Heterogeneous Image Knowledge Driven Visual Perception

Dear Editor,This letter is concerned with visual perception closely related to heterogeneous images.Facing the huge challenge brought by different image modalities,we propose a visual perception framework based on heterogeneous image knowledge,i.e.,the domain knowledge associated with specific vision tasks,to better address the corresponding visual perception problems.

Low-Cost Federated Broad Learning for Privacy-Preserved Knowledge Sharing in the RIS-Aided Internet of Vehicles

High-efficiency and low-cost knowledge sharing can improve the decision-making ability of autonomous vehicles by mining knowledge from the Internet of Vehicles(IoVs).However,it is challenging to ensure high efficiency of local data learning models while preventing privacy leakage in a high mobility environment.In order to protect data privacy and improve data learning efficiency in knowledge sharing,we propose an asynchronous federated broad learning(FBL)framework that integrates broad learning(BL)into federated learning(FL).In FBL,we design a broad fully connected model(BFCM)as a local model for training client data.To enhance the wireless channel quality for knowledge sharing and reduce the communication and computation cost of participating clients,we construct a joint resource allocation and reconfigurable intelligent surface(RIS)configuration optimization framework for FBL.The problem is decoupled into two convex subproblems.Aiming to improve the resource scheduling efficiency in FBL,a double Davidon–Fletcher–Powell(DDFP)algorithm is presented to solve the time slot allocation and RIS configuration problem.Based on the results of resource scheduling,we design a reward-allocation algorithm based on federated incentive learning(FIL)in FBL to compensate clients for their costs.The simulation results show that the proposed FBL framework achieves better performance than the comparison models in terms of efficiency,accuracy,and cost for knowledge sharing in the IoV.

Incorporating empirical knowledge into data-driven variable selection for quantitative analysis of coal ash content by laser-induced breakdown spectroscopy

Laser-induced breakdown spectroscopy(LIBS)has become a widely used atomic spectroscopic technique for rapid coal analysis.However,the vast amount of spectral information in LIBS contains signal uncertainty,which can affect its quantification performance.In this work,we propose a hybrid variable selection method to improve the performance of LIBS quantification.Important variables are first identified using Pearson's correlation coefficient,mutual information,least absolute shrinkage and selection operator(LASSO)and random forest,and then filtered and combined with empirical variables related to fingerprint elements of coal ash content.Subsequently,these variables are fed into a partial least squares regression(PLSR).Additionally,in some models,certain variables unrelated to ash content are removed manually to study the impact of variable deselection on model performance.The proposed hybrid strategy was tested on three LIBS datasets for quantitative analysis of coal ash content and compared with the corresponding data-driven baseline method.It is significantly better than the variable selection only method based on empirical knowledge and in most cases outperforms the baseline method.The results showed that on all three datasets the hybrid strategy for variable selection combining empirical knowledge and data-driven algorithms achieved the lowest root mean square error of prediction(RMSEP)values of 1.605,3.478 and 1.647,respectively,which were significantly lower than those obtained from multiple linear regression using only 12 empirical variables,which are 1.959,3.718 and 2.181,respectively.The LASSO-PLSR model with empirical support and 20 selected variables exhibited a significantly improved performance after variable deselection,with RMSEP values dropping from 1.635,3.962 and 1.647 to 1.483,3.086 and 1.567,respectively.Such results demonstrate that using empirical knowledge as a support for datadriven variable selection can be a viable approach to improve the accuracy and reliability of LIBS quantification.

A new evolutional model for institutional field knowledge flow network

Purpose:This paper aims to address the limitations in existing research on the evolution of knowledge flow networks by proposing a meso-level institutional field knowledge flow network evolution model(IKM).The purpose is to simulate the construction process of a knowledge flow network using knowledge organizations as units and to investigate its effectiveness in replicating institutional field knowledge flow networks.Design/Methodology/Approach:The IKM model enhances the preferential attachment and growth observed in scale-free BA networks,while incorporating three adjustment parameters to simulate the selection of connection targets and the types of nodes involved in the network evolution process Using the PageRank algorithm to calculate the significance of nodes within the knowledge flow network.To compare its performance,the BA and DMS models are also employed for simulating the network.Pearson coefficient analysis is conducted on the simulated networks generated by the IKM,BA and DMS models,as well as on the actual network.Findings:The research findings demonstrate that the IKM model outperforms the BA and DMS models in replicating the institutional field knowledge flow network.It provides comprehensive insights into the evolution mechanism of knowledge flow networks in the scientific research realm.The model also exhibits potential applicability to other knowledge networks that involve knowledge organizations as node units.Research Limitations:This study has some limitations.Firstly,it primarily focuses on the evolution of knowledge flow networks within the field of physics,neglecting other fields.Additionally,the analysis is based on a specific set of data,which may limit the generalizability of the findings.Future research could address these limitations by exploring knowledge flow networks in diverse fields and utilizing broader datasets.Practical Implications:The proposed IKM model offers practical implications for the construction and analysis of knowledge flow networks within institutions.It provides a valuable tool for understanding and managing knowledge exchange between knowledge organizations.The model can aid in optimizing knowledge flow and enhancing collaboration within organizations.Originality/value:This research highlights the significance of meso-level studies in understanding knowledge organization and its impact on knowledge flow networks.The IKM model demonstrates its effectiveness in replicating institutional field knowledge flow networks and offers practical implications for knowledge management in institutions.Moreover,the model has the potential to be applied to other knowledge networks,which are formed by knowledge organizations as node units.

A Cognitive Study on Politeness Intention Processing and Its Association with Pragmatic Failure in Cross-Cultural Communication

Although a large number of studies have focused on various aspects of politeness,very little is known about how politeness intention is activated cognitively during verbal communication.The present study aims to explore the cognitive mechanism of politeness intention processing,and how it is related to pragmatic failure during cross-cultural communication.Using 30 Chinese EFL university students who were instructed to finish a probe word judgment task with 96 virtual scenarios,the results indicate that within both mono-and cross-cultural contexts,the response time in the experimental scenarios was significantly slower than that of the filler scenarios.This suggests that politeness intention was activated while understanding the surface meaning of the conversation;however,the EFL learners could not completely avoid the negative transfer of their native politeness conventions when they were comprehending the conversational intention of the target language.Furthermore,no significant differences in response time were found between the groups with high and low English pragmatic competence,illustrating that transferring the pragmatic rules and principles into cross-cultural communication skills was more cognitively demanding.Overall,this study adds to the literature on politeness research and provides some implications for foreign language pragmatic instructions.

Nutrition Awareness and Knowledge and Body Mass Index in Adolescents in Public Junior Secondary Schools

Background: Non-communicable diseases are increasing among adolescents. The decision about diet is the foundation of eating habits that could persist to adulthood. Dietary decisions, which usually are hard to change later in life, make nutrition education at school paramount to prevent obesity and NCDs, and promote healthy eating. Objectives: To assess level of nutrition awareness and knowledge of healthy eating and food intake behaviors and association with Body Mass Index (BMI) and age. Methods: A cross sectional study that included measures such as age, gender, socioeconomic status, BMI, and nutrition knowledge was conducted in 264 respondents from 18th June 2015 to 9th July 2015. The nutrition knowledge questionnaire was composed of 24 questions divided into food nutrients, food contents, healthiest foods, and energy expenditure and nutrition benefits. CDC BMI chart for 2-20-year-olds was used to plot respondent’s weight and height. Results: The mean age of the respondents was 14.3 years (SD 0.79). Most of the respondents (153/252, 53.6%) had a low socio-economic status as categorized by the present study. The mean (SD) BMI was 20.08 (3.90). Most respondents (56.3%, 142/252) failed the knowledge test and scored below 50% and only two respondents (0.8%) had excellent nutrition knowledge. The mean percentage achieved was 46.1% (SD 15.91) ranging from 8.3% to 87.5%. There was a significant correlation between nutrition knowledge and BMI (p = 0.001). Conclusion: The study shows that adolescents do not have adequate nutrition knowledge, placing them at risk for developing non-communicable diseases later in life. Nutrition education programs are urgently needed for teachers, parents, and children.

GATiT:An Intelligent Diagnosis Model Based on Graph Attention Network Incorporating Text Representation in Knowledge Reasoning

The growing prevalence of knowledge reasoning using knowledge graphs(KGs)has substantially improved the accuracy and efficiency of intelligent medical diagnosis.However,current models primarily integrate electronic medical records(EMRs)and KGs into the knowledge reasoning process,ignoring the differing significance of various types of knowledge in EMRs and the diverse data types present in the text.To better integrate EMR text information,we propose a novel intelligent diagnostic model named the Graph ATtention network incorporating Text representation in knowledge reasoning(GATiT),which comprises text representation,subgraph construction,knowledge reasoning,and diagnostic classification.In the text representation process,GATiT uses a pre-trained model to obtain text representations of the EMRs and additionally enhances embeddings by including chief complaint information and numerical information in the input.In the subgraph construction process,GATiT constructs text subgraphs and disease subgraphs from the KG,utilizing EMR text and the disease to be diagnosed.To differentiate the varying importance of nodes within the subgraphs features such as node categories,relevance scores,and other relevant factors are introduced into the text subgraph.Themessage-passing strategy and attention weight calculation of the graph attention network are adjusted to learn these features in the knowledge reasoning process.Finally,in the diagnostic classification process,the interactive attention-based fusion method integrates the results of knowledge reasoning with text representations to produce the final diagnosis results.Experimental results on multi-label and single-label EMR datasets demonstrate the model’s superiority over several state-of-theart methods.

Combining Deep Learning with Knowledge Graph for Design Knowledge Acquisition in Conceptual Product Design

The acquisition of valuable design knowledge from massive fragmentary data is challenging for designers in conceptual product design.This study proposes a novel method for acquiring design knowledge by combining deep learning with knowledge graph.Specifically,the design knowledge acquisition method utilises the knowledge extraction model to extract design-related entities and relations from fragmentary data,and further constructs the knowledge graph to support design knowledge acquisition for conceptual product design.Moreover,the knowledge extraction model introduces ALBERT to solve memory limitation and communication overhead in the entity extraction module,and uses multi-granularity information to overcome segmentation errors and polysemy ambiguity in the relation extraction module.Experimental comparison verified the effectiveness and accuracy of the proposed knowledge extraction model.The case study demonstrated the feasibility of the knowledge graph construction with real fragmentary porcelain data and showed the capability to provide designers with interconnected and visualised design knowledge.

A Survey of Knowledge Graph Construction Using Machine Learning

Knowledge graph(KG)serves as a specialized semantic network that encapsulates intricate relationships among real-world entities within a structured framework.This framework facilitates a transformation in information retrieval,transitioning it from mere string matching to far more sophisticated entity matching.In this transformative process,the advancement of artificial intelligence and intelligent information services is invigorated.Meanwhile,the role ofmachine learningmethod in the construction of KG is important,and these techniques have already achieved initial success.This article embarks on a comprehensive journey through the last strides in the field of KG via machine learning.With a profound amalgamation of cutting-edge research in machine learning,this article undertakes a systematical exploration of KG construction methods in three distinct phases:entity learning,ontology learning,and knowledge reasoning.Especially,a meticulous dissection of machine learningdriven algorithms is conducted,spotlighting their contributions to critical facets such as entity extraction,relation extraction,entity linking,and link prediction.Moreover,this article also provides an analysis of the unresolved challenges and emerging trajectories that beckon within the expansive application of machine learning-fueled,large-scale KG construction.

A novel fracture-cavity reservoir outcrop geological knowledge base construction method considering parameter collection and processing,mutual transformation of data-knowledge,application and update

This study endeavors to formulate a comprehensive methodology for establishing a Geological Knowledge Base(GKB)tailored to fracture-cavity reservoir outcrops within the North Tarim Basin.The acquisition of quantitative geological parameters was accomplished through diverse means such as outcrop observations,thin section studies,unmanned aerial vehicle scanning,and high-resolution cameras.Subsequently,a three-dimensional digital outcrop model was generated,and the parameters were standardized.An assessment of traditional geological knowledge was conducted to delineate the knowledge framework,content,and system of the GKB.The basic parameter knowledge was extracted using multiscale fine characterization techniques,including core statistics,field observations,and microscopic thin section analysis.Key mechanism knowledge was identified by integrating trace elements from filling,isotope geochemical tests,and water-rock simulation experiments.Significant representational knowledge was then extracted by employing various methods such as multiple linear regression,neural network technology,and discriminant classification.Subsequently,an analogy study was performed on the karst fracture-cavity system(KFCS)in both outcrop and underground reservoir settings.The results underscored several key findings:(1)Utilization of a diverse range of techniques,including outcrop observations,core statistics,unmanned aerial vehicle scanning,high-resolution cameras,thin section analysis,and electron scanning imaging,enabled the acquisition and standardization of data.This facilitated effective management and integration of geological parameter data from multiple sources and scales.(2)The GKB for fracture-cavity reservoir outcrops,encompassing basic parameter knowledge,key mechanism knowledge,and significant representational knowledge,provides robust data support and systematic geological insights for the intricate and in-depth examination of the genetic mechanisms of fracture-cavity reservoirs.(3)The developmental characteristics of fracturecavities in karst outcrops offer effective,efficient,and accurate guidance for fracture-cavity research in underground karst reservoirs.The outlined construction method of the outcrop geological knowledge base is applicable to various fracture-cavity reservoirs in different layers and regions worldwide.

Reviewer Acknowledgements

The editors of International Journal of Ophthalmology gratefully acknowledge the members of IJO Editorial Board and reviewers from 57 countries and regions who participated in the peer-reviews and provided their valuable comments between Nov.1^(st),2022 and Oct.31^(st),2023.

Assessment of Knowledge, Attitude and Practices among Healthcare Workers in a Tertiary Care Hospital on Needle Stick Injury

Purpose: Needle-stick injury (NSI) is one of the most potential occupational hazards for healthcare workers because of the transmission of blood-borne pathogens. As per recent data, around 30 lakh healthcare workers sustain Needle stick injuries each year. This study was conducted to assess healthcare workers’ knowledge, attitude and practices regarding needle stick injury. Materials & Methods: A cross-sectional study was conducted in a Tertiary Care Hospital over the period of 3 months. The study population consisted of Intern Doctors, Post Graduate resident Doctors, Staff Nurses, laboratory technicians of Government Medical College and New Civil Hospital, Surat (n = 300). The data were collected using a self-administered questionnaire via the means of Google Forms. Questionnaire was made with prior review literature. The data obtained were entered and analysed in Microsoft Excel. Results: The prevalence of NSI in our study was 46%, with a higher prevalence among the PG residents (72%). Overall scores regarding knowledge and attitude were better in PG residents (knowledge score > 7 in 71% and Attitude Score > 7 in 68% of PG Residents). Even though the PG residents scored highest in the knowledge category, the majority of them suffered needle stick injuries as a result of poor practice scores. Among those who had NSI (n = 139/300), 70% of study participants had superficial injuries, only 9% reported the incident, 18% got medical attention within 2 hours of the incident, and 7% followed up to recheck their viral markers status. Most incidents of NSI were due to hypodermic needles while recapping needles. Conclusion: Exposure to needle stick injuries and their underreporting remains a common problem. It is imperative that healthcare workers receive regular training on the proper handling of sharp objects. We can also draw the conclusion that preventing NSIs requires putting knowledge into practice.

Global systematic review and meta-analysis of knowledge, attitudes, and practices towards dengue fever among the general population

Objective:To determine the global level of knowledge,attitudes,and practices towards dengue fever among the general population.Methods:To complete this systematic review and meta-analysis,a thorough search for pertinent English-language literature was undertaken during the study's extension until October 2023.The search used Google Scholar,Scopus,PubMed/MEDLINE,Science Direct,Web of Science,EMBASE,Springer,and ProQuest.A quality assessment checklist developed using a modified Newcastle-Ottawa Scale for the cross-sectional study was used to evaluate the risk of bias in the included papers.Inverse variance and Cochran Q statistics were employed in the STATA software version 14 to assess study heterogeneity.When there was heterogeneity,the Dersimonian and Liard random-effects models were used.Results:59 Studies totaling 87353 participants were included in this meta-analysis.These investigations included 86278 participants in 55 studies on knowledge,20196 in 33 studies on attitudes,and 74881 in 29 studies on practices.The pooled estimates for sufficient knowledge,positive attitudes,and dengue fever preventive behaviors among the general population were determined as 40.1%(95%CI 33.8%-46.5%),46.8%(95%CI 35.8%-58.9%),and 38.3%(95%CI 28.4%-48.2%),respectively.Europe exhibits the highest knowledge level at 63.5%,and Africa shows the lowest at 20.3%.Positive attitudes are most prevalent in the Eastern Mediterranean(54.1%)and Southeast Asia(53.6%),contrasting sharply with the Americas,where attitudes are notably lower at 9.05%.Regarding preventive behaviors,the Americas demonstrate a prevalence of 12.1%,Southeast Asia at 28.1%,Western Pacific at 49.6%,Eastern Mediterranean at 44.8%,and Africa at 47.4%.Conclusions:Regional disparities about the knowledge,attitude and preventive bahaviors are evident with Europe exhibiting the highest knowledge level while Africa has the lowest.These findings emphasize the importance of targeted public health interventions tailored to regional contexts,highlighting the need for region-specific strategies to enhance dengue-related knowledge and encourage positive attitudes and preventive behaviors.

Investigation on the Knowledge, Attitude and Practice of Oral Health among Medical College and University Undergraduate

Objectives: This study aims to investigate the status of knowledge, attitude and practice (KAP) of oral health among medical undergraduate students, and provide reference for implementing oral health interventions. Methods: A total of 528 undergraduate students enrolled in Fuzhou Medical College from February 2023 to September 2023 were selected as the research subjects. Their oral health KAP were investigated, and the oral health behavior habits of different types of medical students were compared, and possible influencing factors were analyzed. Results: The total awareness rate of oral health knowledge among medical students is 77.0%, with an average score of 3.85 ± 1.16 points. The overall positive rate of oral health attitudes among medical students is 80.0%, with an average score of 3.19 ± 0.72 points. The total qualified rate of oral health behavior is 65.9%, with an average score of 4.61 ± 1.23 points. The scores of oral health knowledge, attitudes, and behaviors among medical students are related to gender, major, smoking status, and oral health status. The frequency of brushing teeth in the female group was higher than that in the male group, while the habit of brushing teeth before bedtime and the frequency of timely replacement of toothbrushes when deformed were lower, with statistical significance (p 0.05). The frequency of timely replacement of toothbrushes varies among medical students from different majors, and the difference is statistically significant (p 0.05). People who have a habit of eating hot and cold food have a higher frequency of brushing their teeth every day, and the difference is statistically significant (p 0.05). Non smokers have a better habit of brushing their teeth before bedtime and a higher frequency of timely replacement when their toothbrush deforms, with a statistically significant difference (p 0.05). The frequency of using fluoride toothpaste or medicated toothpaste, having a habit of unilateral chewing, and timely replacement of toothbrushes when deformed in patients with existing oral problems is higher than that of those without oral problems, and the difference is statistically significant (p 0.05). Conclusion: The knowledge, attitude, and behavior of oral health among medical students in this school are above average. Students with different genders, dietary and smoking habits, and oral health status have different oral health behavioral habits. It is recommended to include oral health education in mandatory courses for various medical majors.

The Transmission,Establishment and Cross-cultural Integration of Chinese Medicine in the Mainstream Healthcare,through the Eyes of a Generation of Visionaries and Pioneers

It has historically been very difficult to trace the history of the westward transmission of Chinese medicine through the accounts of its protagonists. Many of the early scholars such as Jack Worsley, Dick Van Buren, and Joe Goodman were reluctant to divulge information about the source of their knowledge, or their professional qualifications. Others, such as John Shen and Hong Yuan-bain were early 20th century immigrants who transmitted highly personalized versions of acupuncture and Chinese medicine to select disciples. Eventually, a new class of scholars appeared, including names such as Ted Kaptchuk, Peter Deadman, Nigel Wiseman, William Morris, Peter Eckman, John Mc Donald, Charles Buck, and the late Giovanni Maciocia who looked for answers back in China, developed translation methodologies and terminology, compiled the main textbooks currently in use at TCM colleges, overcame enormous scholastic adversity, developed courses and pursued the regulation and accreditation of TCM in various countries. This special issue synopsizes the path towards the global acculturation of TCM over the last 50 years, the main protagonists, the enormous accomplishments they have achieved for the profession, their philosophy, their clinical perspectives and visions for the future.

Knowledge of Hospital Acquired Infections (HAIs) among Medical Students in a Tertiary Hospital in Jos North Local Government Area, Plateau State, Nigeria

Background: Hospital Acquired Infections (HAIs) remain a common cause of death, functional disability, emotional suffering and economic burden among hospitalized patients. Knowledge of HAIs is important in its prevention and control. This study seeks to assess the knowledge of Hospital Acquired Infections (HAIs) among medical students in a Tertiary Hospital in Jos North Local Government Area, Plateau State, Nigeria. Methods: This was a descriptive cross-sectional study done in October 2019 among clinical medical students using a Multistage sampling technique. Data was collected using a self-administered structured questionnaire and analyzed using the IBM SPSS 20 (Statistical Package for the Social Sciences). Ethical approval was granted by Bingham University Teaching Hospital, Ethics Committee, Jos, Plateau State. Results: A total of 219 students in the clinical arm of the College of Medicine and Health Sciences were selected. A higher proportion (97.7%) of respondents knew about Hospital Acquired Infections and 85.4% knew that Hospital Acquired infections occur in the hospital, and (86.3%) considered patients contagious with half (58.9%) considered patients as the most important source of HAIs, followed by care givers (13.2%), then doctors including medical students and interns (10.0%) and lastly nurses (8.7%). The majority of respondents (70.8%) considered Surgical Wound Infections to be the most commonly occurring HAI, followed by UTIs (69.9%), RTIs (61.2%), BSIs (37.0%) and others (0.9%). The clinical thermometer was the instrument that most commonly transmits HAIs (82.6%), then followed by stethoscope (62.1%), white coats (53.9%), and blood pressure cuff (51.1%). Most respondents knew the infectious substances, like blood (96.3%), nasal discharge (82.6%), saliva (85.3%), and faeces (79.4%) transmitted HAIs, 72.6% of the respondents said that they were aware of the recommended hand washing techniques by WHO. Conclusion: The majority of students 91.3% had good knowledge while 8.7% had poor knowledge of HAIs. Lower classes had more respondents with poor knowledge. This finding was statistically significant (p = 0.002, Chi-square 12.819). Students are encouraged to keep up the level of knowledge they have about HAIs. These students can help improve the knowledge of those whose knowledge level is low. Government and NGOs should support sponsorship for capacity-building events targeted at HAIs for healthcare workers and medical students.

A cross-sectional study to assess medication safety,knowledge,attitude,and practices regarding nutrition and medication among pregnant women

Objective:To assess pregnant women's knowledge,attitude,and practice regarding nutrition and medication usage,analyse the prescribing pattern,and categorize them based on the Food and Drug Administration(FDA)guidelines.Methods:A cross-sectional study was conducted with 264 pregnant women in the obstetrics and gynaecology department of a tertiary care hospital from October 2022 to August 2023.A knowledge,attitude,and practice(KAP)questionnaire was prepared in English language by the researchers and validated by an expert panel consisting of 12 members.The validated questionnaire was then translated into regional languages,Kannada and Malayalam.The reliability of the questionnaire was assessed with test-retest method with a representative sample population of 30 subjects(10 subjects for each language).The subjects'knowledge,attitude,and practice were evaluated using the validated KAP questionnaire.The safety of the medication was assessed using the FDA drug safety classification for pregnancy.Results:The mean scores for nutritional and medication usage knowledge,attitude,and practice were 4.14±1.15,4.50±1.09,and 3.00±1.47,respectively.Among 30 prescribed medications,3 belong to category A(no risk in human studies),8 belong to category B(no risk in animal studies),18 belong to category C(risk cannot be ruled out)and 1 drug is not classified.A significant association was observed between medication knowledge and practice(r=0.159,P=0.010).Conclusions:Most of the study population knows the need to maintain good dietary and medication practices during pregnancy.Counselling pregnant women regarding diet and medication usage is crucial in maternal care.

RepDNet:A re-parameterization despeckling network for autonomous underwater side-scan sonar imaging with prior-knowledge customized convolution

Side-scan sonar(SSS)is now a prevalent instrument for large-scale seafloor topography measurements,deployable on an autonomous underwater vehicle(AUV)to execute fully automated underwater acoustic scanning imaging along a predetermined trajectory.However,SSS images often suffer from speckle noise caused by mutual interference between echoes,and limited AUV computational resources further hinder noise suppression.Existing approaches for SSS image processing and speckle noise reduction rely heavily on complex network structures and fail to combine the benefits of deep learning and domain knowledge.To address the problem,Rep DNet,a novel and effective despeckling convolutional neural network is proposed.Rep DNet introduces two re-parameterized blocks:the Pixel Smoothing Block(PSB)and Edge Enhancement Block(EEB),preserving edge information while attenuating speckle noise.During training,PSB and EEB manifest as double-layered multi-branch structures,integrating first-order and secondorder derivatives and smoothing functions.During inference,the branches are re-parameterized into a 3×3 convolution,enabling efficient inference without sacrificing accuracy.Rep DNet comprises three computational operations:3×3 convolution,element-wise summation and Rectified Linear Unit activation.Evaluations on benchmark datasets,a real SSS dataset and Data collected at Lake Mulan aestablish Rep DNet as a well-balanced network,meeting the AUV computational constraints in terms of performance and latency.

An Intelligent Quality Control Method for Manufacturing Processes Based on a Human–Cyber–Physical Knowledge Graph

Quality management is a constant and significant concern in enterprises.Effective determination of correct solutions for comprehensive problems helps avoid increased backtesting costs.This study proposes an intelligent quality control method for manufacturing processes based on a human–cyber–physical(HCP)knowledge graph,which is a systematic method that encompasses the following elements:data management and classification based on HCP ternary data,HCP ontology construction,knowledge extraction for constructing an HCP knowledge graph,and comprehensive application of quality control based on HCP knowledge.The proposed method implements case retrieval,automatic analysis,and assisted decision making based on an HCP knowledge graph,enabling quality monitoring,inspection,diagnosis,and maintenance strategies for quality control.In practical applications,the proposed modular and hierarchical HCP ontology exhibits significant superiority in terms of shareability and reusability of the acquired knowledge.Moreover,the HCP knowledge graph deeply integrates the provided HCP data and effectively supports comprehensive decision making.The proposed method was implemented in cases involving an automotive production line and a gear manufacturing process,and the effectiveness of the method was verified by the application system deployed.Furthermore,the proposed method can be extended to other manufacturing process quality control tasks.

De-biased knowledge distillation framework based on knowledge infusion and label de-biasing techniques

Knowledge distillation,as a pivotal technique in the field of model compression,has been widely applied across various domains.However,the problem of student model performance being limited due to inherent biases in the teacher model during the distillation process still persists.To address the inherent biases in knowledge distillation,we propose a de-biased knowledge distillation framework tailored for binary classification tasks.For the pre-trained teacher model,biases in the soft labels are mitigated through knowledge infusion and label de-biasing techniques.Based on this,a de-biased distillation loss is introduced,allowing the de-biased labels to replace the soft labels as the fitting target for the student model.This approach enables the student model to learn from the corrected model information,achieving high-performance deployment on lightweight student models.Experiments conducted on multiple real-world datasets demonstrate that deep learning models compressed under the de-biased knowledge distillation framework significantly outperform traditional response-based and feature-based knowledge distillation models across various evaluation metrics,highlighting the effectiveness and superiority of the de-biased knowledge distillation framework in model compression.