Knowledge-based Model Research Articles

Abstract 341: Predicting clinical endocrine response in advanced breast cancers using a reproducible low-dimensional biomarker

Abstract In the absence of reliable and effective prognostic biomarkers, endocrine therapy remains the standard of care for all advanced and metastatic estrogen receptor-positive (ER+) breast cancers. Attempts to develop biomarkers using the baseline tumor transcriptome or genome of advanced ER+ breast cancers have so far been unsuccessful due to predictive models with poor reproducibility in independent studies. Here we present an approach to develop a low-dimensional biomarker that estimates the risk of adverse events on endocrine therapy using the baseline tumor transcriptome of patients. Using a framework for supervised dimensionality reduction of the gene expression feature space, we constructed an endocrine response signature (ENDORSE) modeled on the survival outcomes of ER+ breast cancers from METABRIC. ENDORSE outperformed transcriptome-wide and knowledge-based signature models while significantly improving upon routine histopathological and genomic classifiers in cross-validation analyses. The ENDORSE risk estimate accurately predicted the outcomes for endocrine therapy in three independent clinical trials for ER+ breast cancers. Further, analysis of the phenotypes enriched in high-risk categories show endocrine resistance was not associated with rates of proliferation, but instead with a potential loss of DNA damage repair and cell-matrix interaction pathways. Citation Format: Aritro Nath, Adam Cohen, Jeffrey Chang, Andrea Bild. Predicting clinical endocrine response in advanced breast cancers using a reproducible low-dimensional biomarker [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2021; 2021 Apr 10-15 and May 17-21. Philadelphia (PA): AACR; Cancer Res 2021;81(13_Suppl):Abstract nr 341.

GIScience research at the 2021 Esri User Conference

GIScience research at the 2021 Esri User Conference

MODEL PENGEMBANGAN SUMBER DAYA MANUSIA DI LEMBAGA PENDIDIKAN ISLAM

This article discusses the procedure for diagnosing capabilities in a knowledge-based organizational capability development model. This research uses library research. In this study, researchers used two kinds of data, namely primary data and secondary data. The method of data collection is by tracing sources of literature documentation and library materials that are relevant to the problems studied. The results of the analysis conclude that staff development is an increase in intellectual or emotional abilities needed to do a better job with the principles of growth, change, and reform. Staff development constraints include participants, trainers or infrastructure, development facilities, curriculum, and development funds. An effective staff development model begins with human resource planning, identifying the required capabilities and capacities, Succession Planning, Development Needs Assessment, Development Planning, Development Approach, and Evaluation of Development Success.

Intelligent approach to automated star-schema construction using a knowledge base

Most data-warehouse construction processes are performed manually by experts, which is laborious, time-consuming, and prone to error. Furthermore, special knowledge is required to design complex multidimensional models, such as a star schema. This predicament has motivated computer scientists to propose automation techniques to generate such models. For this reason, we present a new strategy that incorporates knowledge-based models into a framework, named the Semantic-based Star-schema Designer, that assists the automation of star schema construction. Our models provide reasoning capabilities needed by star schema designs, including those that can disambiguate heterogeneous terms, detect appropriate data types and attribute sizes, and organize data hierarchies to support online analytical processes. We also propose strategies to overcome the uncertainty arising when attribute names are not available in the data source. The names of unknown attributes are thus predicted using an arithmetic coding technique to infer column names. Our system also generates star schema from semi-structured data (e.g., comma-separated-value files and spreadsheets), which do not provide primary keys, foreign keys, or relationship cardinalities between tables. Our framework facilitates star schema construction and their relationship information without human intervention using homegrown algorithms. Experiments demonstrate that our technique predicts column names and data types that enable the effective generation of star schema better than baseline approaches.

Assessment of a conventional volumetric-modulated arc therapy knowledge-based planning model applied to the new Halcyon© O-ring linac in locoregional breast cancer radiotherapy.

The aim of this study was to evaluate the performance of a knowledge-based planning (KBP) model for breast cancer trained on plans performed on a conventional linac with 6 MV FF (flattening filter) beams and volumetric-modulated arc therapy (VMAT) for plans performed on the new jawless Halcyon© system with 6 MV FFF (flattening filter-free) beams. Based on the RapidPlan© (RP) KBP optimization engine, a DVH Estimation Model was first trained using 56 VMAT left-sided breast cancer treatment plans performed on a conventional linac, and validated on another 20 similar cases (without manual intervention). To determine the capacity of the model for Halcyon©, an additional cohort of 20 left-sided breast cancer plans was generated with RP and analyzed for both TrueBeam© and Halcyon© machines. Plan qualities between manual vs RP (followed by manual intervention) Halcyon© plans set were compared qualitatively by blinded review by radiation oncologists for 10 new independent plans. Halcyon© plans generated with the VMAT model trained with conventional linac plans showed comparable target dose distribution compared to TrueBeam© plans. Organ sparingwas comparable between the 2 devices with a slight decrease in heart dose for Halcyon© plans. Nine out of ten automatically generated Halcyon© plans were preferentially chosen by the radiation oncologists over the manually generated Halcyon© plans. A VMAT KBP model driven by plans performed on a conventional linac with 6 MV FF beams provides high quality plans performed with 6 MV FFF beams on the new Halcyon© linac.

Multitask Learning with Knowledge Base for Joint Intent Detection and Slot Filling

Intent detection and slot filling are important modules in task-oriented dialog systems. In order to make full use of the relationship between different modules and resource sharing, solving the problem of a lack of semantics, this paper proposes a multitasking learning intent-detection system, based on the knowledge-base and slot-filling joint model. The approach has been used to share information and rich external utility between intent and slot modules in a three-part process. First, this model obtains shared parameters and features between the two modules based on long short-term memory and convolutional neural networks. Second, a knowledge base is introduced into the model to improve its performance. Finally, a weighted-loss function is built to optimize the joint model. Experimental results demonstrate that our model achieves better performance compared with state-of-the-art algorithms on a benchmark Airline Travel Information System (ATIS) dataset and the Snips dataset. Our joint model achieves state-of-the-art results on the benchmark ATIS dataset with a 1.33% intent-detection accuracy improvement, a 0.94% slot filling F value improvement, and with 0.19% and 0.31% improvements respectively on the Snips dataset.

Data and knowledge driven approach for burden surface optimization in blast furnace

This paper presents a hybrid optimization strategy for determining the setting values of burden surface through measured data and domain knowledge integration manner. The proposed hybrid optimization strategy, including broad learning-based soft sensing models for production indicators, novel twin information fusion based pre-setting model, knowledge-mining based feedback compensation model, data-based production status evaluation and knowledge-based adjustment model, can adjust the setting values of burden surface in response to the changes in production status and safe operation can be reached as well. Finally, comprehensive experiments are conducted to verify the effectiveness and feasibility of the proposed method.

Modeling the Th17 and Tregs Paradigm: Implications for Cancer Immunotherapy.

CD4 + T cell differentiation is governed by gene regulatory and metabolic networks, with both networks being highly interconnected and able to adapt to external stimuli. Th17 and Tregs differentiation networks play a critical role in cancer, and their balance is affected by the tumor microenvironment (TME). Factors from the TME mediate recruitment and expansion of Th17 cells, but these cells can act with pro or anti-tumor immunity. Tregs cells are also involved in tumor development and progression by inhibiting antitumor immunity and promoting immunoevasion. Due to the complexity of the underlying molecular pathways, the modeling of biological systems has emerged as a promising solution for better understanding both CD4 + T cell differentiation and cancer cell behavior. In this review, we present a context-dependent vision of CD4 + T cell transcriptomic and metabolic network adaptability. We then discuss CD4 + T cell knowledge-based models to extract the regulatory elements of Th17 and Tregs differentiation in multiple CD4 + T cell levels. We highlight the importance of complementing these models with data from omics technologies such as transcriptomics and metabolomics, in order to better delineate existing Th17 and Tregs bifurcation mechanisms. We were able to recompilate promising regulatory components and mechanisms of Th17 and Tregs differentiation under normal conditions, which we then connected with biological evidence in the context of the TME to better understand CD4 + T cell behavior in cancer. From the integration of mechanistic models with omics data, the transcriptomic and metabolomic reprograming of Th17 and Tregs cells can be predicted in new models with potential clinical applications, with special relevance to cancer immunotherapy.

A knowledge-based model on quality management system compliance assessment for maritime higher education institutions

ABSTRACT A quality management system is an essential and mandatory instrument for maritime higher education institutions mandated by the International Convention on Standards of Training, Certification, and Watchkeeping for Seafarers. To design an effective quality management system, it is strongly recommended to take the most comprehensive model of the quality system such as ISO 9001 quality management system. This paper proposes a knowledge-based model for assessing the compliance level of the quality management system of maritime higher education institutions with respect to ISO 9001:2015 to provide meaningful information to design an effective quality management system, to identify potential gaps and required improvement points in the quality management system. In the proposed model, fuzzy axiomatic design is selected as a suitable research methodology. The obtained results provide a decision aid for the relevant executives in maritime institutions who design a quality management system integrated with ISO 9001:2015 guidelines.

Using data assimilation to train a hybrid forecast system that combines machine-learning and knowledge-based components.

We consider the problem of data-assisted forecasting of chaotic dynamical systems when the available data are in the form of noisy partial measurements of the past and present state of the dynamical system. Recently, there have been several promising data-driven approaches to forecasting of chaotic dynamical systems using machine learning. Particularly promising among these are hybrid approaches that combine machine learning with a knowledge-based model, where a machine-learning technique is used to correct the imperfections in the knowledge-based model. Such imperfections may be due to incomplete understanding and/or limited resolution of the physical processes in the underlying dynamical system, e.g., the atmosphere or the ocean. Previously proposed data-driven forecasting approaches tend to require, for training, measurements of all the variables that are intended to be forecast. We describe a way to relax this assumption by combining data assimilation with machine learning. We demonstrate this technique using the Ensemble Transform Kalman Filter to assimilate synthetic data for the three-variable Lorenz 1963 system and for the Kuramoto-Sivashinsky system, simulating a model error in each case by a misspecified parameter value. We show that by using partial measurements of the state of the dynamical system, we can train a machine-learning model to improve predictions made by an imperfect knowledge-based model.

Ontology based semantic interoperability approach in the Internet of Things for healthcare domain

Recent years have seen enormous growth in the number of devices connected to the Internet. With such rapid development in the Internet of Things (IoT) domain, data generated by these devices is ever increasing. Data is considered as one of the most crucial entities in the Internet of Things, and this data may be homogeneous as well as heterogeneous in nature. Analysis of homogeneous information is a simple process as this will not involve further processing, but analysis of heterogeneous data is a huge task. The heterogeneous nature of data in IoT based healthcare system, an important application, leads to semantic interoperability, which is the ability of systems to exchange data with definite, shared meaning. Semantic Interoperability expedites data interchange unambiguously irrespective of format and source of data. Therefore, a knowledge-based model is required to integrate heterogeneous data-generating devices to expand the applications of IoT. In this paper, an ontology-based model is proposed and implemented to collect the patient’s diverse data using different tools over gateways. Then the generated/collected data is transmitted to the cloud for processing in terms of semantics and structure. This results in a holistic mechanism in the form of an ontology used for the prediction and diagnostics of heart diseases in patients located at distant places by experts based at another location.

Development of a method for estimating security state: Supporting integrated response to cyber-attacks in NPPs

Nuclear regulatory guidelines require all nuclear facilities to establish sufficient prevention and response capabilities against cyber-attacks. In this study, an integrated cyber-attack response process at NPPs is analyzed. The integrated response process includes a safety-response security analysis that enacts a safety response against unperceived damage, as well as against potential damage. To help operators conduct the safety-related security analysis, a security state estimation method is developed. A knowledge-based hidden Markov modeling method is developed to model a probabilistic transition process of a security state. The constructed HMMs can be updated online for optimized security state estimation. The developed security state estimation method can help operators conduct a cause analysis and security impact analysis. By integrating with the probabilistic safety assessment method, the developed method can also be applied to a functional impact analysis. A case study was conducted to prove the validity of the developed method using a hardware-in-the-loop system.

Efficient estimation of Hindi WSD with distributed word representation in vector space

Word Sense Disambiguation (WSD) is significant for improving the accuracy of the interpretation of a Natural language text. Various supervised learning-based models and knowledge-based models have been developed in the literature for WSD of the language text. However, these models do not provide good results for low-resource languages, due to the lack of labelled and tagged data. Therefore, in this work, we have examined different word embedding techniques for word sense disambiguation of the Hindi language texts. Several studies in the literature show that these embeddings have been utilized for different foreign languages in the field of word sense disambiguation. However, to the best of our knowledge, no such work exists for the Hindi language. Therefore, in this paper, we utilize various existing word embeddings for WSD of Hindi text. Moreover, we have created Hindi word embeddings on articles taken from Wikipedia and test the quality of the created word embeddings using Pearson correlation. In this direction, we perform different experiments and observe that Word2Vec model gives best performance among all the considered embeddings on the used Hindi dataset. In our method, the proposed model directly takes input that is trained with word embedding methods and helps to develop a sense inventory using clustering that has been employed for performing disambiguation. Experimental observations indicate that the performance of the proposed approach is moderate and competent in terms of accuracy. The paper, thus, presents how WSD can leverage these representations to encode rich semantic information.

Technological Sector of the Economy: Problems of Identification

Technological development overall and support for high-tech areas of business one of the key segments of state policy of most of the world’s countries. At the same time, there is no uniform approach towards terminology and concept of the high-tech sector of the economy. The subject of this research is determination of the criteria that allow identifying the technological level of companies. The article employs the methods of content and bibliometric analysis, systematization and classification. Analysis is conducted on interpretation of the concepts of “technology” and “technology sector”, which reveals several approaches towards comprehension of the essence of these categories: instrumental, knowledge-based, performance, and business model. The conducted bibliometric analysis of the number of publications in leading Russian and international databases on the topics of “technology sector”, “technology companies”, “high-tech business”, “high-tech companies” and “information sector” indicates heightened interest in this topic. Examination of the experience of various countries, significant differences in identification of the technology sector are established. The author clarifies the direct and indirect criteria for classification of the companies as high-tech. Direct criteria included the use of high technologies in manufacturing and the production of high-tech products. The group of indirect criteria includes the intensity of costs for research and development, scientific content of products and production, involvement of highly competent personnel in business processes, and a short life cycle of the products.

An Improved Fuzzy Knowledge-Based Model For Long Stay Container Yards

An Improved Fuzzy Knowledge-Based Model For Long Stay Container Yards

Inherently safer design: An accident prevention perspective on reported confined space fatalities in Quebec

The design of most industrial facilities incorporates confined spaces. Although they are not designed for human occupation, many workers penetrate them to perform tasks such as repairs, cleaning, and inspections while facing the risks of asphyxiation, drowning, and toxicity from chemical exposure. Legislative and normative frameworks recommend adopting Inherently Safer Design (ISD) principles as the primary accident prevention strategy However, confined space fatalities occur mainly during improvised interventions, emphasizing the need for designers to consider these accidents' underlying factors in their future or present projects. This paper provides an applied perspective, suggesting how practitioners can employ ISD principles to effectively overcome the inherent design deficiencies and hazards associated with confined space fatalities. For this purpose, ten confined space fatalities in six different sectors of activity were analyzed using the Causal Tree Method (CTM). Industrial process cases are included. Our results show that alternative safer designs of confined spaces or permanent adapted equipment could eliminate the need for a confined space entry or confined space work. A first model of a design-oriented solutions knowledge base, called Confined Space Permanent Collective Principles (CSPCP), is proposed. This model provides stakeholders from across various industries with an overview of safety measures that can be integrated at different life cycle phases to address confined space hazards.

A PATTERNS OF MASCULINITIES IN DISCOURSE OF REPORTS ASSESSING CONDITION OF POLISH STARTUPS ORGANISATIONS

The purpose of this article is discourse analysis of masculinity created in reports assessing the current condition of Polish startups. The analysis covered reports published by the Startup Poland foundation from 2015-2019. This text is an attempt to apply the heuristic framework of integrative gender theories to interpret the results of the research, and explain how the discursively masculinity was constructed. Startups as innovative professional structures belonging to the knowledge-based economy model are an example of organizations typical of the information society. Numerous studies report changes (crises) occurring among the practiced male patterns (especially those typical for the countries of the global North). The results of the analysis show that despite these reports, the largest startup organizations striving to produce innovative solutions and using modern solutions, on the discursive surface, are associated with cultural patterns of hegemonic masculinity. Polish startups, on a structural and symbolic dimensions, are a highly masculine spaces. However, due to the practice of achieving hegemony, they (startups) can be interpreted in terms of cooperative or hybrid masculinity.

Word sense disambiguation based on context selection using knowledge-based word similarity

In this paper, we introduce a novel knowledge-based word-sense disambiguation (WSD) system. In particular, the main goal of our research is to find an effective way to filter out unnecessary information by using word similarity. For this, we adopt two methods in our WSD system. First, we propose a novel encoding method for word vector representation by considering the graphical semantic relationships from the lexical knowledge bases, and the word vector representation is utilized to determine the word similarity in our WSD system. Second, we present an effective method for extracting the contextual words from a text for analyzing an ambiguous word based on word similarity. The results demonstrate that the suggested methods significantly enhance the baseline WSD performance in all corpora. In particular, the performance on nouns is similar to those of the state-of-the-art knowledge-based WSD models, and the performance on verbs surpasses that of the existing knowledge-based WSD models.

Power Towers Knowledge Base Model Construction and Inference Analysis Based on Ontology

Due to the knowledge limitations in current traditional manual inspection of power towers and the difficulty of knowledge sharing and management, this paper would discuss the components of power towers with the characteristics and connections of different components based on the analysis on manual inspection. And then, an ontology-based knowledge model construction would be established for power towers. Finally, the potential association relationships in the model would be analysed according to the ontology inference rules, and the hidden information was excavated with several examples. The establishment of this knowledge base provides technical support for the path planning of UAV’s automatic inspection and helps with the fault diagnosis and identification so that it improves the sharing and reusability of knowledge in the field of power towers.

Development of model of a web-based information system control problem

The object of research is the processes of operation of a web-based information system. The conducted research is based on the application of existing approaches to organizing the operation of IT products, as well as on the previously developed formal model of the problem of managing the operation of an information system. The existing assessment of the satisfaction degree of the requirements for the system was adopted as the main criterion for managing the operation of the information system. The main hypothesis of the study is the assumption that the main criterion for managing the operation of a web-based information system should be considered the efficiency indicator as the ratio of the degree of satisfaction of requests for changes in individual components of the information system and the total costs of operating the system. The analysis of the applicability of the criterion «Satisfaction of the requirements of users of the information system» is carried out and its incomplete objectivity is shown for describing the goals of managing the operation of the information system. The use of the management efficiency indicator is substantiated, the features of the use of this indicator for solving the problem of managing the operation of the information system are considered. The existence of two approaches to determining the efficiency of the operation of an information system is recognized. Based on the results obtained, a concept for managing the operation of a web-based information system is proposed. This concept represents the main task of managing the operation of a web-based information system as a special case of a multicriteria optimization problem, the solution of which will be a Pareto-optimal system. On the basis of the proposed concept, a mathematical model of the problem of effective management of a web-based information system has been developed. To describe the function of the goal in the course of developing the model, it is proposed to move from descriptions of requirements to knowledge-based models of requests for changing the information system. It is also proposed to divide the set of model constraints into two separate complexes – a set of technical management constraints and a set of operating process constraints. Application of the developed model will make it possible to create new information technologies for managing the operation of web-based information systems for enterprise management. In contrast to the existing ones, such technologies will allow formalizing and automating the work on the formation and approval of the most profitable for the participants in the operation of the information system of project plans for fulfilling requests for changes in the operating system.