility of cooperation working betweenμRIT and CNTN was fully verified,as well as the simulation and experimental study of neutralization control strategy,which finally passed the engineering assessment test.Since the launch of‘Taiji-1’satellite on 31 August,2019,the RF ion micropropulsion system has successfully completed nearly one hundred test missions in space.The test results indicate that CNTN does not have performance degradation,and the neutralization control strategy is effective.

High magnetic energy product in isotropic nanocomposite powders with high percent of soft phase towards ultrastrong magnets

Nanostructure of magnetically hard and soft materials is fascinating for exploring next-generation ul-trastrong permanent magnets with less expensive rare-earth elements.However,the resulting hard/soft nanocomposites often exhibit a low remanence/energy product due to the challenge in obtaining ideal phase components and appropriate soft phase fraction.In this work,a novel microstructure of multiple phases consisting of 1:5 phase and 1:3 phase as main hard phase,and a high ratio of Fe(Co)(27 wt.%-48 wt.%)as soft phase was obtained in Sm-Co(Fe)/Fe nanocomposite magnet.The grain size of both hard and soft phases below 15 nm was observed.The optimal energy product for Sm-Co(Fe)/Fe(Co)nanocom-posite is 2.1 times(an increment of 107%)of the corresponding single-hard-phase powders without soft phase.It reports that the isotropic nanocomposite powders exhibit a record of magnetic energy product larger than 25 MGOe(the highest value is 28.6 MGOe).The high performance and the microstructure achieved in this work for the isotropic powders will shed light on and provide a good premise for syn-thesizing high performance anisotropic bulk nanocomposite magnets.

Calculation of Space NURBS Curve Interpolation Error

Aiming at the problem of low accuracy of interpolation error calculation of existing NURBS curves, an approximate method for the distance between a point and a NURBS interpolation curve is proposed while satisfying the accuracy of the solution. Firstly, the minimum parameter interval of the node vector corresponding to the data point under test in the original data point sequence is determined, and the parameter interval is subdivided according to the corresponding step size, and the corresponding parameter value is obtained. Secondly, the distance from the measured point to the NURBS curve is calculated, and the nearest distance is found out. The node interval is subdivided again on one side of the nearest distance. Finally, the distance between the data point to be measured and each subdivision point is calculated again, and the minimum distance is taken as the interpolation error between the point and the NURBS curve. The simulation results of actual tool position data show that this method can more accurately obtain the error of spatial NURBS interpolation curve.

Comparison of mini-probe endoscopic ultrasonography with computed tomography scan in preoperative staging of esophageal cancer

Objective:To compare mini-probe endoscopic ultrasonography(MCUS)with computed tomography(CT)in pre-operative T and N staging of esophageal cancer,and to find out the MCUS parameters to judge lymph nodes metastasis for esophageal cancer.Methods:Thirty-five patients received both MCUS and CT preoperatively,on both of which the T and N stages were determined.The accuracy,sensitivity,specificity,positive predicting value and negative predicting value were compared with the postoperative pathological results.Results:The accuracy of MCUS was 85.7% in T staging and 85.7% and 80.0% in N staging by two different methods,which were 45.7% and 74.3%,respectively,by CT.Conclusion:MCUS is better than CT in preoperative staging for esophageal cancer.The ratio of short to long axis(S/L)combined with short axis is a useful way to determine lymph nodes metastasis.

High energy product of isotropic bulk Sm-Co/α-Fe(Co)nanocomposite magnet with multiple hard phases and nanoscale grains

Nanocomposite magnets consisting of hard and soft magnetic phases have potential applications to be the next generation of permanent magnets with very high energy product and less expensive rare-earth elements.But it is still a big challenge to obtain bulk magnets with ideal microstructure and high performance.In this work,two-step warm processing at relative low temperatures had been adopted to obtain nearly theoretical density bulk nanocomposite magnets from amorphous/nanocrystalline powder precursors.Novel nanostructures consisting of multiple Sm-Co hard phases(SmCo_(5)as main phase,SmCO_(3),SmCo_(7),Sm_(2)Co_(17)as minor phases)and 25 wt%α-Fe(Co)soft phase,nanoscale grain size below 20 nm for both the hard phase and soft phase,and the diffusion of Fe and Co compositions had been obtained in bulk isotropic magnets.Besides the ideal nanostructures,a high coercivity of 5.9 kOe,M_(r)/M_(s)value of 0.78 and a high square degree of demagnetization curve S=0.47 were obtained.All of these factors together brought a new record-high energy product(BH)_(max)of 23.6 MGOe.These results make an important step toward fabricating novel nanostructure with high performance.

Artificial intelligence-based ultrasound imaging technologies for hepatic diseases

Ultrasound(US)imaging is a non-invasive,real-time,economical,and convenient imaging modality that has been widely used in diagnosing and treating hepatic diseases.Artificial intelligence(AI)technology can predict or make decisions based on the experience of clinical experts and knowledge obtained from training data.This technology can help clinicians improve the detection efficiency and evaluate hepatic diseases,promote clinical treatment of the liver,and predict the response of the liver after treatment.This review summarizes the current rapid development of US technology and related AI methods in the diagnosis and treatment of hepatic diseases.Covered topics include steatosis grading,fibrosis staging,detection of focal liver lesions,US image segmentation,multimodal image registration,and other applications.At present,the field of AI in US imaging is still in its early stages.With the future progress of AI technology,AI-based US imaging can further improve diagnosis,reduce medical costs,and optimize US-based clinical workflow.This technology has broad prospects for application to hepatic diseases.

Building up 1-D, 2-D, and 3-D Polyiodide Frameworks by Finely Tuning the Size of Aryls on Ar-S-TTF in the Charge-Transfer （CT） Complexes of Ar-S-TTFs and Iodine

The arylthio-substituted tetrathiafuivalenes （Ar-S-TTFs） are electron donors having three reversible states, neutral, cation radical, and dica- tion. The charge-transfer （CT） between Ar-S-TTFs （TTF1--TTF3） and iodine （12） is reported herein. TTF1--TTF3 show the CT with 12 in the CH2C12 solution, but they are not completely converted into cation radical state. In CT complexes of TTF1--TTF3 with 12, the charged states of Ar-S-TTFs are distinct from those in solution. TTF1 is at cation radical state, and TTF2--TTF3 are oxidized to dication. The iodine components in complexes show various structures including 1-D chain of V-shaped （Is）-, and 2-D and 3-D iodine networks composed of 12 and （13）^- .