Search for: All records

Abstract Illegal trade in sharks and rays continues to undermine global conservation efforts, with enforcement often hampered by the inability to identify products to the species level. Here, we present a portable, cost-effective High-Resolution melt (HRM) assay for rapid DNA-based identification of elasmobranch species in trade. Using a reference library of 669 vouchered tissue samples collected from field operations and international market surveys, we validated the assay’s capacity to accurately differentiate at least 55 shark and ray species based on melt curve profiles, including 38 species listed under the Convention on International Trade in Endangered Species of Wild Fauna and Flora. Automated image classification enabled high-throughput identification with 99.2% accuracy. The assay yields results within two hours at a per-sample cost of $1.50, and is compatible with portable qPCR platforms, making it suitable for on-site applications. This approach represents a scalable molecular enforcement tool that can empower local authorities to monitor trade more effectively, support compliance with international regulations, and enhance global efforts to combat wildlife trafficking. 

The effectiveness of feedback in enhancing learning outcomes is well documented within Educational Data Mining (EDM). Various prior research have explored methodologies to enhance the effectiveness of feedback to students in various ways. Recent developments in Large Language Models (LLMs) have extended their utility in enhancing automated feedback systems. This study aims to explore the potential of LLMs in facilitating automated feedback in math education in the form of numeric assessment scores. We examine the effectiveness of LLMs in evaluating student responses and scoring the responses by comparing 3 different models: Llama, SBERT-Canberra, and GPT4 model. The evaluation requires the model to provide a quantitative score on the student's responses to open-ended math problems. We employ Mistral, a version of Llama catered to math, and fine-tune this model for evaluating student responses by leveraging a dataset of student responses and teacher-provided scores for middle-school math problems. A similar approach was taken for training the SBERT-Canberra model, while the GPT4 model used a zero-shot learning approach. We evaluate and compare the models' performance in scoring accuracy. This study aims to further the ongoing development of automated assessment and feedback systems and outline potential future directions for leveraging generative LLMs in building automated feedback systems.