Query Retrieval Research Articles

Layered Query Retrieval: An Adaptive Framework for Retrieval-Augmented Generation in Complex Question Answering for Large Language Models

Retrieval-augmented generation (RAG) addresses the problem of knowledge cutoff and overcomes the inherent limitations of pre-trained language models by retrieving relevant information in real time. However, challenges related to efficiency and accuracy persist in current RAG strategies. A key issue is how to select appropriate methods for user queries of varying complexity dynamically. This study introduces a novel adaptive retrieval-augmented generation framework termed Layered Query Retrieval (LQR). The LQR framework focuses on query complexity classification, retrieval strategies, and relevance analysis, utilizing a custom-built training dataset to train smaller models that aid the large language model (LLM) in efficiently retrieving relevant information. A central technique in LQR is a semantic rule-based approach to distinguish between different levels of multi-hop queries. The process begins by parsing the user’s query for keywords, followed by a keyword-based document retrieval. Subsequently, we employ a natural language inference (NLI) model to assess whether the retrieved document is relevant to the query. We validated our approach on multiple single-hop and multi-hop datasets, demonstrating significant improvements in both accuracy and efficiency compared to existing single-step, multi-step, and adaptive methods. Our method exhibits high accuracy and efficiency, particularly on the HotpotQA dataset, where it outperforms the Adaptive-RAG method by improving accuracy by 9.4% and the F1 score by 16.14%. The proposed approach carefully balances retrieval efficiency with the accuracy of the LLM’s responses.

Combined query embroidery image retrieval based on enhanced CNN and blend transformer

Embroidery images carry rich historical information and are an important form of embroidery art. In the field of combination query image retrieval, how to efficiently retrieve the embroidery image information required by users has become a current research challenge. In recent years, convolutional neural networks (CNNs) have achieved significant success in image feature extraction, but they tend to focus on local information, making it easy to ignore global context information when processing such textured embroidery images. Therefore, we propose a combination query retrieval method for embroidery images. First, we propose Blend-Transformer, which introduces Group External Attention (GEA). GEA can integrate feature information from three different dimensions, effectively capturing the local and global context information of embroidery images. Second, we propose Enhanced CNN, which introduces Shuffle Attention (SA), regrouping the reference image features extracted by CNN and reaggregating them by channel to enhance the richness of embroidery image feature information. Through experiments on the TCE-S and ICR2020 standard datasets, we verify the excellent performance of the proposed algorithm in embroidery image retrieval. Our method fills the gap in embroidery image retrieval research and provides a new perspective for the protection of embroidery art.

PubMed Computed Authors in 2024: an open resource of disambiguated author names in biomedical literature.

Over 55% of author names in PubMed are ambiguous: the same name is shared by different individual researchers. This poses significant challenges on precise literature retrieval for author name queries, a common behavior in biomedical literature search. In response, we present a comprehensive dataset of disambiguated authors. Specifically, we complement the automatic PubMed Computed Authors algorithm with the latest ORCID data for improved accuracy. As a result, the enhanced algorithm achieves high performance in author name disambiguation, and subsequently our dataset contains more than 21 million disambiguated authors for over 35 million PubMed articles and is incrementally updated on a weekly basis. More importantly, we make the dataset publicly available for the community such that it can be utilized in a wide variety of potential applications beyond assisting PubMed's author name queries. Finally, we propose a set of guidelines for best practices of authors pertaining to use of their names. The PubMed Computed Authors dataset is publicly available for bulk download at: https://ftp.ncbi.nlm.nih.gov/pub/lu/ComputedAuthors/. Additionally, it is available for query through web API at: https://www.ncbi.nlm.nih.gov/research/bionlp/APIs/authors/.

Database Construction and Application of Large-scale Geospatial Data

Abstract. Geospatial data refers to data that related to spatial location. It is the abstract representation of objects, events, or other characteristic information located on or near the surface of the Earth. It characterizes attribute features, spatial features, and associated information of geospatial features. Geospatial data commonly include various data types such as point, polyline, polygon, and so on. Geospatial database is the basic method to store and manage geospatial data. It is also the important component of geographic information systems (GIS). Geospatial database generally stores data in a specific structure in a medium, which can achieve efficient management of geospatial data. Users can add, modify, and delete data efficiently. Furthermore, query retrieval and statistical analysis can be quickly performed based on geospatial database. In this paper, distributed geospatial database is constructed by using database partition tables storage technology. Meanwhile, database construction software is developed to achieve the construction, management, and application of large-scale geospatial data. It can improve data import, query and retrieval efficiency significantly. The database application service system can directly connect to the database for displaying statistical analysis results. At the same time, geospatial data are processed to vector tiles, which stored in the tile database. Furthermore, standard online service is then published, which can be used for database management and application service system. It can be used for natural resource management work such as basic surveying, survey and monitoring, and so on.

AMGPT: A large language model for contextual querying in additive manufacturing

Generalized large language models (LLMs) such as GPT-4 may not provide specific answers to queries formulated by materials science researchers. These models may produce a high-level outline but lack the capacity to return detailed instructions on manufacturing and material properties of novel alloys. We introduce “AMGPT”, a specialized LLM text generator designed for metal AM queries. The goal of AMGPT is to assist researchers and users in navigating a curated corpus of literature. Instead of training from scratch, we employ a pre-trained Llama2-7B model from Hugging Face in a Retrieval-Augmented Generation (RAG) setup, utilizing it to dynamically incorporate information from ∼50 AM papers and textbooks in PDF format. Mathpix is used to convert these PDF documents into TeX format, facilitating their integration into the RAG pipeline managed by LlamaIndex. A query retrieval function has also been added, enabling the system to fetch relevant literature from Elsevier journals based on the context of the query. Expert evaluations of this project highlight that specific embeddings from the RAG setup accelerate response times and maintain coherence in the generated text.

Automated SPARQL Template for Flexible Question Answering

The knowledge bases required the query language SPARQL, which consists of subject, property, and object. SPARQL is a structured query language and is difficult to understand. That issue becomes a problem in natural language processing queries. One situation in question answering is how to translate natural language into a structural SPARQL. This work aims to develop an automated SPARQL template algorithm regardless of the pattern structure of the query triples. It provides a more varied SPARQL query for data retrieval named Flexible SPARQL. This approach initially lies in combining elements of RDF with basic techniques of natural language processing to generate a template of SPARQL. In this work, the approach to making automatic templates is proposed without regard to the pattern of the triple structure or the location of the subject and object. Template-based research that exists today still uses rules to determine the position of subjects, objects, and properties in the SPARQL structure. Therefore, this work used the QALD 7 question set and DBpedia dataset. The previous systems utilized the same questions and data sets. Despite the simple proposed approaches that do not use complex, sophisticated techniques, they have shown promising results compared to the previous systems. The accuracy result from 215 questions is 73% and micro-Recall 0.701, micro-Precision 0.664, micro-F-Measure 0.682, macro-Recall 0.711, macro-Precision 0.592, macro-F-Measure 0.646. Overall, the Flexible SPARQL system has higher results on several measurements that define a promising approach. However, it's important to note that Flexible SPARQL generally tends to fail at generating complex SPARQL, which is a limitation of the system.

Object-based image retrieval and detection for surveillance video

With technological advancement worldwide, the video surveillance market is growing drastically in a versatile field. Monitoring, browsing, and retrieving a specific object in a long video becomes difficult due to the enormous amount of data produced by the surveillance camera. With limitations on human resources and browsing time, there is a need for a new video analytics model to handle more complex tasks, such as object detection and query retrieval. The current approach involves techniques like unsupervised segmentation, multiscale segmentation, and feature-based descriptions. However, these methods often encounter extensive space and time consumption challenges. A solution has been developed for retrieving targeted objects from surveillance videos via user queries, employing a graphical interface for input. Extracting relevant frames based on user-entered text queries is enabled through using YOLOv8 for object detection. Users interact through a graphical user interface deployed on a Jetson Xavier Development board. The system's outcome is a time-efficient and highly accurate automated model for object detection and query retrieval, eliminating human errors associated with manually locating objects in videos upon user queries.

CoDuBoTeSS: A Pilot Study to Eradicate Counterfeit Drugs via a Blockchain Tracer Support System on the Nigerian Frontier

The pharma-sector has maintained improved productivity and profitability via a concerted effort to address critical issues such as an unorganized regulatory system, lack of safety data, no standards in manufacture process, non-adaptation to pharma-chain, and no-harmony of inventory supports. Study proposes blockchain trace-support to ensure drugs quality, consumer safety, and its trading as asset. It uses a radio-frequency identification sensor to register manufacture and administration process, and provide a databank to trace drug records. Results notes: (a) presents a roadmap for adoption by the National Agency for Food and Drug Administration and Control (NAFDAC) to ensure a traceable pharmaceutical blockchain, (b) show ensemble is scalable for up-to 7500users to yield a performance of 1138-transactions per seconds with response time of 88secs for page retrieval and 128secs for queries respectively, and (c) yields slightly longer time for increased number of users via its world-state as stored in the permissionless blockchain hyper-fabric ledger. Thus, the framework can directly query and retrieve data without it traversing the whole ledger. This, in turn, improves the efficiency and effectiveness of the traceability system. Keywords: Blockchain, Counterfeit drugs, Healthcare, Nigeria, CORDA, hyper-ledger fabric, HIPPA Journal Reference Format: Ifioko, A.M., Yoro, R.E., Okpor, M.D., Brizimor, S.E, Obasuyi, D., Emordi, F.U., Odiakaose, C.C., Ojugo, A.A., Atuduhor, R.R, Abere, R.A., Ejeh, P.O., Ako, R.E. & Geteloma, V.O. (2024): CoDuBoTeSS: A Pilot Study to Eradicate Counterfeit Drugs via a Blockchain Tracer Support System on the Nigerian Frontier. Journal of Behavioural Informatics, Digital Humanities and Development Rese Vol. 10 No. 2. Pp 53-74 https://www.isteams.net/behavioralinformaticsjournal dx.doi.org/10.22624/AIMS/BHI/V10N2P6

CoDuBoTeSS: A Pilot Study to Eradicate Counterfeit Drugs via a Blockchain Tracer Support System on the Nigerian Frontier

The pharma-sector has maintained improved productivity and profitability via a concerted effort to address critical issues such as an unorganized regulatory system, lack of safety data, no standards in manufacture process, non-adaptation to pharma-chain, and no-harmony of inventory supports. Study proposes blockchain trace-support to ensure drugs quality, consumer safety, and its trading as asset. It uses a radio-frequency identification sensor to register manufacture and administration process, and provide a databank to trace drug records. Results notes: (a) presents a roadmap for adoption by the National Agency for Food and Drug Administration and Control (NAFDAC) to ensure a traceable pharmaceutical blockchain, (b) show ensemble is scalable for up-to 7500users to yield a performance of 1138-transactions per seconds with response time of 88secs for page retrieval and 128secs for queries respectively, and (c) yields slightly longer time for increased number of users via its world-state as stored in the permissionless blockchain hyper-fabric ledger. Thus, the framework can directly query and retrieve data without it traversing the whole ledger. This, in turn, improves the efficiency and effectiveness of the traceability system. Keywords: Blockchain, Counterfeit drugs, Healthcare, Nigeria, CORDA, hyper-ledger fabric, HIPPA Journal Reference Format: Ifioko, A.M., Yoro, R.E., Okpor, M.D., Brizimor, S.E, Obasuyi, D., Emordi, F.U., Odiakaose, C.C., Ojugo, A.A., Atuduhor, R.R, Abere, R.A., Ejeh, P.O., Ako, R.E. & Geteloma, V.O. (2024): CoDuBoTeSS: A Pilot Study to Eradicate Counterfeit Drugs via a Blockchain Tracer Support System on the Nigerian Frontier. Journal of Behavioural Informatics, Digital Humanities and Development Rese Vol. 10 No. 2. Pp 53-74 https://www.isteams.net/behavioralinformaticsjournal dx.doi.org/10.22624/AIMS/BIJ/V10N1P6

Towards the development of an electrochemical random access DNA memory (e-RADM)

As a result of the exponentially growing amount of information being produced, new data storage solutions are required. DNA has attracted significant attention as a potential data storage medium thanks to several intrinsic properties, such as ultrahigh physical information density with up to 2 bits per nucleotide. Current DNA-based memories rely on sequencing strategies for data recovery. However, sequencing all DNA strands for data retrieval would be very time consuming and thus result in high levels of latency. Therefore, random access strategies are required to make DNA-based data storage a viable alternative. Here, we present our first steps towards the development of a compartmentalized electrochemical random access DNA memory (e-RADM) using cascade reactions controlled by DNA nanostructures immobilized on gold microelectrode arrays which will be triggered when a specific information retrieval query is put into the system. Electrodes containing the desired information can then be identified by Square Wave Voltammetry.Graphical abstract

Integrated knowledge graph construction framework for places-of-interest retrieval using a property graph database

ABSTRACT With recent technological advances, the efficient extraction and utilization of valuable information from large-scale data sources have become increasingly important. The development of knowledge graphs (KGs) based on logical relationships between data has garnered attention from various location-related services. To provide results that satisfy the diverse preferences of individuals, explicit attributes and implicit semantic context must be considered during the retrieval of places of interest (POIs). Most POI retrievals often involve not just examining detailed information about places but also specifying places for intended visits. Therefore, spatial knowledge regarding the surroundings of POIs, such as proximity and accessible routes, should be incorporated to support decision-making. In this study, we propose a comprehensive framework for constructing a KG for POI retrieval (PKG), which adeptly integrates the place attributes, semantic features, and spatial context of locations. The core objective of this framework is to acquire suitable data for facilitating POI retrieval that effectively considers diverse user preferences for places. After constructing a PKG of Orlando (FL, USA), we verified the practical applicability of the proposed framework by conducting 10 types of distinct POI retrieval queries catering to a range of user preferences. The graph queries returned a list of POIs that precisely aligned with the requirements of users on not only the explicit attributes of places but also the spatial and semantic features while providing detailed travel route information to these destinations. In conclusion, the PKG enabled POI retrieval that satisfied user preferences and diversified the retrieved places and the information provided. As the PKG offers flexibility in data integration without physical constraints, it can be expanded by incorporating information from various sources.

Developing User-Friendly and Cost-Effective Sales Accounting Systems for the MSME Sector

This study aimed to develop and implement a user-friendly sales accounting information system for Manja Cheese Tea Macanan, a Small and Medium-sized Enterprise (SME) specializing in contemporary milk-based beverages. Employing a development research methodology, data was collected through interviews, observations, and document analysis to understand the existing sale process and information needs of Manja Cheese Tea Macanan. The sales accounting information system design process comprised constructing relational database tables, defining entity-relationship diagrams, creating data retrieval queries, and designing user-friendly forms, reports, and navigation menus (login, home, sales switchboard). The findings revealed that Manja Cheese Tea Macanan relied on a amnual sales system, highlighting the need for automation and improved data management. The designed sales accounting information system was tailored to the specific needs of Manja Cheese Tea Macanan and successfully implemented. The system demonstrated operational effectiveness in facilitating sales recording, data management, and information retrieval, addresing the identified limitations of the earlier manual system.

Counterfeit Drugs Detection in the Nigeria Pharma-Chain via Enhanced Blockchain-based Mobile Authentication Service

Drugs has since become a major source of livelihood for Nigerians. It also accounts for over 85% of the total food consumed within her borders. The sector has maintained improved productivity and profitability via a concerted effort to address critical issues such as an unorganized regulatory system, lack of food safety data, no standards in agricultural produce, non-adaptation to precision farming, and non-harmony via inventory trace supports. This study proposes blockchain-based tracer-support system in a continued effort to ensure food quality, consumer safety, and trading of food assets. It uses the radio-frequency identification sensors to register and trace drugs manufacture cum administration process and provide a databank to trace the drug records via the shipment to its distribution centers. To ascertain, if the drug is genuine or fake, the user scans the QRcode via the mobile application API, which then generates feedback. Results achieves the following: (a) presents a framework and roadmap for adoption by the National Agency for Food and Drug Administration and Control (NAFDAC) to ensure pharmaceutical blockchain, (b) show ensemble is scalable for up-to 7500users to yield a performance of 1138-transactions per seconds with response time of 88secs for page retrieval and 128secs for queries respectively, and (c) yields slightly longer time for increased number of users via its world-state as stored in the permissionless blockchain hyper-fabric ledger. Thus, the framework can directly query and retrieve data without it traversing the whole ledger. This, in turn, improves the efficiency and effectiveness of the traceability system. Keywords: Nigerian Pharma-Chain, Fake/Counterfeit drugs, Healthcare, CORDA, hyper-ledger fabric, NAFDAC Ejeh, P.O., Okpor, M.D., Yoro, R.E., Ifioko, A.M., Onyemenem, I.S., Odiakaose, C,C., Ojugo, A.A., Ako, R.E., Emordi, F.U., Geteloma, V.O., Counterfeit Drugs Detection in the Nigeria Pharma-Chain via Enhanced Blockchain-based Mobile Authentication Service. Journal of Advances in Mathematical & Computational Science. 2024, Vol. 12, No. 1. Pp 25-44. Available online at www.isteams.net/mathematics-computationaljournal. dx.doi.org/10.22624/AIMS/MATHS/V12N2P3

Your Cursor Reveals: On Analyzing Workers’ Browsing Behavior and Annotation Quality In Crowdsourcing Tasks

In this work, we investigate the connection between browsing behavior and task quality of crowdsourcing workers performing annotation tasks that require information judgements. Such information judgements are often required to derive ground truth answers to information retrieval queries. We explore the use of workers’ browsing behavior to directly determine their annotation result quality. We hypothesize <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">user attention</i> to be the main factor contributing to a worker’s annotation quality. To predict annotation quality at the task level, we model two aspects of task-specific user attention, also known as <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">general</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">semantic user attentions</i> . Both aspects of user attention can be modeled using different types of browsing behavior features but most previous research mostly focuses on the former. This work therefore proposes to model semantic user attention by capturing the worker’s understanding of task content using task-semantics specific behavior features. We develop a web-based annotation interface for gathering user behavior data when workers perform a knowledge path retrieval task. With the collected data, we train several prediction models using behavior features corresponding to different aspects of user attention and conduct experiments on a set of annotation tasks performed by 51 Amazon Mechanical Turk workers. We show that the prediction model using both general and semantic user attention features can achieve the best performance of nearly 75% accuracy.

Dynamically retrieving knowledge via query generation for informative dialogue generation

Knowledge-driven dialogue systems have recently made remarkable breakthroughs. Compared with general dialogue systems, superior knowledge-driven dialogue systems can generate more informative and knowledgeable responses with pre-provided knowledge. However, in practical applications, the knowledge-driven dialogue systems cannot be supplied with relevant knowledge beforehand. Hence, to enhance the practicality of the knowledge-driven dialogue systems, it is crucial to devise a method to dynamically retrieve pertinent knowledge based on the context. In addressing this challenge, we introduce a knowledge-driven dialogue system called DRKQG (Dynamically Retrieving Knowledge via Query Generation for informative dialogue response). Specifically, this system is composed of two main modules: a query generation module and a response generation module. Initially, a time-aware mechanism is employed to capture contextual information, enabling the generation of a query for knowledge retrieval through a search engine. Subsequently, we incorporate the copy mechanism and transformers, empowering the response generation module to create responses based on both the context and retrieved knowledge. Experimental results at LIC2022, Language and Intelligence Technology Competition, show that our module outperforms the baseline model by a large margin on automatic evaluation metrics, while human evaluation by the Baidu Linguistics team shows that our system achieves impressive results in Factually Correct and Knowledgeable.

Trip Planning and Recommendation System with AI Chatbot

The principle aim of this project is to develop a responsive website, which would comprehend the process of tour planning and management for users. With the increasing popularity of tourism and recreational activities all around the world has increased, there is a need for an advanced and smart tour planning system, which would make it easier for users to plan and execute trips. This proposed website is built in such a way that the user will get to know all aspects related to his trips, and there will be a ChatBot, which would make the booking procedure easier for the user. The Chatbot would suggest the user different destinations based on the user’s area of interest and make the decision-making process more rational. Also, it would help the user to gain more insights about their dream holidays for a smooth trip without any disturbances and mismanagements. Along with the ChatBot, we also integrated a virtual tour feature, which would give users a glance at their dream destinations. The development of the website involves various software integrated using a robust backend system, which will implement and handle the processing and retrieval of travel-related data, ensuring fast and accurate user queries. The front end of the website will be designed to provide an intuitive and visually appealing UI, enhancing the UX. Keywords — Chatbot, virtual tour, user interface, user experience, frontend, backend.

Simple questions for complex matters?

Renewable energy sources have emerged as a current subject matter in Sweden amidst discussions regarding energy costs, climate change and development of energy production. This study explores how Google Search is used for seeking information about wind power and how utilised search queries contribute to the understanding of this energy source. Adopting a practice theoretical perspective, the study explores search queries as doings and sayings, and understands search engines as an established part of everyday routinised information seeking-activities. Data collection was carried out in a trace ethnographic vein through the automatic retrieval of search queries enacted between November 2021 and October 2022. Through a digital methods approach, the search queries were analysed and visualised according to their prevalence and character string composition. A qualitative, multiple coding approach was moreover used for the identification and interpretation of themes and subthemes. The results show that geographical locations, wind power functions and small wind turbines comprise the most prominent subthemes of the search queries. This is replicated also in the search term frequencies, providing further insights to queries related to wind turbine’s efficiency as well as subthemes of advantages and disadvantages. Moreover, the study shows the tendency to phrase search queries as simple questions for complex matters, with nuances being lost in the pursuit of austere, uncomplicated answers. Altogether, the results contribute to a wider understanding of how environmental information seeking is conducted today.

Effective matching of patients to clinical trials using entity extraction and neural re-ranking

Introduction:Clinical trials (CTs) often fail due to inadequate patient recruitment. Finding eligible patients involves comparing the patient’s information with the CT eligibility criteria. Automated patient matching offers the promise of improving the process, yet the main difficulties of CT retrieval lie in the semantic complexity of matching unstructured patient descriptions with semi-structured, multi-field CT documents and in capturing the meaning of negation coming from the eligibility criteria. Objectives:This paper tackles the challenges of CT retrieval by presenting an approach that addresses the patient-to-trials paradigm. Our approach involves two key components in a pipeline-based model: (i) a data enrichment technique for enhancing both queries and documents during the first retrieval stage, and (ii) a novel re-ranking schema that uses a Transformer network in a setup adapted to this task by leveraging the structure of the CT documents. Methods:We use named entity recognition and negation detection in both patient description and the eligibility section of CTs. We further classify patient descriptions and CT eligibility criteria into current, past, and family medical conditions. This extracted information is used to boost the importance of disease and drug mentions in both query and index for lexical retrieval. Furthermore, we propose a two-step training schema for the Transformer network used to re-rank the results from the lexical retrieval. The first step focuses on matching patient information with the descriptive sections of trials, while the second step aims to determine eligibility by matching patient information with the criteria section. ResultsOur findings indicate that the inclusion criteria section of the CT has a great influence on the relevance score in lexical models, and that the enrichment techniques for queries and documents improve the retrieval of relevant trials. The re-ranking strategy, based on our training schema, consistently enhances CT retrieval and shows improved performance by 15% in terms of precision at retrieving eligible trials. ConclusionThe results of our experiments suggest the benefit of making use of extracted entities. Moreover, our proposed re-ranking schema shows promising effectiveness compared to larger neural models, even with limited training data. These findings offer valuable insights for improving methods for retrieval of clinical documents.

Developing Energy Access Ontology using Protege Tool

In this internet-based world where a large amount of information exists on the World Wide Web (WWW), the information retrieval systems are mainly centred on topic-based classification. Numerous efforts and time have been consumed for relevant information extraction through major search engines if the data is not organised correctly. Ontologies proved to be an effective technique for representing and retrieving information, which is the key idea in semantic web applications. Ontologies not only help in efficient knowledge representation and information retrieval, but it also helps in mapping the hidden knowledge about a subject. This paper discusses the process and method of building ontology on the “Energy access” domain. The methodology is based on the tools used in developing the ontology. Several tools are used to create an ontology. Protégé is a most popular tool for ontology editing and for developing ontology.1 In this paper, various aspects like super class and subclass hierarchy, creating a subclass, instances for class illustration, query retrieval process, visualisation, and graph views have been demonstrated by using protégé software.

Half-plane point retrieval queries with independent and dependent geometric uncertainties

This paper addresses a family of geometric half-plane retrieval queries of points in the plane in the presence of geometric uncertainty. The problems include exact and uncertain point sets and half-plane queries defined by an exact or uncertain line whose location uncertainties are independent or dependent and are defined by k real-valued parameters. Point coordinate uncertainties are modeled with the Linear Parametric Geometric Uncertainty Model (LPGUM), an expressive and computationally efficient worst-case, first order linear approximation of geometric uncertainty that supports parametric dependencies between point locations. We present an efficient O(k2) time and space algorithm for computing the envelope of the LPGUM line that defines the half-plane query. For an exact line and an LPGUM n points set, we present an O(log⁡nk+mk) time query and O(nk) space algorithm, where m is the number of LPGUM points on or above the half-plane line. For a LPGUM line and an exact points set, we present a O(k2+(klog⁡nlog⁡log⁡n)ε+m) time and O(n2log⁡n+kε) space approximation algorithm, where 0<ε≤1 is the desired approximation error. For a LPGUM line and an LPGUM points set, we present two O(k2+(klog⁡nklog⁡log⁡nk)ε+mk) and O(mk2+(klog⁡nklog⁡log⁡nk)ε) time query and O((nk)2log⁡nk+kε) space approximation algorithms for the independent and dependent case, respectively.