Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
14,997
result(s) for
"knowledge retrieval"
Sort by:
Transition from Traditional Knowledge Retrieval into AI-Powered Knowledge Retrieval in Infrastructure Projects: A Literature Review
The transition from traditional knowledge retrieval to artificial intelligence-powered knowledge retrieval signifies a fundamental change in data processing, analysis, and use in infrastructure projects. This systematic review presents a thorough literature analysis, examining the transition of traditional knowledge retrieval strategies from manual-based and statistical models to modern AI methodologies. This study systematically retrieved data from 2015–2024 through Scopus, Google Scholar, Web of Science, and PubMed. This study underscores the constraints of traditional approaches, particularly their reliance on manually generated rules and domain-specific attributes, in comparison to the flexibility and scalability of AI-powered solutions. This review highlights limitations, including data bias, computing requirements, and interpretability in the AI-powered knowledge retrieval systems, while exploring possible mitigating measures. This paper integrates current research to clarify the advancements in knowledge retrieval and discusses prospective avenues for integrating AI technology to tackle developing data-driven concerns in knowledge retrieval for infrastructure projects.
Journal Article
Knowledge retrieval of historic concepts using semantic web
This paper presents a comprehensive survey on knowledge retrieval of historical concepts using semantic web technologies. The scope of this discussion encompasses research material in the field of computing and humanities including but not limited to Cultural Heritage, Museum and Digital Library research. Semantic web techniques used to describe, store, search, query and retrieve historic concepts such as RDF, RDFs, OWL, and Ontologies are discussed along with other extensively researched methods from domains like Natural Language Processing and Computer Vision. The discussion elaborates on Ontological-enabled information retrieval and the concept of new knowledge discovery. This work presents a comprehensive set of problems identified in the field of information retrieval and their solutions through the semantic web along with an insight in the future directions and the open-ended questions in the domain of retrieval of historic concept.
Journal Article
Business analytics using R - A practical approach
Learn the fundamental aspects of the business statistics, data mining, and machine learning techniques required to understand the huge amount of data generated by your organization. This book explains practical business analytics through examples, covers the steps involved in using it correctly, and shows you the context in which a particular technique does not make sense. Further, Practical Business Analytics using R helps you understand specific issues faced by organizations and how the solutions to these issues can be facilitated by business analytics. This book will discuss and explore the following through examples and case studies: An introduction to R: data management and R functions The architecture, framework, and life cycle of a business analytics project Descriptive analytics using R: descriptive statistics and data cleaning Data mining: classification, association rules, and clustering Predictive analytics: simple regression, multiple regression, and logistic regression This book includes case studies on important business analytic techniques, such as classification, association, clustering, and regression. The R language is the statistical tool used to demonstrate the concepts throughout the book. You will:? Write R programs to handle data? Build analytical models and draw useful inferences from them? Discover the basic concepts of data mining and machine learning? Carry out predictive modeling? Define a business issue as an analytical problem.
Book
Appropriability and the retrieval of knowledge after spillovers
Research summary: Firms create and capture value through innovation. In technology-driven firms, there has been an explicit emphasis on appropriability through imitation deterrence and cumulative inventions that build on prior firm innovation. We introduce systematic empirical evidence for a third mechanism of appropriability namely, knowledge retrieval, which is defined as the re-absorption of previously spilled knowledge. We extend previous studies which consider technological complexity and organizational coupling as predictors of appropriability by examining their impact on knowledge retrieval. We find that technological complexity has a curvilinear relationship with retrieval while organizational coupling has a negative relationship. We discuss the implications of these findings for theories of absorptive capacity, organizational design and appropriability of innovation. Managerial summary: It is a widely held assumption that knowledge should be protected and held tightly within the firm to ensure value creation and value capture. The implicit recognition is that knowledge spillovers, or knowledge leakage, is detrimental to performance. By examining the patterns of citations among patents of 142 semiconductor firms, we study how organizational structure and technological complexity play a role. We find that moderate technological complexity improves appropriability. If imitation deterrence is paramount, then the optimal structure would be a tightly-coupled organization. In other instances, loosely-coupled organizations may be superior because they foster internal cumulative innovations and, if spillovers were to occur, they also maximize knowledge retrieval. Our findings suggest that all is not lost when spillovers occur and that firms can continue to benefit in downstream innovations.
Journal Article
KnowledgeNavigator: leveraging large language models for enhanced reasoning over knowledge graph
Large language models have achieved outstanding performance on various downstream tasks with their advanced understanding of natural language and zero-shot capability. However, they struggle with knowledge constraints, particularly in tasks requiring complex reasoning or extended logical sequences. These limitations can affect their performance in question answering by leading to inaccuracies and hallucinations. This paper proposes a novel framework called KnowledgeNavigator that leverages large language models on knowledge graphs to achieve accurate and interpretable multi-hop reasoning. Especially with an analysis-retrieval-reasoning process, KnowledgeNavigator searches the optimal path iteratively to retrieve external knowledge and guide the reasoning to reliable answers. KnowledgeNavigator treats knowledge graphs and large language models as flexible components that can be switched between different tasks without additional costs. Experiments on three benchmarks demonstrate that KnowledgeNavigator significantly improves the performance of large language models in question answering and outperforms all large language models-based baselines.
Journal Article
Augmenting Orbital Debris Identification with Neo4j-Enabled Graph-Based Retrieval-Augmented Generation for Multimodal Large Language Models
This preliminary study covers the construction and application of a Graph-based Retrieval-Augmented Generation (GraphRAG) system integrating a multimodal LLM, Large Language and Vision Assistant (LLaVA) with graph database software (Neo4j) to enhance LLM output quality through structured knowledge retrieval. This is aimed at the field of orbital debris detection, proposed to support the current intelligent methods for such detection by introducing the beneficial properties of both LLMs and a corpus of external information. By constructing a dynamic knowledge graph from relevant research papers, context-aware retrieval is enabled, improving factual accuracy and minimizing hallucinations. The system extracts, summarizes, and embeds research papers into a Neo4j graph database, with API-powered LLM-generated relationships enriching interconnections. Querying this graph allows for contextual ranking of relevant documents, which are then provided as context to the LLM through prompt engineering during the inference process. A case study applying the technology to a synthetic image of orbital debris is discussed. Qualitative results indicate that the inclusion of GraphRAG and external information result in successful retrieval of information and reduced hallucinations. Further work to refine the system is necessary, as well as establishing benchmark tests to assess performance quantitatively. This approach offers a scalable and interpretable method for enhanced domain-specific knowledge retrieval, improving the qualitative quality of the LLM’s output when tasked with description-based activities.
Journal Article
COVID-19 knowledge deconstruction and retrieval: an intelligent bibliometric solution
COVID-19 has been an unprecedented challenge that disruptively reshaped societies and brought a massive amount of novel knowledge to the scientific community. However, as this knowledge flood continues surging, researchers have been disadvantaged by not having access to a platform that can quickly synthesize emerging information and link the new knowledge to the latent knowledge foundation. Aiming to fill this gap, we propose a research framework and develop a dashboard that can assist scientists in identifying, retrieving, and understanding COVID-19 knowledge from the ocean of scholarly articles. Incorporating principal component decomposition (PCD), a knowledge mode-based search approach, and hierarchical topic tree (HTT) analysis, the proposed framework profiles the COVID-19 research landscape, retrieves topic-specific latent knowledge foundation, and visualizes knowledge structures. The regularly updated dashboard presents our research results. Addressing 127,971 COVID-19 research papers from PubMed, the PCD topic analysis identifies 35 research hotspots, along with their inner correlations and fluctuating trends. The HTT result segments the global knowledge landscape of COVID-19 into clinical and public health branches and reveals the deeper exploration of those studies. To supplement this analysis, we additionally built a knowledge model from research papers on the topic of vaccination and fetched 92,286 pre-Covid publications as the latent knowledge foundation for reference. The HTT analysis results on the retrieved papers show multiple relevant biomedical disciplines and four future research topics: monoclonal antibody treatments, vaccinations in diabetic patients, vaccine immunity effectiveness and durability, and vaccination-related allergic sensitization.
Journal Article
Evaluation of LLMs accuracy and consistency in the registered dietitian exam through prompt engineering and knowledge retrieval
Large language models (LLMs) are fundamentally transforming human-facing applications in the health and well-being domains: boosting patient engagement, accelerating clinical decision-making, and facilitating medical education. Although state-of-the-art LLMs have shown superior performance in several conversational applications, evaluations within nutrition and diet applications are still insufficient. In this paper, we propose to employ the Registered Dietitian (RD) exam to conduct a standard and comprehensive evaluation of state-of-the-art LLMs, GPT-4o, Claude 3.5 Sonnet, and Gemini 1.5 Pro, assessing both accuracy and consistency in nutrition queries. Our evaluation includes 1050 RD exam questions encompassing several nutrition topics and proficiency levels. In addition, for the first time, we examine the impact of Zero-Shot (ZS), Chain of Thought (CoT), Chain of Thought with Self Consistency (CoT-SC), and Retrieval Augmented Prompting (RAP) on both accuracy and consistency of the responses. Our findings revealed that while these LLMs obtained acceptable overall performance, their results varied considerably with different prompts and question domains. GPT-4o with CoT-SC prompting outperformed the other approaches, whereas Gemini 1.5 Pro with ZS recorded the highest consistency. For GPT-4o and Claude 3.5, CoT improved the accuracy, and CoT-SC improved both accuracy and consistency. RAP was particularly effective for GPT-4o to answer Expert level questions. Consequently, choosing the appropriate LLM and prompting technique, tailored to the proficiency level and specific domain, can mitigate errors and potential risks in diet and nutrition chatbots.
Journal Article