Table 1_Establishment and preliminary application of object recognition system based on De

36 behavioral indicators across three categories—sniffing frequency, exploration duration, and novelty preference—were automatically quantified from video of mice. The dataset, created by Cenfei Zhou and last updated in April 2026, describes a system for assessing cognitive function in natural aging and elderly periodontitis mouse models. It compares results from a DeepLabCut-based tracking system against traditional visual inspection methods.

Use Cases

• Training machine learning models for fine-grained rodent behavior classification based on 5 tracked body landmarks.
• Comparing cognitive performance between aged and young mice based on quantified exploration frequency and duration.
• Investigating the link between inflammation (e.g., periodontitis) and cognitive decline using multidimensional behavioral metrics.
• Validating automated tracking systems against traditional manual scoring methods in novel object and object location recognition paradigms.

Strengths

• Quantifies 36 specific behavioral indicators across three defined categories.
• Uses dynamic distance thresholds (1 cm, 1.5 cm, 2 cm) for the nose tip to capture fine-grained exploration.
• Tracks five distinct mouse body landmarks for detailed behavioral subdivision.
• Provides comparative analysis between a DeepLabCut system and traditional visual inspection.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small (41.6 KB), suggesting it may contain summary results or a description rather than raw tracking data.

Provenance

Source

Cenfei Zhou via figshare

Collection Method

Data likely generated from video recordings of mice in custom arenas, analyzed with a trained DeepLabCut algorithm.

Freshness

Last updated 2026-04-21 05:35:20; freshness should be verified.