Text-based Queries Research Articles

A clip-based dual-stream method for text based vehicle search

A text-based vehicle search refers to a system where users can find vehicles or route information by entering text-based queries. The primary objective of text-based vehicle search is to identify the most relevant vehicle in a given dataset using a natural language description as a query. This approach leverages natural language processing (NLP) to understand and interpret description queries and provide relevant results. Despite significant progress, this task still faces several challenges due to the complexity and diversity of natural language, as well as inherent difficulties in the vision domain. Moreover, few studies have focused on tracked-vehicle retrieval, where vehicle tracklets are considered instead of single images. In this paper, we propose a novel framework for natural language-based tracked-vehicle retrieval based on CLIP model, one of the most effective models for image-text matching task. This framework leverages both appearance and motion information to enhance the matching accuracy of vehicle tracklet retrieval. Some experiments are conducted on the CityFlow-NL dataset, provided by the 6-th AI City Challenge, an annual competition. The results are comparable to state-of-the-art methods, achieving an MRR score of 46.63%, Rank@5 of 67.02%, and Rank@10 of 81.82%

Unsupervised Content Mining in CBIR: Harnessing Latent Diffusion for Complex Text-Based Query Interpretation.

The paper demonstrates a novel methodology for Content-Based Image Retrieval (CBIR), which shifts the focus from conventional domain-specific image queries to more complex text-based query processing. Latent diffusion models are employed to interpret complex textual prompts and address the requirements of effectively interpreting the complex textual query. Latent Diffusion models successfully transform complex textual queries into visually engaging representations, establishing a seamless connection between textual descriptions and visual content. Custom triplet network design is at the heart of our retrieval method. When trained well, a triplet network will represent the generated query image and the different images in the database. The cosine similarity metric is used to assess the similarity between the feature representations in order to find and retrieve the relevant images. Our experiments results show that latent diffusion models can successfully bridge the gap between complex textual prompts for image retrieval without relying on labels or metadata that are attached to database images. This advancement sets the stage for future explorations in image retrieval, leveraging the generative AI capabilities to cater to the ever-evolving demands of big data and complex query interpretations.

Generating Novel Leads for Drug Discovery Using LLMs with Logical Feedback

Large Language Models (LLMs) can be used as repositories of biological and chemical information to generate pharmacological lead compounds. However, for LLMs to focus on specific drug targets typically requires experimentation with progressively more refined prompts. Results thus become dependent not just on what is known about the target, but also on what is known about the prompt- engineering. In this paper, we separate the prompt into domain-constraints that can be written in a standard logical form and a simple text-based query. We investigate whether LLMs can be guided, not by refining prompts manually, but by refining the logical component automatically, keeping the query unchanged. We describe an iterative procedure LMLF (“Language Model with Logical Feedback”) in which the constraints are progressively refined using a logical notion of generalisation. On any iteration, newly generated instances are verified against the constraint, providing "logical-feedback" for the next iteration's refinement of the constraints. We evaluate LMLF using two well-known targets (inhibition of the Janus Kinase 2; and Dopamine Receptor D2); and two different LLMs (GPT-3 and PaLM). We show that LMLF, starting with the same logical constraints and query text, can be used to guide both LLMs to generate potential leads. We find: (a) Binding affinities of LMLF-generated molecules are skewed towards higher binding affinities than those from existing baselines; (b) LMLF results in generating molecules that are skewed towards higher binding affinities than without logical feedback; (c) Assessment by a computational chemist suggests that LMLF generated compounds may be novel inhibitors. These findings suggest that LLMs with logical feedback may provide a mechanism for generating new leads without requiring the domain-specialist to acquire sophisticated skills in prompt-engineering.

Efficient text-based query based on multi-level and deep-semantic multimedia indexing and retrieval

Efficient text-based query based on multi-level and deep-semantic multimedia indexing and retrieval

Is the laboratory report dead? AI and ChatGPT

The launch of ChatGPT and artificial intelligence (AI) platforms capable of generating written responses to a vast range of text-based queries has transformed the conceptualisation of assessment in education. Apart from its potential for misuse in test and examinations, the laboratory report in Science Education may be vulnerable to AI-disruption. This article outlines five text-based prompts that educators can use to assess the quality of AI-generated output in scientific writing. When used to query the freely accessible version of ChatGPT (GPT-3.5) in June 2023, these prompts revealed its ability to produce written work that showcases high-level organisation of concepts relevant to a scientific topic. However, these AI-generated responses remain generalised, lacking specificity and without effective integration of peer-reviewed scientific literature. As these generative AI platforms continue to improve, educators can use this series of prompts to evaluate the quality of AI output and adapt the assessment criteria for this new era in scientific writing.

Semantic Protocol and Resource Description Framework Query Language: A Comprehensive Review

This review presents various perspectives on converting user keywords into a formal query. Without understanding the dataset’s underlying structure, how can a user input a text-based query and then convert this text into semantic protocol and resource description framework query language (SPARQL) that deals with the resource description framework (RDF) knowledge base? The user may not know the structure and syntax of SPARQL, a formal query language and a sophisticated tool for the semantic web (SEW) and its vast and growing collection of interconnected open data repositories. As a result, this study examines various strategies for turning natural language into formal queries, their workings, and their results. In an Internet search engine from a single query, such as on Google, numerous matching documents are returned, with several related to the inquiry while others are not. Since a considerable percentage of the information retrieved is likely unrelated, sophisticated information retrieval systems based on SEW technologies, such as RDF and web ontology language (OWL), can help end users organize vast amounts of data to address this issue. This study reviews this research field and discusses two different approaches to show how users with no knowledge of the syntax of semantic web technologies deal with queries.

Diagnostic accuracy of ICD code versus discharge summary-based query for endocarditis cohort identification.

Studies of infective endocarditis (IE) have relied on International Classification of Disease (ICD) codes to identify cases, a method vulnerable to misclassification. Clinical narrative data could offer greater accuracy and richness to cohort identification. We evaluated two algorithms: 1.a standard query of ICD-9/10 billing codes, with or without procedure codes for echocardiogram and2.a text query of discharge summaries (DS) that selected on the term “endocarditis” in fields headed by “Discharge Diagnosis” or “Admission Diagnosis” or similar.Further coding extracted valve involved and organism responsible if present. All cases were chart reviewed using pre-specified criteria. Positive predictive value (PPV), sensitivity and specificity were calculated. The ICD-based query identified 612 individuals from July 2015 to July 2019 who had a hospital billing code for infective endocarditis; of these, 534 had an echocardiogram. The DS query identified 387 cases. PPV for the DS query was 84.5% (95% CI 80.6%, 87.8%) compared with 72.4% (95% CI 68.7%, 75.8%) for ICD only (P < .001) and 75.8% (95% CI 72.0%, 79.3%) for ICD + echo queries (P = .002). Sensitivity was 75.9% for DS query and 86.8% to 93.4% for ICD queries (P < .02 for these comparisons). Specificity was high for all queries >94%. The DS query also yielded valve data (prosthetic, tricuspid, aortic, etc) in 60% and microbiologic agent in 73% of identified cases with an accuracy of 94% and 90%, respectively when assessed by chart review. Compared with ICD-based queries, text-based queries of discharge summaries have the potential to improve precision of IE case ascertainment and extract key clinical variables.

693. Performance of ICD Code Versus Discharge Summary based Query for Endocarditis Cohort Identification

BackgroundStudies on infective endocarditis (IE) have relied on International Classification of Diseases (ICD) codes to identify cases but few have validated this method which may be prone to misclassification. Examination of clinical narrative data could offer greater accuracy and richness.MethodsWe evaluated two algorithms for IE identification from 7/1/2015 to 7/31/2019: (1) a standard query of ICD codes for IE (ICD-9: 424.9, 424.91, 424.99, 421.0, 421.1, 421.9, 112.81, 036.42 and ICD-10: I38, I39, I33, I33.9, B37.6 and A39.51) with or without procedure codes for echocardiogram (93303-93356) and (2) a key word, pattern-based text query of discharge summaries (DS) that selected on the term “endocarditis” in fields headed by “Discharge Diagnosis” or “Admission Diagnosis” or similar. Further coding extracted the nature and type of valve and the organism responsible for the IE if present in DS. All identified cases were chart reviewed using pre-specified criteria for true IE. Positive predictive value (PPV) was calculated as the total number of verified cases over the algorithm-selected cases. Sensitivity was the total number of algorithm-matched cases over a final list of 166 independently identified true IE cases from ID and Cardiology services. Specificity was defined using 119 pre-adjudicated non-cases minus the number of algorithm-matched cases over 119.ResultsThe ICD-based query identified 612 individuals from July 2015 to July 2019 who had a hospital billing code for infective endocarditis; of these, 534 also had an echocardiogram. The DS query identified 387 cases. PPV for the DS query was 84.5% (95% confidence interval [CI] 80.6%, 87.8%) compared with 72.4% (95% CI 68.7%, 75.8%) for ICD only and 75.8% (95% CI 72.0%, 79.3%) for ICD + echo queries. Sensitivity was 75.9% for the DS query and 86.8-93.4% for the ICD queries. Specificity was high for all queries >94%. The DS query also yielded valve data (prosthetic, tricuspid, pulmonic, aortic or mitral) in 60% and microbiologic data in 73% of identified cases with an accuracy of 94% and 90% respectively when assessed by chart review.Table 1. Test Characteristics of Three Electronic Health Record Queries for Infective Endocarditis ConclusionCompared to traditional ICD-based queries, text-based queries of discharge summaries have the potential to improve precision of IE case ascertainment and extract key clinical variables.Disclosures All Authors: No reported disclosures

Mapping the Knowledge of Dante Commentaries in the Digital Context: A Web Ontology Approach

AbstractWith digital repositories and databases available since the 1990s, Dante scholarship has always been at the forefront of the digital humanities and the digitization of medieval texts and manuscripts. However, the amount of information available about such aspects is imposing, and its location subject to the extreme dispersion of traditional scholarly publications: commentaries first but also academic journals, miscellanies, and so forth. Rather than being based on traditional word searches, a true advancement of knowledge needs to overcome the rigidity of text-based queries (and in-line markup embedded in text). Such paramount evolution is now made possible by the Semantic Web, an extension of the current web by description standards that help machines to understand and connect the information already available on the web. To achieve this, the latter is mapped using formal description and classification patterns, called ontologies. Ontologies are a key factor in managing meaningful search/data extraction, publishing relevant results on the web, search existing web resources, and offering answers to more sophisticated queries. Due to its vastness and complexity, Dante scholarship has calls for an ontology-based mapping, and specific tools have been designed to express the most difficult and articulate aspects of Dante’s literary production, such as its use of biblical, classical, and medieval sources. This paper aims to introduce the aims and scope of a new digital library of Dante commentaries, built according to the aforementioned standards and aiming to refine and extend the ontologies developed for Dante’s minor works to the more complex world of the Commedia.

COMPARATIVE ANALYSIS OF IMAGE RETRIEVAL TECHNIQUES IN CYBERSPACE

Purpose: With the popularity and remarkable usage of digital images in various domains, the existing image retrieval techniques need to be enhanced. The content-based image retrieval is playing a vital role to retrieve the requested data from the database available in cyberspace. CBIR from cyberspace is a popular and interesting research area nowadays for a better outcome. The searching and downloading of the requested images accurately based on meta-data from the cyberspace by using CBIR techniques is a challenging task. The purpose of this study is to explore the various image retrieval techniques for retrieving the data available in cyberspace. &#x0D; Methodology: Whenever a user wishes to retrieve an image from the web, using present search engines, a bunch of images is retrieved based on a user query. But, most of the resultant images are unrelated to the user query. Here, the user puts their text-based query in the web-based search engine and compute the related images and retrieval time.&#x0D; Main Findings: This study compares the accuracy and retrieval-time of the requested image. After the detailed analysis, the main finding is none of the used web-search engines viz. Flickr, Pixabay, Shutterstock, Bing, Everypixel, retrieved the accurate related images based on the entered query. &#x0D; Implications: This study is discussing and performs a comparative analysis of various content-based image retrieval techniques from cyberspace.&#x0D; Novelty of Study: Research community has been making efforts towards efficient retrieval of useful images from the web but this problem has not been solved and it still prevails as an open research challenge. This study makes some efforts to resolve this research challenge and perform a comparative analysis of the outcome of various web-search engines.

Young People's Online Help-Seeking and Mental Health Difficulties: Systematic Narrative Review.

BackgroundYoung people frequently make use of the internet as part of their day-to-day activities, and this has extended to their help-seeking behavior. Offline help-seeking is known to be impeded by a number of barriers including stigma and a preference for self-reliance. Online help-seeking may offer an additional domain where young people can seek help for mental health difficulties without being encumbered by these same barriers.ObjectiveThe objective of this systematic literature review was to examine young peoples’ online help-seeking behaviors for mental health concerns. It aimed to summarize young peoples’ experiences and identify benefits and limitations of online help-seeking for this age group. It also examined the theoretical perspectives that have been applied to understand online help-seeking.MethodsA systematic review of peer-reviewed research papers from the following major electronic databases was conducted: PsycINFO, Cumulative Index of Nursing and Allied Health Literature, PubMed, Cochrane Library, Association for Computing Machinery Digital Library, and Institute of Electrical and Electronics Engineers Xplore. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines were followed. The search was conducted in August 2017. The narrative synthesis approach to reviews was used to analyze the existing evidence to answer the review questions.ResultsOverall, 28 studies were included. The most common method of data collection was through the use of surveys. Study quality was moderate to strong. Text-based query via an internet search engine was the most commonly identified help-seeking approach. Social media, government or charity websites, live chat, instant messaging, and online communities were also used. Key benefits included anonymity and privacy, immediacy, ease of access, inclusivity, the ability to connect with others and share experiences, and a greater sense of control over the help-seeking journey. Online help-seeking has the potential to meet the needs of those with a preference for self-reliance or act as a gateway to further help-seeking. Barriers to help-seeking included a lack of mental health literacy, concerns about privacy and confidentiality, and uncertainty about the trustworthiness of online resources. Until now, there has been limited development and use of theoretical models to guide research on online help-seeking.ConclusionsApproaches to improving help-seeking by young people should consider the role of the internet and online resources as an adjunct to offline help-seeking. This review identifies opportunities and challenges in this space. It highlights the limited use of theoretical frameworks to help conceptualize online help-seeking. Self-determination theory and the help-seeking model provide promising starting points for the development of online help-seeking theories. This review discusses the use of these theories to conceptualize online help-seeking and identify key motivations and tensions that may arise when young people seek help online.

BUILDING ONTOLOGIES OVER RELATIONAL DATABASES

Relational Databases are typically created to fulfil the information requirements of a community of users generally belongs to a single organization. Data stored in these databases were typically accessed by using Structured Query Languages or through customized interfaces. With the popularity of the World Wide Web and the availability of large number of Relational Databases for public access there is a need for users to retrieve data from these databases by using a text-based queries, possibly by using the terms that they are familiar with. However, the inherent limitations of Structured Query Languages used to create and access data in relational Data Bases does not allow uses to access data by using text-based queries. Also, the terms used in queries should be limited to those used during the construction of the databases. This paper proposes an architecture to generated ontologies over relation databases and show how they could be enhanced semantically by using available domain-specific or top-level ontologies so that the data managed by the DBs can be accessed by using text-based queries. The feasibility of the proposed architecture was demonstrated by building a prototype system over a sample MySQL database.

An analysis of a discrete cosine transform (DCT)compression technique on low level features of image for image retrieval system

A digital image is basically formed together with metadata which describes the image such as information about the file (e.g. location captured, author, date, time and etc.), tags and keywords. These properties allow images to be stored accordingly to its categories in a database. Those images later can be retrieved from the system by running a text-based query which explained the characteristics of an image. Although retrieving by text-based query method is a common and widely used to find images in a very large database, this method however does not guarantee that the results returned is as described in searching query due to the fact that it is totally dependent on the accuracy of stated image properties. In order to improve the accuracy of the text-based retrieval method, a Content-Based Image Retrieval (CBIR) has been proposed as a complement to the standard method.

Omicseq: a web-based search engine for exploring omics datasets.

The development and application of high-throughput genomics technologies has resulted in massive quantities of diverse omics data that continue to accumulate rapidly. These rich datasets offer unprecedented and exciting opportunities to address long standing questions in biomedical research. However, our ability to explore and query the content of diverse omics data is very limited. Existing dataset search tools rely almost exclusively on the metadata. A text-based query for gene name(s) does not work well on datasets wherein the vast majority of their content is numeric. To overcome this barrier, we have developed Omicseq, a novel web-based platform that facilitates the easy interrogation of omics datasets holistically to improve ‘findability’ of relevant data. The core component of Omicseq is trackRank, a novel algorithm for ranking omics datasets that fully uses the numerical content of the dataset to determine relevance to the query entity. The Omicseq system is supported by a scalable and elastic, NoSQL database that hosts a large collection of processed omics datasets. In the front end, a simple, web-based interface allows users to enter queries and instantly receive search results as a list of ranked datasets deemed to be the most relevant. Omicseq is freely available at http://www.omicseq.org.

Inference of User Image-Search Goals and Personalization Using Click Through Log

Improving the image search engine relevance and user experience is very important to figure out user image search goals. When a user will enter a query to search an image, he should be displayed with relevant images. In proposed work, browsing history session information, bookmark data and visual information with image tags of user click through images or user feedback images are extracted. The session history is stored as click through log and the images are stored separately. This history and clicked and downloaded images by user is considered as implicit guidance, so that the personalized results can be presented to the user. From the browsing history, the URLs are visited for getting user domain keywords. By using these keywords and tags of images, user query specific topic mapping and query mapping is done. The proposed method performs Naive Bayesian classification on user clicked images to group them into relevant concepts. This classifier is tested on the images obtained as a result of user submitted, so that the user interesting images or goal images can be displayed as a result. A label wise clustering is used to display goal image results. The system is mainly for retrieving images using text-based queries. The main aim of the proposed work is an efficient image retrieval system to facilitates image search through user queries and improve user satisfaction by returning images that have a high probability to be downloaded by the user. Index Terms—Click through log, User Profiles, Goal images, Image search goals.

On the coupled use of signal and semantic concepts to bridge the semantic and user intention gaps for visual content retrieval

The effectiveness of image indexing and retrieval systems has been negatively impacted by both the semantic and user intention gaps. The first is related to the challenge of characterizing the visual semantic information through low-level extracted features (color, texture...) while the second highlights the difficulty for human users to convey their search intents using the traditional relevance feedback or query-by-example visual query mechanisms. We address both issues by highlighting vocabularies of visual concepts that are mapped to extracted low-level features through an automated learning paradigm. These are then instantiated within a semantic indexing and retrieval framework based on a Bayesian model considering the joint distribution of visual and semantic concepts. To address the user intention gap and enrich the expressiveness of the retrieval module, visual and semantic concepts can be coupled within text-based queries. We are therefore able to process both single-concept queries such as the state-of-the-art solutions but also topic-based queries, i.e. non-trivial queries involving multiple characterizations of the visual content. We evaluate our proposal in a precision/recall based evaluation framework on the IAPR-TC 12 benchmark dataset.

Investigating the precision of Web image search engines for popular and less popular entities

Image search is the second most frequently used search service on the Web. However, there are very few studies investigating any aspect of it. In this study, we investigate the precision of Web image search engines of Google and Bing for popular and less popular entities using text-based queries. Furthermore, we investigate four additional aspects of Web image search engines that have not been studied before. We used 60 different queries in total from three different domains for popular and less popular categories. We examined the relevancy of the top 100 images for each query. Our results indicate that image search is a solved problem for popular entities. They deliver 97% precision on the average for popular entities. However, precision values are much lower for less popular entities. For the top 100 results, average precision is 48% for Google and 33% for Bing. The most important problem seems to be the worst cases in which the precision can be less than 10%. The results show that significant improvement is needed to better identify relevant images for less popular entities. One of the main issues is the association problem. When a Web page has query words and multiple images, both Google and Bing are having difficulty determining the relevant images.

A Comparison of Methods for Assessing Situation Awareness in Current Day and Future Air Traffic Management Operations: Graphics-Based vs Text-Based Online Probe Systems

Abstract: Operator situation awareness can be measured by examining operator response time and accuracy to online queries or probes. We compared an existing, text-based query method with a new graphics-based method. The text-based method presented multiple-choice queries to air traffic controllers (ATCos) on a display next to the DSR. Responses were entered by selecting one of the response alternatives presented with the query. The graphics-based method presented the query along with a screen shot of ATCo’s current traffic on the DSR. The ATCo responded by touching the symbol of the aircraft that was the subject of the question. These methods were compared in a simulation involving student ATCos currently enrolled in an Aviation Sciences program.

A database of circadian and diel rhythmic gene expression in the yellow fever mosquito Aedes aegypti.

BackgroundThe mosquito species Aedes aegypti is the primary vector of many arboviral diseases, including dengue and yellow fevers, that are responsible for a large worldwide health burden. The biological rhythms of mosquitoes regulate many of the physiological processes and behaviors that influence the transmission of these diseases. For insight into the molecular basis of biological rhythms, diel and circadian gene expression profiling has been carried out for many species. To bring these resources to Aedes aegypti researchers, we used microarray technology to carry out a genome wide assessment of gene expression during the 24 hour light/dark (LD) cycle and during constant darkness (DD). The purpose of this report is to describe the methods, the validation of the results, and the organization of this database resource.DescriptionThe Aedes aegypti Circadian Database is a publicly accessible database that can be searched via a text-based query to visualize 44 hour temporal expression patterns of a given gene in Ae. aegypti heads under diel (observed under a 12 hour/12 hour LD cycle) and circadian (observed under DD) conditions. Profiles of gene expression under these conditions were assayed by Nimblegen 12-plex microarrays and rhythmicity was objectively assessed by the JTK_CYCLE algorithm. The output of the search is a graphical representation of the expression data along with computed period length, the time-of-day of gene expression peaks, and statistical determination for rhythmicity.ConclusionOur results show that at least 7.9% of the gene set present in the Aedes aegypti head are rhythmic under LD conditions and 6.7% can be considered circadian, oscillating under constant dark conditions. We present these results in the Aedes aegypti Circadian Database through Bioclock, a public website hosted by the University of Notre Dame at http://www.nd.edu/~bioclock/. This website allows searchable browsing of this quantitative gene expression information. The visualization allows for gene-by-gene comparison of transcript expression under both diel and circadian conditions, and the results are presented graphically in a plot profile of gene expression. The Ae. aegypti Circadian Database provides a community resource for observing diel and circadian fluctuations in gene expression across the Ae. aegypti genome.

Identifying Sign Language Videos in Video Sharing Sites

Video sharing sites enable members of the sign language community to record and share their knowledge, opinions, and worries on a wide range of topics. As a result, these sites have formative digital libraries of sign language content hidden within their large overall collections. This article explores the problem of locating these sign language (SL) videos and presents techniques for identifying SL videos in such collections. To determine the effectiveness of existing text-based search for locating these SL videos, a series of queries were issued to YouTube to locate SL videos on the top 10 news stories of 2011 according to Yahoo!. Overall precision for the first page of results (up to 20 results) was 42%. An approach for automatically detecting SL video is then presented. Five video features considered likely to be of value were developed using standard background modeling and face detection. The article compares the results of an SVM classifier when given all permutations of these five features. The results show that a measure of the symmetry of motion relative to the face position provided the best performance of any single feature. When tested against a challenging test collection that included many likely false positives, an SVM provided with all five features achieved 82% precision and 90% recall. In contrast, the text-based search (queries with the topic terms and “ASL” or “sign language”) returned a significant portion of non-SL content---nearly half of all videos found. By our estimates, the application of video-based filtering techniques such as the one proposed here would increase precision from 42% for text-based queries up to 75%.