Structured Knowledge Research Articles

A study to assess the effectiveness of awareness program on knowledge regarding management of obesity among house wives in village (Larsun) of district Ganderbal Kashmir

Obesity often known as “NEW WORLD SYNDROME” is a new disease despite being an old recognized physical feature. Regardless of age or socioeconomic background, obesity is a serious social and psychological condition that affects practically everyone. The threat of invasion affects both developed and growing countries. Similar to how they do in industrialized countries, diet and lifestyle, which are significantly changing as a result of the economic and nutritional transition, have an impact on the risk of obesity. a significant risk factor for the onset of non-communicable diseases as hypertension and heart disease, among others Globally, obesity has reached epidemic levels; at least 2.8 million people die from being overweight or obese each year. Obesity was originally only a problem in high-income nations, but it is now widespread in middle- and low-income nations as well.The knowledge of housewives in the village of Larsun, district of Ganderbal, regarding obesity was evaluated using a quantitative approach. Data from housewives who met the inclusion criteria were gathered using a purposeful sampling strategy. A self-administered structured knowledge questionnaire was used to obtain the data. 11 professionals validated the tool. By utilizing the Karal-Pearson correlation coefficient (r = 0.83), the tool's dependability was determined. Following the pretest, a structured teaching programme was offered. A posttest was conducted three months later. Quantitative analysis was used to examine the data.The majority of the subject (12.9%) scored poorly on the pretest, followed by 61.3% who scored well, and 25.8% who scored well. 100% had outstanding knowledge on the posttest. The mean knowledge score before the test was (16.45 +_.943), and the mean knowledge score after the test was (28.45 +_1.12). Additionally, it showed that it had statistical significance (P 0.05). The funding of the study came to the conclusion that there was a considerable improvement in housewives' understanding of obesity following the implementation of a self-structured instruction programme.

Effectiveness of Awareness Programme on Knowledge of Teachers Regarding School Bullying Among Children at Selected Urban Schools of Bengaluru

Background: A quasi-experimental design was used to evaluate the effectiveness of awareness program on knowledge of teachers regarding school bullying among children at selected urban schools of Bengaluru. A total sample of 40 teachers were selected using purposive sampling technique. The objective of the study was to assess the level of knowledge of teachers regarding school bullying among children and to evaluate the effectiveness of awareness programme on knowledge of teachers regarding school bullying among children. The final objective was to find out the association between pre-test level of knowledge score of teachers regarding school bullying among children and selected socio demographic variables. Materials and Methods: A quasi experimental design was used to conduct the study. A sample comprising of 40 teachers were enrolled using purposive sampling technique. The conceptual framework adopted for the study was based on General system theory by Ludwig von Bertalanffy model of nursing. Tools used for data collection were demographic Performa and structured knowledge questionnaire. Results: Data analysis was done using descriptive and inferential statistics. Findings of the study revealed that the mean post-test knowledge score 16.20± 7.47 was significantly higher than the mean pre-test knowledge score 12.73± 4.64. Paired t value computed at 6.63 was statistically significant at p<0.05. which revealed that, there is significant increase in the mean post-test knowledge score. There was no significant association was observed at 0.05 found between pre-test level knowledge scores and selected demographic variables. Conclusion: The findings of the study clearly showed that the structured teaching programme was significantly effective in improving the knowledge of teachers regarding school bullying. Keywords: Awareness, Teachers, Children, Urban School.

Knowledge of child sexual abuse and attitudes towards reporting it among teachers and parents of children studying in selected primary schools of Udupi Taluk, India

BackgroundChild sexual abuse is one of the major issues of concern globally. Teachers and parents being the child’s primary caregivers should be knowledgeable regarding child sexual abuse.Aim of the studyThis study aimed to assess knowledge about child sexual abuse, determine attitudes toward reporting child sexual abuse, and find the relationship between knowledge and the attitude among the teachers and parents of the children studying in selected primary schools of Udupi taluk.MethodsA descriptive survey design was adopted; the study participants were 90 teachers and 50 parents of the children studying in selected primary schools of Udupi Taluk. The instruments used were demographic proforma, a structured knowledge questionnaire about child sexual abuse, and an attitude scale toward reporting it.ResultsResults depicted that 50% of the teachers had average knowledge and 50% had good knowledge about child sexual abuse. All the teachers reported a favorable attitude towards reporting child sexual abuse. Similarly, 80% of the parents had average knowledge about child sexual abuse, and a majority of 76% had a favorable attitude towards reporting child sexual abuse. Unfavorable attitude towards reporting child sexual abuse was reported by 24% of the parents. No statistically significant correlation was found between knowledge and attitude toward reporting child sexual abuse among parents ((χ2 = 1.891, p = 0.388). A significant association was found between teachers’ knowledge scores, their previous knowledge about child sexual abuse (χ2 = 7.56, p = 0.006), and the existence of a school counselor (χ2 = 5.40, p = 0.020). Likewise, the association was found between parents’ knowledge score, educational level of parents (χ2 = 18.3, p = 0.019), and marital status (χ2 = 18.5, p = 0.005).ConclusionChild sexual abuse is one of the major issues of concern globally. Teachers and parents being the child’s primary caregivers should be knowledgeable regarding child sexual abuse. As parents are not exposed to any training regarding identifying and reporting child sexual abuse, they may have unfavorable attitudes toward reporting it.

A hybrid methodology for knowledge organization and application of Chinese civil aviation regulations from mission safety support perspective

Safety is one of the most important issues in aviation. Aviation regulations provide significant information pertinent to the safety design and operation of aircraft; however, this information has not been effectively used. It is difficult to precisely identify and obtain the necessary information due to massive and unstructured provisions. In this study, a hybrid methodology is proposed to realize knowledge system construction using Chinese Civil Aviation Regulations as the object of study. To realize structured knowledge organization and intelligent knowledge application for aviation regulations, the hybrid methodology integrates a semantic cohesion model, a knowledge recognition model, a knowledge organization model, and a knowledge application model. A knowledge system of aviation regulations is built using the hybrid methodology comprising all knowledge necessary for aviation safety. The system provides intelligent knowledge support for the safety analysis of aircraft from the perspective of control system, including the accurate positioning of control elements and thorough acquisition of control conditions. Experiments were conducted to confirm the accuracy of the proposed method, and the 56,853 knowledge triples contained in the knowledge system supported its reliability. A few examples of knowledge retrieval are provided, focusing on the interaction processes of socio-technical elements during aircraft missions. It takes only a few seconds to acquire the knowledge required for safety analysis. The examples show how the hybrid methodology and knowledge system can be utilized to increase the efficiency of safety analysis for socio-technical systems while advancing intelligent knowledge applications in the aviation domain.

Hybrid 5G Positioning Systems with Applications to Mobile Robot Technology

A new concept of 5G/INS integration of artificial intelligence-based systems is proposed, namely the Recurrent Neural Networkbased Fuzzy Inference System (RNNFIS). The 5G system with fuzzy logic was used as a reference during its availability. Data from the 5G system and the inertial navigation system (INS) are used to build a structured knowledge base consisting of the behavior of the INS system in some special scenarios of robotic technology. Using the same data, the proposed fuzzy system is trained to obtain corrected navigation data. In the absence of 5G system information, the system will only utilize data from the INS system and blur correction algorithms to perform its tasks.

Effectiveness of Structured Teaching Programme on Knowledge of Adolescents Regarding Prevention and Early Detection of Thyroid Disorders

Background: A pre-experimental study was conducted to assess the effectiveness of structured teaching programme on knowledge of adolescents regarding prevention and early detection of thyroid disorders at selected pre-university colleges, Bengaluru. A total sample of 60, adolescents were selected using non-probability convenient sampling. The objectives of the study were to assess the pre-test level of knowledge of adolescents regarding prevention and early detection of thyroid disorders and to find the effectiveness of structured teaching program on knowledge of adolescents regarding prevention and early detection of thyroid disorders. The final objective was to find out the association between pre-test score of adolescents with socio-demographic variables. Materials and Methods: A one-group pre-test post-test design was used to conduct the study. A sample comprising of 60 adolescents were enrolled using non-probability sampling technique. The conceptual framework of the study was based on Imogene King’s goal attainment model. Tools used for data collection were demographic Performa and structured knowledge questionnaire. Results: Data analysis was done using descriptive and inferential statistics. Findings of the study revealed that the mean post-test knowledge score 26.15 ±3.66 was significantly higher than the mean pre-test knowledge score 11.58±4.17 (p<0.05). Paired t value computed at 39.58 was statistically significant at p<0.05. which revealed that, there is significant increase in the mean post-test knowledge score. There was no significant association was observed at 0.05 found between pre-test level knowledge scores and selected demographic variables. Conclusion: The findings of the study clearly showed that the structured teaching programme was significantly effective in improving the knowledge of adolescents regarding prevention and early detection of thyroid disorders. Keywords: Effectiveness, structured teaching programme, knowledge of adolescents, prevention of diseases, hypothyroidism, hyperthyroidism.

Midwives as the Primary Care Providers: Knowledge, Attitude, Practice, and Skill of Early Detection of Cervical Cancer Using Visual Inspection with Acetic Acid.

Cervical cancer is the third most common malignancy in women globally. It is also the leading cause of death for women in Indonesia. When detected at an early precancerous stage, cervical cancer is largely preventable. Early detection with Visual Inspection with Acetic Acid (VIA) is an acceptable, affordable, and safe alternative method in developing countries. Midwives, as primary health care providers, can perform VIA at various health center levels. This study evaluated the knowledge, attitude, practice, and skill of cervical cancer screening with VIA among midwives in Denpasar. A cross-sectional study was conducted among 70 midwives at Public Health Centers in Denpasar, Bali, Indonesia, from July-August 2022. The data were collected using a structured knowledge, attitude, and practice questionnaire. An obstetrician-gynecologist assessed the skills with a standardized checklist. Data were analyzed using univariate, bivariate, and multivariate analysis on SPSS version 26. A level of p<0.05 was considered significant with a prevalence ratio (PR) and 95% confidence interval (CI). Out of all midwives, 42 (60.0%) were knowledgeable, 42 (60.0%) had a favorable attitude, 36 (51.4%) had good practice of VIA, and 54 (77.1%) had competent skills. Knowledge (PR=5.00, 95%CI=1.76-14.16), attitude (PR=2.92, 95%CI=1.08-7.89), and skill (PR=11.90, 95%CI=2.44-57.84) were associated with the practice of VIA. Age group and work experience were strongly associated with the training and skill of VIA. Most midwives in Denpasar were knowledgeable, had a favorable attitude, good practice, and competent skills to perform cervical cancer screening using VIA.

Weakly Supervised Concept Map Generation through Task-Guided Graph Translation.

Recent years have witnessed the rapid development of concept map generation techniques due to their advantages in providing well-structured summarization of knowledge from free texts. Traditional unsupervised methods do not generate task-oriented concept maps, whereas deep generative models require large amounts of training data. In this work, we present GT-D2G (Graph Translation-based Document To Graph), an automatic concept map generation framework that leverages generalized NLP pipelines to derive semantic-rich initial graphs, and translates them into more concise structures under the weak supervision of downstream task labels. The concept maps generated by GT-D2G can provide interpretable summarization of structured knowledge for the input texts, which are demonstrated through human evaluation and case studies on three real-world corpora. Further experiments on the downstream task of document classification show that GT-D2G beats other concept map generation methods. Moreover, we specifically validate the labeling efficiency of GT-D2G in the label-efficient learning setting and the flexibility of generated graph sizes in controlled hyper-parameter studies.

Research on Multirelational Entity Modeling based on Knowledge Graph Representation Learning

Background: A research concern revolves around as to what can make the representation of entities and relationships fully integrate the structural information of the knowledge atlas to solve the entity modeling capability in complex relationships. World knowledge can be organized into a structured knowledge network by mining entity and relationship information in real texts. In order to apply the rich structured information in the knowledge map to downstream applications, it is particularly important to express and learn the knowledge map. In the knowledge atlas with expanding scale and more diversified knowledge sources, there are many types of relationships with complex types. The frequency of a single relationship in all triples is further reduced, which increases the difficulty of relational reasoning. Thus, this study aimed to improve the accuracy of relational reasoning and entity reasoning in complex relational models. Methods: For the multi-relational knowledge map, CTransR based on the TransE model and TransR model adopts the idea of piecewise linear regression to cluster the potential relationships between head and tail entities, and establishes a vector representation for each cluster separately, so that the same relationship represented by different clusters still has a certain degree of similarity. Results: The CTransR model carried out knowledge reasoning experiments in the open dataset, and achieved good performance. Conclusion: The CTransR model is highly effective and progressive for complex relationships. In this experiment, we have evaluated the model, including link prediction, triad classification, and text relationship extraction. The results show that the CTransR model has achieved significant improvement.

A study to assess the awareness on e –learning among the selected group of students from JIET College of Nursing at Jodhpur

The aim of this study is to assess the awareness on e –learning among the selected group of students from JIET College of Nursing at Jodhpur. The objectives of the study were to assess the level of knowledge on e-learning among the nursing students, to find out the level of attitude on e-learning among the nursing students. The study was undertaken with 40 samples. Stratified random sampling technique was used. Quantitative research design was used. Structured knowledge questionnaire was used for collecting the data. Descriptive stasis was used to analyze the data. The study findings show that 12.5% students have inadequate knowledge, 85% students have moderately adequate knowledge and 2.5% have adequate knowledge. Attitude as: 0% students have unfavorable attitude, 25% students have moderately favorable attitude and 75% have favorable attitude. It was concluded that entire samples knowledge should be upgraded. The flexible and global nature of E-learning has increased its favor and is more pursue as studying technique. The technique of E-learning and classroom should be use in parallel manner, for better result and achieving great studying technique.

Effect of Structured Teaching and Demonstration on Knowledge regarding Basic Life Support among Higher Secondary Students

The present study was aimed to assess the effect of structured teaching and demonstration on knowledge regarding Basic Life Support among higher secondary students in selected school of Kottayam. The objectives of the study were to assess the knowledge of higher Secondary students regarding Basic Life Support, determine the effect of structured teaching and demonstration programme on knowledge of higher secondary students regarding Basic Life Support and find the association between pretest knowledge of higher secondary students regarding Basic Life Support with selected socio-personnel variables. The study was conducted among 30 higher secondary students of M T Seminary Higher Secondary School, Kottayam. One group pre test and post test research design was used and subjects were selected by purposive sampling. The Socio-personal variables were used to assess the sample characteristics and structured knowledge questionnaire to assess the level of knowledge regarding Basic life Support. After the pre-test on the same day a structure teaching and demonstration was delivered and the post test was conducted on the seventh day using the same tools. The data was analyzed using descriptive and inferential statistics. The study revealed that the average pretest and post-test knowledge score was 11.4 and 20.9 respectively. The teaching programme was found to be effective in improving the knowledge (t = 13.69p&lt; 0.05) regarding Basic Life Support. There was no significant association between pre-test knowledge of higher secondary students regarding Basic Life Support and socio personal variables. Hence the study concluded that the knowledge regarding Basic Life Support among higher Secondary students could be improved by structured teaching and demonstration.

KNOWLEDGE REGARDING UPPER RESPIRATORY TRACT INFECTION (URI) AND ITS PREVENTION AMONG UNDER FIVE CHILDREN, IN SELECTED COMMUNITY AREA, DEHRADUN

Aim: A descriptive cross-sectional study was conducted with aim to assess the knowledge regarding upper respiratory tract infection (URI) and its prevention among mothers of under five children, in selected community area, Dehradun and to find out association between knowledge score of mothers regarding upper respiratory tract infection &amp; its prevention and selected socio-demographic profile. Materials and Methods:After obtaining the ethical permission from the ethical committee a quantitative research approach with descriptive cross-sectional study was conducted to assess the knowledge regarding upper respiratory tract infection and its prevention among mothers of under five children in selected community area of Dehradun. Total 60 mothersof under five children were selected based on inclusion criteria by using purposive sampling technique through structured knowledge questionnaire tool. The exclusion criteria for mothers of under five children were who are sick during data collection, having any chronic illness, children above five years and for children were who are physically disabled and mentally retarded children, children had URI with other disease condition. Results: In the present study revealed thatmore than (65%) mothers were between the age group of 26-33, nearly (40%) mothers were graduated andthe mother who are employed were (67%), (60%) mothers having girl child,(55%) mothers having child between 3-5 years and(75%) children were immunized up to their age. The result findings conclude that 18% (10) of mother had excellent knowledge regarding prevention of URI approximately half of 45% (27) of study participants had good knowledge 28% (17) of mothers had average knowledge and only 10% (6) of study participants had poor knowledge regarding prevention of URIThe result finding reveals that there is association between socio- demographic variables and knowledge score of mothers. Conclusion:The present study concludethathalfof the 45% (27) mothers had good knowledge regarding URI and itsprevention, 18% (10) mothers having excellent knowledge and 10% (6) mothers having poor knowledge. Thus, it is concluded that some of the mothers need training and teaching to improve knowledge regarding Upper respiratory tract infection and its prevention among mothers of under five children and decrease the childhood acute respiratory infection.

A study to assess the knowledge, attitude and practice regarding handwashing during covid-19 pandemic among ASHA workers working under RHTC Najafgarh, Delhi, NCR

Background: The World Health Organization (WHO) has declared the coronavirus disease 2019 (COVID-19) a pandemic. Hand hygiene is a highly cost-effective investment, providing outsized health benefits for relatively little cost; truly a ‘no-regrets’ investment. In this study researcher want to assess the knowledge, practice and attitude of ASHA workers regarding hand washing during COVID-19 pandemic. Methods: In this study interpretation of data collected from 100 ASHA workers through a structured knowledge questionnaire to assess the knowledge and Likert scale to assess the attitude and practice regarding hand washing during Covid-19 pandemic among ASHA workers. The non- probability, convenient sampling technique was used to select samples. Results: The results showed that (66%) of ASHA workers had average knowledge, the remaining (31%) had good knowledge, (3%) had poor knowledge. Conclusions: The study reveals the level of knowledge, attitude and practice of ASHA worker regarding hand washing during covid 19 pandemic was average. It suggests a need for improvement of hand hygiene practices and knowledge among health professional working under covid 19 pandemic.

A-Quasi Experimental Study to Assess the Effectiveness of Video Assisted Teaching Programme on Knowledge regarding MTP among the Reproductive age group women (18-45years) in a selected area of District Chamba Himachal Pradesh

Background: -MTP is also called the medical termination of pregnancy. MTP is the safe legal procedure for abortion performed by the qualified registered medical practitioner in a approved hospital. The aim of the study was to improve the knowledge of the reproductive age group women (18-45years) regarding the Medical Termination of pregnancy (MTP). A Quantitative research was used to assess the effectiveness of video assisted teaching programme related to knowledge regarding the Medical Termination of pregnancy (MTP) among reproductive age group women (18-45years). The non- probability purposive sampling technique was used to select 60 women of reproductive age group (18-45years) in selected area of district Chamba, Himachal Pradesh. A semi structured knowledge questionnaire was used to assess the level of knowledge. Analysis of collected data was done according to the objectives of the study and data analyzed by using descriptive and inferential statistics. The study showed that out of60 women. 11.6% was 18-24years, 18.33% was 25-31years, 40% was 32-38years, 30% was 39-45years. According to the findings, the pre-test level of knowledge score of reproductive age group (18-45years) women 0% women had good knowledge, 31.6% women had average knowledge, 61.3% women had poor knowledge and the post-test level of knowledge score of reproductive age group (18-45years) women 83.3% women had good knowledge, 16.6% women had average knowledge and 0% women had poor knowledge score. It was concluded that video assisted teaching programme was an effective strategy in improving knowledge of reproductive age group women (18-45years) regarding the MTP (Medical termination of Pregnancy)

ChatGPT를 활용한 대학 교양교육에서의 자기소개서 쓰기 사례 연구

In this paper, a case analysis of writing self-introductions using ChatGPT was conducted to examine the new writing experience and its effects. Learners conducted self-inquiry through the following question strategies: ① Understanding and gathering information about the job ② Exploring personal tendencies and experiential factors ③ Checking alignment and expression ④ Identifying problem situations and seeking advice and evaluation for resolution. In terms of learning responses, learners evaluated ChatGPT's functionality positively, citing that it: ① Offers not only directed solutions but also extended knowledge and information; ② Assists in reflecting individual unique traits and capabilities; ③ Effectively aids in exploring one's social identity. Based on this, the researchers concluded that the utilization of interactive artificial intelligence is meaningful in expanding self-directed learning experiences through collaboration to solve problems, rather than passively assimilating conventional structured knowledge or information. Collaborating with conversational artificial intelligence can facilitate a novel self-understanding and introduce a new writing experience that demands critical and analytical thinking towards the generated texts.

Selection methodology for additive manufacturing processes considering design, material, and manufacturability

PurposeOne of the critical reasons for the nonacceptance of additive manufacturing (AM) processes is the lack of understanding and structured knowledge of design for additive manufacturing (DfAM). This paper aims to assist designers to select the appropriate AM technology for product development or redesign. Using the suggestion provided by the design assist tool, the user’s design alterations depend on their ability to interpret the suggestion into the design without affecting the design’s primary objective.Design/methodology/approachThis research reports the development of a tool that evaluates the efficacy values for all seven major standard AM processes by considering design parameters, benchmark standards within the processes and their material efficacies. In this research, the tool provides analytical and visual approaches to suggestion and assistance. Seventeen design parameters and seven benchmarking standards are used to evaluate the proposed product and design quality value. The full factorial design approach has been used to evaluate the DfAM aspects, design quality and design complexity.FindingsThe outcome is evaluated by the product and design quality value, material suit and material-product-design (MPD) value proposed in this work for a comparative assessment of the AM processes for a design. The higher the MPD value, the better the process. The visual aspect of the evaluation uses spider diagrams, which are evaluated analytically to confirm the results’ appropriateness with the proposed methodology.Originality/valueThe data used in the database is assumed to make the study comprehensive. The output aims to help opt for the best process out of the seven AM techniques for better and optimized manufacturing. This, as per the authors’ knowledge, is not available yet.

Cybersecurity threat perception technology based on knowledge graph

&lt;p class="Abstract"&gt;The issue of complex sources, difficult to understand and share security threat intelligence, this paper realizes deep learning of threat intelligence features based on Restricted Boltzmann Machine, which graphs the original threat intelligence features from high dimensional space to low dimensional space layer by layer, and constructs the cyberspace security threat knowledge graphs. The deep learning used to build a multi-level and structured knowledge graph of cyberspace security threats can reflect the structural characteristics of the knowledge graph, making the graph have a lower dimension and a higher level of abstraction. The experiment verifies the feasibility of constructing the cyberspace security threat knowledge graph, and verifies the security threat perception method based on the knowledge graph is more suitable for the perception of high-intensity security threats by comparing with traditional threat detection methods.&lt;strong&gt;&lt;/strong&gt;&lt;/p&gt;

Deep purified feature mining model for joint named entity recognition and relation extraction

Table filling based joint named entity recognition and relation extraction task aims to share representation of subtasks in a table to extract structured knowledge. However, most of existing studies need additional labels and dedicated deep neural networks to learn shared representation, imposing heavy burdens to decoders. More seriously, almost all these models suffer from feature confusion problem, failing to capture purified task-specific features from shared representation to perform subtasks. To address these challenging problems, in this paper we propose a novel and effective Deep puRified fEAture Mining (DREAM) model for joint named entity recognition and relation extraction task, which can automatically capture purified task-specific features to improve the classification performance of subtasks. Specifically, unlike introducing additional labels or dedicated network architectures, we design a new lightweight shared representation learning (LSRL) module by the plainest labels of joint task and thus encodes context by the hybrid convolutional neural networks. Afterwards, a task-aware information bottleneck (TIB) module is proposed to explore the relation between the mutual information of the joint distribution of each subtask and its task-specific features. With the above two modules well obtain shared representation and purified task-specific features, the satisfactory classification results of both subtasks can be guaranteed. Experiment results show that the proposed model is highly effective, obtaining the promising results on three different benchmarks: CoNNL04 (general text), ADE (biomedical text) and SciERC (scientific text). For example, DREAM respectively achieves F1-scores of 78.18%, 80.28% and 44.60% in performing the relation extraction subtask on the CoNNL04, ADE and SciERC datasets. The promising performance indicates that the proposed model can be applied to many practical applications such as biomedical information extraction. The source code is publicly available at https://github.com/SWT-AITeam/DREAM.

Masked image modeling-based boundary reconstruction for 3D medical image segmentation

Accurate segmentation of 3D medical images is vital for computer-aided diagnosis. However, the complexity of target morphological variations and a scarcity of labeled data make segmentation more challenging. Furthermore, existing models make it difficult to fully and efficiently integrate global and local information, which hinders structured knowledge acquisition. To overcome these challenges, we introduce the TNT Masking Network (TNT-MNet), a groundbreaking transformer-based 3D model that utilizes a transformer-in-transformer (TNT) encoder. For the first time, we present masked image modeling (MIM) in supervised learning, utilizing target boundary regions as masked prediction targets to enhance structured knowledge acquisition. We execute multiscale random masking on inner and outer tokens in online branch to tackle the challenge of segmenting organs and lesion regions with varying structures at multiple scales and to enhance modeling capabilities. In contrast, the target branch utilizes all tokens to guide the online branch to reconstruct the masked tokens. Our experiments suggest that TNT-MNet’s performance is comparable, or even better, than state-of-the-art models in three medical image datasets (BTCV, LiTS2017, and BraTS2020) and effectively reduces the dependence on labeled data. The code and models are publicly available at https://github.com/changliu-work/TNT_MNet.

Open-world story generation with structured knowledge enhancement: A comprehensive survey

Storytelling and narrative are fundamental to human experience, intertwined with our social and cultural engagement. As such, researchers have long attempted to create systems that can generate stories automatically. In recent years, powered by deep learning and massive data resources, automatic story generation has shown significant advances. However, considerable challenges, like the need for global coherence in generated stories, still hamper generative models from reaching the same storytelling ability as human narrators. To tackle these challenges, many studies seek to inject structured knowledge into the generation process, which is referred to as structured knowledge-enhanced story generation. Incorporating external knowledge can enhance the logical coherence among story events, achieve better knowledge grounding, and alleviate over-generalization and repetition problems in stories. This survey provides the latest and comprehensive review of this research field: (i) we present a systematic taxonomy regarding how existing methods integrate structured knowledge into story generation; (ii) we summarize involved story corpora, structured knowledge datasets, and evaluation metrics; (iii) we give multidimensional insights into the challenges of knowledge-enhanced story generation and cast light on promising directions for future study.