arXiv subjects

Kurmanbek Kaiyrbekov

Publications and source records attributed to Kurmanbek Kaiyrbekov.

3 recordsLinked to original sources

arXiv2025

Automated Survey Collection with LLM-based Conversational Agents

Objective: Traditional phone-based surveys are among the most accessible and widely used methods to collect biomedical and healthcare data, however, they are often costly, labor intensive, and difficult to scale effectively. To overcome these limitations, we propose an end-to-end survey collection framework driven by conversational Large Language Models (LLMs). Materials and Methods: Our framework consists of a researcher responsible for designing the survey and recruiting participants, a conversational phone agent powered by an LLM that calls participants and administers the survey, a second LLM (GPT-4o) that analyzes the conversation transcripts generated during the surveys, and a database for storing and organizing the results. To test our framework, we recruited 8 participants consisting of 5 native and 3 non-native english speakers and administered 40 surveys. We evaluated the correctness of LLM-generated conversation transcripts, accuracy of survey responses inferred by GPT-4o and overall participant experience. Results: Survey responses were successfully extracted by GPT-4o from conversation transcripts with an average accuracy of 98% despite transcripts exhibiting an average per-line word error rate of 7.7%. While participants noted occasional errors made by the conversational LLM agent, they reported that the agent effectively conveyed the purpose of the survey, demonstrated good comprehension, and maintained an engaging interaction. Conclusions: Our study highlights the potential of LLM agents in conducting and analyzing phone surveys for healthcare applications. By reducing the workload on human interviewers and offering a scalable solution, this approach paves the way for real-world, end-to-end AI-powered phone survey collection systems.

cs.CL↗

arXiv2024

Does nematic order allow groups of elongated cells to sense electric fields better?

Collective response to external directional cues like electric fields plays a pivotal role in processes such as tissue development, regeneration, and wound healing. In this study we focus on the impact of anisotropy in cell shape and local cell alignment on the collective response to electric fields. We model elongated cells that have a different accuracy sensing the field depending on their orientation with respect to the field. Elongated cells often line up with their long axes in the same direction - "nematic order" - does this help the group of cells sense the field more accurately? We use simulations of a simple model to show that if cells orient themselves perpendicular to their average velocity, alignment of a cell's long axis to its nearest neighbors' orientation can enhance the directional response to electric fields. However, for cells to benefit from aligning, their accuracy of sensing must be strongly dependent on cell orientation. We also show that cell-cell adhesion modulates the accuracy of cells in the group.

q-bio.CB↗

arXiv2019

Stroke-based sketched symbol reconstruction and segmentation

Hand-drawn objects usually consist of multiple semantically meaningful parts. For example, a stick figure consists of a head, a torso, and pairs of legs and arms. Efficient and accurate identification of these subparts promises to significantly improve algorithms for stylization, deformation, morphing and animation of 2D drawings. In this paper, we propose a neural network model that segments symbols into stroke-level components. Our segmentation framework has two main elements: a fixed feature extractor and a Multilayer Perceptron (MLP) network that identifies a component based on the feature. As the feature extractor we utilize an encoder of a stroke-rnn, which is our newly proposed generative Variational Auto-Encoder (VAE) model that reconstructs symbols on a stroke by stroke basis. Experiments show that a single encoder could be reused for segmenting multiple categories of sketched symbols with negligible effects on segmentation accuracies. Our segmentation scores surpass existing methodologies on an available small state of the art dataset. Moreover, extensive evaluations on our newly annotated big dataset demonstrate that our framework obtains significantly better accuracies as compared to baseline models. We release the dataset to the community.

cs.GR↗