Entity Relationship Research Articles

Construction and application of knowledge graph for grid dispatch fault handling based on pre-trained model

With the construction of new power systems, the power grid has become extremely large, with an increasing proportion of new energy and AC/DC hybrid connections. The dynamic characteristics and fault patterns of the power grid are complex; additionally, power grid control is difficult, operation risks are high, and the task of fault handling is arduous. Traditional power-grid fault handling relies primarily on human experience. The difference in and lack of knowledge reserve of control personnel restrict the accuracy and timeliness of fault handling. Therefore, this mode of operation is no longer suitable for the requirements of new systems. Based on the multi-source heterogeneous data of power grid dispatch, this paper proposes a joint entity–relationship extraction method for power-grid dispatch fault processing based on a pre-trained model, constructs a knowledge graph of power-grid dispatch fault processing and designs, and develops a fault-processing auxiliary decision-making system based on the knowledge graph. It was applied to study a provincial dispatch control center, and it effectively improved the accident processing ability and intelligent level of accident management and control of the power grid.

Are NoSQL Databases Affected by Schema?

During data modelling, NoSQL databases are usually considered schema-less databases. They do not support rigid schema as traditional databases. Instead, offer flexibility and support dynamic schema, which means schema design can be changed at run time to support analytical tasks. NoSQL databases allow storing similar information with multiple schemas, which facilitates data evolution by eliminating restrictions on the schema. It raises the question of whether the schema matters in NoSQL databases, given that explicit schema declaration is not required before data storage. Furthermore, if the schema does matter, what is its potential impact on application performance? This paper examines these questions by taking three types of NoSQL databases: Document store, Column store, and Key-Value store. All possible schema structure alternatives are designed using a sample Entity Relationship (ER) model. Then, a set of common queries are performed on various schema alternatives to analyse the impact of query performance in terms of query response time, speedup factor, read and write Latency, and database size. The results suggest that the scheme alternatives affect the database performance in different NoSQL models.

Research on Personalized Video Matching Algorithm Based on Implicit Feature Transfer and PTransE

With the rapid development of internet plus education, it is increasingly important to quickly and accurately match personalized videos for learners from massive learning videos. However, the existing resource recommendation methods have two problems. On the one hand, they do not make full use of the implicit interaction data of learners in the learning process, i.e., they rarely reflect the comprehensive consideration of learners' interest preferences and cognitive level when describing learners. On the other hand, they are mostly based on collaborative filtering algorithms, using the similarity between learners or videos to recommend, ignoring the impact of semantic relations between videos on the recommendation results. In view of this, we proposed a personalized learning video matching method (IFT‐PTransE) based on heterogeneous feature data transfer and knowledge reasoning from two aspects of learning behavior data mining and knowledge graph representation learning. In this method, firstly, a learner model is constructed. By analyzing and quantifying various implicit interaction behavior data of learners, the sparse video scoring matrix is filled as auxiliary data to complete the transfer of target scoring data. Secondly, the semantic close relationship between videos is introduced. PTransE algorithm is used to mine the multi‐path relationship between entities. All entity relationships are embedded into the low dimensional vector space, so that the semantic similarity between videos can be calculated using the distance between vectors. Finally, video score similarity and semantic similarity between frequencies are fused. video sorting is performed based on the improved collaborative filtering algorithm and then recommend the top N videos to the students. Through simulation and analysis, the effectiveness of this method in personalized video matching is proved. This method makes up for the shortcomings of collaborative filtering algorithm in using implicit information, enhances the recommendation effect at the semantic level, and solves the data sparse and cold start problems to a certain extent. © 2023 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

Blockchain-enabled cyber-physical system for construction site management: A pilot implementation

Prefabricated construction has become one of the most innovative methods to address the pressing housing demands. However, conventional prefabricated construction projects often suffer from challenges of managing numerous paper-based documentation, non-standardized management and intricate stakeholders in construction site management (CSM). The current design approaches lack sufficient consideration of the activity-based user relationships. To facilitate the system framework design and implementation for CSM, this study proposes a generic Cyber-physical Centered (CCD) Design, illustrating an effective and systematic approach to identify user-activity relationships in a cross-collaborative context. The consideration of entity, value chain and user-activity relationships facilitate identity management and value chain management services. The proposed approach was then utilized to a pilot project to design and implement the Blockchain-enabled Cyber-physical Site Management System (BCSMS) integrated with Digital Work Supervision System (DWSS), incorporating considerations on multi-source information flow and user-centric applications design. The implemented BCSMS decentralized two types of fundamental documents in CSM - Request for Inspection and Survey Checking (RISC) form and site diary. It addresses information fragmentation and asymmetry in a cross-collaborative environment caused by manual-input and error-prone records. The proposed system was evaluated by two important system performance indicators in terms of average response time and transaction per second. The system performance test shows that the accountability of BCSMS is significant compared to DWSS, given the p-value 0.01. Blockchain effectively improves DWSS with enhanced data submission, identity management and data-driven site performance evaluation functions. This study also qualitatively analyzed the pros and cons of proposed blockchain-enabled cyber-physical system (CPS) from society-economy-technology aspects for technical practitioners, construction stakeholders and governments.

Knowledge-Graph- and GCN-Based Domain Chinese Long Text Classification Method

In order to solve the current problems in domain long text classification tasks, namely, the long length of a document, which makes it difficult for the model to capture key information, and the lack of expert domain knowledge, which leads to insufficient classification accuracy, a domain long text classification model based on a knowledge graph and a graph convolutional neural network is proposed. BERT is used to encode the text, and each word’s corresponding vector is used as a node for the graph convolutional neural network so that the initialized vector contains rich semantic information. Using the trained entity–relationship extraction model, the entity-to-entity–relationships in the document are extracted and used as the edges of the graph convolutional neural network, together with syntactic dependency information. The graph structure mask is used to learn about edge relationships and edge types to further enhance the learning ability of the model for semantic dependencies between words. The method further improves the accuracy of domain long text classification by fusing knowledge features and data features. Experiments on three long text classification datasets—IFLYTEK, THUCNews, and the Chinese corpus of Fudan University—show accuracy improvements of 8.8%, 3.6%, and 2.6%, respectively, relative to the BERT model.

An Entity based Approach for Extracting Relationship between Chinese Characters

Knowledge extraction includes the extraction of entity relationships, which is crucial. Deep learning algorithms are increasingly prevalent in relation extraction tasks when compared to conventional pattern recognition techniques. The majority of current research on remotely supervised methods and kernel functions in relationship extraction strategies for Chinese language cannot disregard the detrimental effects of noisy data in the dataset on the experimental findings. A bidirectional GRU neural network, a two-layer attention mechanism, and a Chinese relationship extraction model are proposed. For the forgetfulness problem, a bidirectional GRU neural network is utilised to fuse the input vectors. Integrating the structural properties of the Mandarin language, word vectors are employed as the input. Sentence-level attention mechanisms are utilised to extract sentence features, and word-level feature information is retrieved from a sentence. About 1300 bits of data are extracted from news websites using a remotely supervised methodology for validation. According to the experimental findings, the neural network model with a two-layer attention mechanism is able to fully utilise all of the feature information in a sentence, and it performs significantly better than the neural network model without an attention mechanism in terms of accuracy and recall rates. Compared to the model without the attention mechanism, the accuracy and recall rates are noticeably greater.

RDBridge: a knowledge graph of rare diseases based on large-scale text mining.

Despite low prevalence, rare diseases affect 300 million people worldwide. Research on pathogenesis and drug development lags due to limited commercial potential, insufficient epidemiological data, and a dearth of publications. The unique characteristics of rare diseases, including limited annotated data, intricate processes for extracting pertinent entity relationships, and difficulties in standardizing data, represent challenges for text mining. We developed a rare disease data acquisition framework using text mining and knowledge graphs and constructed the most comprehensive rare disease knowledge graph to date, Rare Disease Bridge (RDBridge). RDBridge offers search functions for genes, potential drugs, pathways, literature, and medical imaging data that will support mechanistic research, drug development, diagnosis, and treatment for rare diseases. RDBridge is freely available at http://rdb.lifesynther.com/. Supplementary data are available at Bioinformatics online.

Perancangan Sistem Informasi Pengelolaan Praktikum Berbasis Website

Practicum is one of the supporting activities in the learning process as well as routine and mandatory activities that students must follow. Practicum management at the Untirta Industrial Engineering Laboratory is still carried out conventionally, so it is inflexible, inefficient, and the information provided is not detailed and transparent. The design of information systems in practicum management is carried out to overcome these problems. This study aims to obtain a practicum management information system design at the Untirta Industrial Engineering Laboratory. The method used in this study is the Framework for the Applications of System Thinking (FAST) method. The results of this study indicate that the practicum management information system design at the Untirta Industrial Engineering Laboratory is in the form of a context diagram that describes the process and scope of the system. Data flow diagrams provide an overview of data flow in processes within the system and entity relationship diagrams describe the relationships that exist in entities. Blackbox testing has been carried out on 17 page groups and shows valid results and functions properly. The usability test resulted in a system usability scale value of 86.75 which indicates that the designed information system is acceptable with grade B and an excellent rating.

Prototyping an Online Patient Registration Based on a Smartphone App at the Malang Primary Health Care

Currently, the patient registration system at the Primary Health Care (PHC) in Malang City still uses a manual registration system with various existing problems, like the emergence of queues and patients jostling in the waiting room, so it takes longer for health services. This study aimed to design a prototype application for online patient registration at the Malang City Health Center. The method used is Research and Development Prototyping. The manufacturing stages start from (1) the identification of basic needs, (2) developing a working prototype, (3) using a prototype (trial), and (4) revising and improving the prototype. The instrument used in this study was an interview guide conducted with two Heads of PHC (Dinoyo and Rampal Celaket) and nine Registration Officers at two Health Centers to determine the need for designing a prototype online registration application. Observations were made regarding the existing IT systems (Hardware and Software) in both PHC, the facilities and infrastructure that support IT systems (rooms, internet networks, etc.) and the documents supporting the processes. The results of this prototype design were in the form of a list of functional and non-functional requirements, business process flow diagrams, data flow diagrams, Entity Relationship Diagrams, and Interface Design, including programming language and user interface. Based on the results of the online patient registration prototype design, it enters the initial stage of using a system design that is by user needs but has yet to reach the implementation stage. However, this prototype can be used as a reference in developing an integrated online registration system with existing information systems at the PHC.
 Keywords: Prototype, Online Registration, Smartphone, Primary Health Care, Patient

Research on Chinese Semantic Named Entity Recognition in Marine Engine Room Systems Based on BERT

With the development of intelligentization in maritime vessels, the pursuit of an organized and scalable knowledge storage approach for marine engine room systems has become one of the current research hotspots. This study addressed the foundational named entity recognition (NER) task in constructing a knowledge graph for marine engine rooms. It proposed an entity recognition algorithm for Chinese semantics in marine engine rooms that integrates language models. Firstly, the bidirectional encoder representation from transformers (BERT) language model is used to extract text features and obtain word-level granularity vector matrices. Secondly, the trained word embeddings are fed into a bidirectional long short-term memory network (BiLSTM) to extract contextual information. It considers the surrounding words and their sequential relationships, enabling a better understanding of the context. Additionally, the conditional random field (CRF) model was used to extract the globally optimal sequence of named entities in the marine engine room semantic. The CRF model considered the dependencies between adjacent entities that ensured a coherent and consistent final result for entity recognition in marine engine room semantics. The experiment results demonstrate that the proposed algorithm achieves superior F1 scores for all three entity types. Compared with BERT, the overall precision, recall, and F1 score of the entity recognition are improved by 1.36%, 1.41%, and 1.38%, respectively. Future research will be carried out on named entity recognition of a small sample set to provide basic support for more efficient entity relationship extraction and construction of a marine engine room knowledge graph.

Sistem Pendukung Metode Pembelajaran Self Paced Learning bagi Mahasiswa di dalam Kelas berbasis Web

Currently Moodle is being used in the classroom learning process for web development courses at Universitas Ciputra by applying the self-paced learning method, but it is not optimal. Moodle features do not limit access to learning materials, so that the learning process in class is not based on actual student understanding and does not follow each student's learning pace. The purpose of this study is to determine the effectiveness of implementing self-paced learning methods in the classroom through the design of a web-based support system. This study uses a quantitative method with the SDLC model consisting of data collection, design, implementation, and system testing with Black Box. The data collection technique uses a questionnaire created with Google Form. At the design stage, the design is carried out on use case diagrams, entity relationship diagrams, and interfaces. The findings from this study are a web-based system to support students in applying self-paced learning methods in class. The test results show that all system functionality works well. This system makes the learning process in the classroom with self-paced learning more effective and helps students understand learning material well and is very effective in facilitating access to communication between students and teachers.

Stratification of Tamoxifen Synergistic Combinations for the Treatment of ER+ Breast Cancer.

Breast cancer alone accounts for the majority of cancer deaths among women, with the most commonly diagnosed subtype being estrogen receptor positive (ER+). Survival has greatly improved for patients with ER+ breast cancer, due in part to the development of antiestrogen compounds, such as tamoxifen. While treatment of the primary disease is often successful, as many as 30% of patients will experience recurrence and metastasis, mainly due to developed endocrine therapy resistance. In this study, we discovered two tamoxifen combination therapies, with simeprevir and VX-680, that reduce the tumor burden in animal models of ER+ breast cancer more than either compound or tamoxifen alone. Additionally, these tamoxifen combinations reduced the expression of HER2, a hallmark of tamoxifen treatment, which can facilitate acquisition of a treatment-resistant phenotype. These combinations could provide clinical benefit by potentiating tamoxifen treatment in ER+ breast cancer.

“Standard Text” Relational Classification Model Based on Concatenated Word Vector Attention and Feature Concatenation

The task of relation classification is an important pre-task in natural language processing tasks. Relation classification can provide a high-quality corpus for tasks such as machine translation, human–computer dialogue, and structured text generation. In the process of the digitalization of standards, identifying the entity relationship in the standard text is an important prerequisite for the formation of subsequent standard knowledge. Only by accurately labeling the relationship between entities can there be higher efficiency and accuracy in the subsequent formation of knowledge bases and knowledge maps. This study proposes a standard text relational classification model based on cascaded word vector attention and feature splicing. The model was compared and ablated on our labeled standard text Chinese dataset. At the same time, in order to prove the performance of the model, the above experiments were carried out on two general English datasets, SemEval-2010 Task 8 and KBP37. On standard text datasets and general datasets, the model proposed in this study achieved excellent results.

Estrogen receptor blockade and radiation therapy cooperate to enhance the response of immunologically cold ER+ breast cancer to immunotherapy

BackgroundMost patients with estrogen receptor positive (ER+) breast cancer do not respond to immune checkpoint inhibition (ICI); the tumor microenvironment (TME) of these cancers is generally immunosuppressive and contains few tumor-infiltrating lymphocytes. Radiation therapy (RT) can increase tumor inflammation and infiltration by lymphocytes but does not improve responses to ICIs in these patients. This may result, in part, from additional effects of RT that suppress anti-tumor immunity, including increased tumor infiltration by myeloid-derived suppressor cells and regulatory T cells. We hypothesized that anti-estrogens, which are a standard of care for ER+ breast cancer, may ameliorate these detrimental effects of RT by reducing the recruitment/ activation of suppressive immune populations in the radiated TME, increasing anti-tumor immunity and responsiveness to ICIs.MethodsTo interrogate the effect of the selective estrogen receptor downregulator, fulvestrant, on the irradiated TME in the absence of confounding growth inhibition by fulvestrant on tumor cells, we used the TC11 murine model of anti-estrogen resistant ER+ breast cancer. Tumors were orthotopically transplanted into immunocompetent syngeneic mice. Once tumors were established, we initiated treatment with fulvestrant or vehicle, followed by external beam RT one week later. We examined the number and activity of tumor infiltrating immune cells using flow cytometry, microscopy, transcript levels, and cytokine profiles. We tested whether fulvestrant improved tumor response and animal survival when added to the combination of RT and ICI.ResultsDespite resistance of TC11 tumors to anti-estrogen therapy alone, fulvestrant slowed tumor regrowth following RT, and significantly altered multiple immune populations in the irradiated TME. Fulvestrant reduced the influx of Ly6C+Ly6G+ cells, increased markers of pro-inflammatory myeloid cells and activated T cells, and augmented the ratio of CD8+: FOXP3+ T cells. In contrast to the minimal effects of ICIs when co-treated with either fulvestrant or RT alone, combinatorial treatment with fulvestrant, RT and ICIs significantly reduced tumor growth and prolonged survival.ConclusionsA combination of RT and fulvestrant can overcome the immunosuppressive TME in a preclinical model of ER+ breast cancer, enhancing the anti-tumor response and increasing the response to ICIs, even when growth of tumor cells is no longer estrogen sensitive.

Penjadwalan Mata Pelajaran Menggunakan Algoritma Particle Swarm Optimization (PSO) Pada SMPIT Mufidatul Ilmi

Scheduling has a division of time based on a work sequence arrangement plan in the form of a list or table of activities or an activity plan with a detailed division of implementation time which is very necessary in carrying out institutional/company business processes. It is important to note the complexity of the process in scheduling appropriate subjects from various perspectives, both teachers, students and classrooms. Provision of teacher teaching schedules based on abilities in the field of subjects, suitable time each semester is very important to consider for very complex schedule arrangements, the number of classrooms that can be used in teaching activities is relatively small, and preventing teacher teaching conflicts so that the need for optimization of eye scheduling lesson to be made. Furthermore, at the stage of application development using the Waterfall method. The purpose of this research is to build a lesson scheduling application at SMPIT Mufidatul Ilmi by applying the particle swarm optimization (PSO) algorithm to compile lesson schedules. Particle Swarm Optimization is a population-based algorithm that exploits individuals in search. In PSO the population is called a swarm and individuals are called particles. Each particle moves at a speed adapted from the search area and stores it as the best position ever achieved. Design analysis includes Use Case Diagrams, Activity Diagrams, Class Diagrams, Sequence Diagrams, Entity Relationship Diagrams (ERD). The results of this study provide several primary data (service) features, especially features to provide scheduling results from processing with the PSO algorithm

Neural-logic multi-agent system for flood event detection

This paper shows the capabilities offered by an integrated neural-logic multi-agent system (MAS). Our case study encompasses logical agents and a deep learning (DL) component, to devise a system specialised in monitoring flood events for civil protection purposes. More precisely, we describe a prototypical framework consisting of a set of intelligent agents, which perform various tasks and communicate with each other to efficiently generate alerts during flood crisis events. Alerts are only delivered when at least two separates sources agree on an event on the same zone, i.e. aerial images and severe weather reports. Images are segmented by a neural network trained over eight classes of topographical entities. The resulting mask is analysed by a Logic Image Descriptor (LID) which then submit the perception to a logical agent.

Focusing on potential named entities during active label acquisition

AbstractNamed entity recognition (NER) aims to identify mentions of named entities in an unstructured text and classify them into predefined named entity classes. While deep learning-based pre-trained language models help to achieve good predictive performances in NER, many domain-specific NER applications still call for a substantial amount of labeled data. Active learning (AL), a general framework for the label acquisition problem, has been used for NER tasks to minimize the annotation cost without sacrificing model performance. However, the heavily imbalanced class distribution of tokens introduces challenges in designing effective AL querying methods for NER. We propose several AL sentence query evaluation functions that pay more attention to potential positive tokens and evaluate these proposed functions with both sentence-based and token-based cost evaluation strategies. We also propose a better data-driven normalization approach to penalize sentences that are too long or too short. Our experiments on three datasets from different domains reveal that the proposed approach reduces the number of annotated tokens while achieving better or comparable prediction performance with conventional methods.

Entity Relationship Extraction Based on a Multi-Neural Network Cooperation Model

Entity relation extraction mainly extracts relations from text, which is one of the important tasks of natural language processing. At present, some special fields have insufficient data; for example, agriculture, the metallurgical industry, etc. There is a lack of an effective model for entity relationship recognition under the condition of insufficient data. Inspired by this, we constructed a suitable small balanced data set and proposed a multi-neural network collaborative model (RBF, Roberta–Bidirectional Gated Recurrent Unit–Fully Connected). In addition, we also optimized the proposed model. This model uses the Roberta model as the coding layer, which is used to extract the word-level features of the text. This model uses BiGRU (Bidirectional Gated Recurrent Unit)–FC (Fully Connected) as the decoding layer, which is used to obtain the optimal relationship of the text. To further improve the effect, the input layer is optimized by feature fusion, and the learning rate is optimized by the cosine annealing algorithm. The experimental results show that, using the small balanced data set, the F1 value of the RBF model proposed in the paper is 25.9% higher than the traditional Word2vec–BiGRU–FC model. It is 18.6% higher than the recent Bert–BiLSTM (Bidirectional Long Short Term Memory)–FC model. The experimental results show that our model is effective.

Synthesis, Docking Studies, and Biological Evaluation of Betti Bases as Promising Anti-tubercular Agents

Background: The occurrence of Tuberculosis (TB) has significantly increased worldwide. The extensively drug-resistant tuberculosis (XDR-TB) and multi-drug resistant tuberculosis (MDR-TB) have made it more challenging to treat this mycobacterial infection caused by the Mycobacterium tuberculosis MTB-H37Rv strain. The present treatments for tuberculosis are of long duration and with side effects. Thus, it is necessary to discover new drugs with short-term chemotherapy, fewer health hazards, and cost effectiveness. Objective: The objective of the study was to divulge the antitubercular properties of Betti base scaffolds. Method: Betti bases were designed, synthesized 4a-4h, 6a-6h, and investigated for their in vitro antitubercular activity using Microplate Alamar Blue assay (MABA) against the MTB-H37Rv strain. Their binding affinity with amino acids was studied by performing molecular docking studies using InhA (PDB ID: 2NSD) present in the MTB-H37Rv strain. Cytotoxicity assay and neutrophil function test (NFT) were also performed. Results: The Betti bases (4a-4h, 6d) showed minimum inhibitory concentration (MIC) values ranging from 1.6 μg/mL to 6.25 μg/mL against the MTB-H37Rv strain. The compounds (4a-4h, 6a-6h) were investigated for their ADME properties and good pharmacokinetic profiles were observed. In molecular docking studies, a strong binding affinity between InhA and the compounds (4a-4h, 6a-6h) was observed, which provided theoretical insight into the inhibitory action of the synthesized compounds (4a-4h, 6a-6h) against InhA. NFT of the compounds (4a-4h, 6a-6h) showed no harmful effects on the functions of neutrophils. In vitro cytotoxicity assay against Vero cell lines revealed the non-cytotoxic behavior of the compounds. Conclusion: Betti bases can be considered to be a promising class of molecular entities that can lead to the development of new anti-tubercular leads.

Implementasi Extreme Programming Pada Perancangan Sistem Informasi Penjualan Buku Menggunakan Java

Technology is needed by humans to facilitate all activities carried out so that they are fast and practical, besides that technology is used as a solution to problems in conventional systems. Conventional sales activities experience several problems such as recording activities, insecure archiving, manual calculations and loss of transaction data. From these problems, the purpose of this study is to design a sales information system, namely object-based book sales transactions in order to minimize errors and produce the information needed by users effectively and efficiently. The method used is Extreme Programming which is very suitable for developing and building object-oriented applications. This method has stages in the method including planning carried out problem finding and needs analysis, the design consists of system design with UML (Unified Modeling Language) and ERD (Entity Relationship Diagram) database design, coding in the form of application menu displays, testing with blackbox testing and software increase. The design of an OOP-based book sales information system using the Extreme Programming method is expected to help and facilitate users in managing data, sales transactions and reports.