Search for: All records

In an era of information overload, research writing, particularly literature review composition, has become increasingly burdensome due to the sheer volume of scholarly publications released each year. This paper introduces {\em WriteAssist}, a novel standalone authoring system that helps researchers efficiently generate literature review sections. Given the title and abstract of a work-in-progress manuscript, WriteAssist automatically retrieves relevant and recent peer-reviewed articles, highlighting portions that offer supporting or contrasting perspectives. A key innovation lies in its personalized recommendation engine, which tailors results based on the user's prior publications and research profile, enabling context-aware synthesis. We position WriteAssist within the landscape of intelligent writing assistants, academic search platforms, and personalized recommender systems, and we detail its architecture -- integrating natural language processing and user modeling to streamline academic writing. The system represents a significant step toward alleviating cognitive overload in scholarly composition and offers a blueprint for smarter, adaptive tools in academic research support. 

Scientific workflows are pivotal for managing complex computational tasks, including data analysis, processing, simulation, and visualization. However, their design and administration typically demand substantial programming expertise, limiting access for domain scientists. Many such workflow systems also lack real-time execution tracking, and streamlined data integration capabilities, hindering efficiency and repeatability in scientific experimentation. In response, we introduce VisFlow 2.0, a next-generation platform derived from the original VisFlow. We compare VisFlow 2.0 to traditional alternatives through a well-studied computational pipeline, highlighting its usability, flexibility, and effectiveness, especially for non-expert users. 

A vast proportion of scientific data remains locked behind dynamic web interfaces, often called the deep web—inaccessible to conventional search engines and standard crawlers. This gap between data availability and machine usability hampers the goals of open science and automation. While registries like FAIRsharing offer structured metadata describing data standards, repositories, and policies aligned with the FAIR (Findable, Accessible, Interoperable, and Reusable) principles, they do not enable seamless, programmatic access to the underlying datasets. We present FAIRFind, a system designed to bridge this accessibility gap. FAIRFind autonomously discovers, interprets, and operationalizes access paths to biological databases on the deep web, regardless of their FAIR compliance. Central to our approach is the Deep Web Communication Protocol (DWCP), a resource description language that represents web forms, HyperText Markup Language (HTML) tables, and file-based data interfaces in a machine-actionable format. Leveraging large language models (LLMs), FAIRFind combines a specialized deep web crawler and web-form comprehension engine to transform passive web metadata into executable workflows. By indexing and embedding these workflows, FAIRFind enables natural language querying over diverse biological data sources and returns structured, source-resolved results. Evaluation across multiple open-source LLMs and database types demonstrates over 90% success in structured data extraction and high semantic retrieval accuracy. FAIRFind advances existing registries by turning linked resources from static references into actionable endpoints, laying a foundation for intelligent, autonomous data discovery across scientific domains. 

The discovery of functional dye materials with superior optical properties is crucial for advancing technologies in biomedical imaging, organic photovoltaics, and quantum information systems. Recent advancements highlight the need to accelerate this discovery process by integrating computational strategies with experimental methods. In this regard, we have employed a computational approach to explore the latent space of dye materials, utilizing swarm optimization techniques to efficiently navigate complex chemical spaces and identify optimal values of molecular properties using machine learning methods based on target properties, such as high extinction coefficients ($$\varepsilon$$). The latent space based evaluation outperformed all available features of a domain. This approach enhances inverse material design by systematically correlating molecular parameters with desired optical characteristics by implementing VAEs. In this process, by defining target properties as inputs, the model effectively determines the key molecular features necessary for engineering high-performance dye compounds. 

A brain tumor is an abnormal growth in the brain that disrupts its functionality and poses a significant threat to human life by damaging neurons. Early detection and classification of brain tumors are crucial to prevent complications and maintain good health. Recent advancements in deep learning techniques have shown immense potential in image classification and segmentation for tumor identification and classification. In this study, we present a platform, BrainView, for detection, and segmentation of brain tumors from Magnetic Resonance Images (MRI) using deep learning. We utilized EfficientNetB7 pre-trained model to design our proposed DeepBrainNet classification model for analyzing brain MRI images to classify its type. We also proposed a EfficinetNetB7 based image segmentation model, called the EffB7-UNet, for tumor localization. Experimental results show significantly high classification (99.96%) and segmentation (92.734%) accuracies for our proposed models. Finally, we discuss the contours of a cloud application for BrainView using Flask and Flutter to help researchers and clinicians use our machine learning models online for research purposes. 

As large language models (LLMs) continue to evolve, their capacity to replace humans as their surrogates is also improving. As increasing numbers of intelligent tutoring systems (ITSs) are embracing the integration of LLMs for digital tutoring, questions are arising as to how effective they are and if their hallucinatory behaviors diminish their perceived advantages. One critical question that is seldom asked if the availability, plurality, and relative weaknesses in the reasoning process of LLMs are contributing to the much discussed digital divide and equity and fairness in online learning. In this paper, we present an experiment with database design theory assignments and demonstrate that while their capacity to reason logically is improving, LLMs are still prone to serious errors. We demonstrate that in online learning and in the absence of a human instructor, LLMs could introduce inequity in the form of “wrongful” tutoring that could be devastatingly harmful for learners, which we call ignorant bias, in increasingly popular digital learning. We also show that significant challenges remain for STEM subjects, especially for subjects for which sound and free online tutoring systems exist. Based on the set of use cases, we formulate a possible direction for an effective ITS for online database learning classes of the future. 

Biologists often set out to find relevant data in an ever-changing landscape of interesting databases. While leading journals publish descriptions of databases, they are usually not recent and do not frequently update the list that discards defunct or poor-quality databases. These indices usually include databases that are proactively requested to be included by their authors. The challenge for individual biologists, then, is to discover, explore, and select databases of interest from a large unorganized collection and effectively use them in their analysis without too large of an investment. The advocation of the FAIR data principle to improve searching, finding, accessing, and inter-operating among these diverse information sources in order to increase usability is proving to be a difficult proposition and consequently, a large number of data sources are not FAIR-compliant. Since linked open data do not guarantee FAIRness, biologists are now left to individually search for information in open networks. In this paper, we propose SoDa, for intelligent data foraging on the internet by biologists. SoDa helps biologists to discover resources based on analysis requirements and generate resource access plans, as well as storing cleaned data and knowledge for community use. SoDa includes a natural language-powered resource discovery tool, a tool to retrieve data from remote databases, organize and store collected data, query stored data, and seek help from the community when things do not work as anticipated. A secondary search index is also supported for community members to find archived information in a convenient way to enable its reuse. The features supported in SoDa endows biologists with data integration capabilities over arbitrary linked open databases and construct powerful computational pipelines using them, capabilities that are not supported in most contemporary biological workflow systems, such as Taverna or Galaxy. 

Biology today is heavily data-driven and knowledge-centric that are stored across the linked open web in numerous heterogeneous deep web databases. To improve searching, finding, accessing, and inter-operating among these diverse information sources to increase usability, the FAIR data principle has been proposed. Unfortunately, FAIR compliance is extremely low and linked open data does not guarantee FAIRness, leaving biologists on a solo hunt for information on the open network. In this paper, we propose {\em SoDa}, for intelligent data foraging on the internet. SoDa helps biologists discover resources based on analysis requirements, generate resource access plans, and store cleaned data and knowledge for community use. A secondary search index is also supported for community members to find archived information conveniently. 

In a programmer's pursuit of using or creating new programming languages, finding errors in the syntax of code can present many issues. Languages with little to no documentation and incomprehensible exception handling and reports are frustrating to work with and can create confusion when trying to locate where in the code the program has faulted. In this paper we present {\em CodeBlock}, a parser generator and syntax checker for arbitrary programming languages. CodeBlock is a block based grammar builder for any programming language that constructs a parsing expression grammar for the language based on user built expressions. This grammar can then be used within the CodeBlock website or in the CodeBlock Node.JS application to test the syntax of either written code, or files containing code in the language, reporting comprehensible error messages if errors in syntax are found. Our eventual goal is to incorporate CodeBlock into a compiler design tutoring system, called {\em CompiTS}, in which it will play a central role in teaching students how to design new programming languages and test the effectiveness of the new language using rapid prototyping and a translational approach to implementation. This is an emerging research, and in this paper, we only focus on the syntax checking component of the CompiTS system. 

Mastering SQL is a key data science competence. While most large language models are able to translate natural language queries to SQL, their ability to tutor learners and authentically assess student assignments are at the least fragile. In this paper, we introduce {\em ExplainS} as an experimental prototype. In this web-based system, we augment Gemini with abstract syntax tree (AST) to enhance Gemini's semantic analysis power to be able to assist and tutor students better. This edition of ExplainS provides a collection of exercises with varying difficulty levels, covering core SQL concepts. Users interact with a dynamic schema display, and their queries are validated against carefully crafted solutions. To provide context-aware personalized feedback, ExplainS leverages Gemini and the SQLglot library to analyze query AST differences between user queries and correct solutions, pinpointing the root cause of errors. This emerging research is part of a wider Data Science effort, and in this paper, we only focus on the meaningful feedback generation component of the ExplainS system.