pith. sign in

arxiv: 2604.16307 · v1 · submitted 2026-01-26 · 💻 cs.MM · cs.HC

Multimodal Digital Sensing of Early-Life Laying Hens: A Pilot Study Integrating Thermal, Acoustic, Optical-Flow and Environmental Data

Yashan Dhaliwal , Daniel Essien , Suresh Neethirajan This is my paper

Pith reviewed 2026-05-16 11:00 UTC · model grok-4.3

classification 💻 cs.MM cs.HC
keywords multimodal sensinglaying henspoultry welfarethermal imagingacoustic monitoringoptical flowprecision livestock farmingearly-life development
0
0 comments X

The pith

A combination of thermal, acoustic, and movement sensors can track age-related developmental patterns in young laying hens from hatch to 20 weeks.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper tests a multimodal sensing approach that combines thermal imaging, audio recordings, optical-flow video analysis, and environmental data to follow physiological and behavioral changes in laying hens during their first 20 weeks. Measurements showed rising and stabilizing surface temperatures, systematic shifts in sound features, and a clear drop in how much the birds reacted to people entering the room as they aged. Within each sensor type the patterns held together strongly, but the different types stayed mostly independent except for some links with humidity. The work aims to replace subjective welfare checks with parallel, objective data streams that could fit into precision poultry systems.

Core claim

A multimodal sensing framework integrating thermal imaging, acoustic recording, optical-flow video analysis, and environmental monitoring can characterize physiological and behavioural development in early-life laying hens, as shown by age-related increases in peripheral temperatures, systematic changes in acoustic features, declining reactivity to caretaker presence, and high within-modality consistency alongside domain independence in the aggregated trajectories.

What carries the argument

The multimodal sensing framework that collects and aggregates weekly features from thermal surface temperatures, acoustic spectral descriptors, optical-flow movement responses to caretaker entry, and ambient environmental conditions.

If this is right

  • Foot surface temperature exhibits a strong developmental effect across weeks.
  • Acoustic features change systematically with vocal maturation.
  • Optical-flow reactivity to caretaker presence declines markedly after week 10.
  • Multimodal trajectories maintain high consistency within each sensing domain.
  • Humidity shows selective correlation with acoustic features while thermal, acoustic, and behavioural domains remain largely independent.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • If scaled, the same sensor combination could flag deviations from normal developmental trajectories before visible health problems appear.
  • The observed independence across sensor domains implies that single-modality monitoring would miss part of the overall picture.
  • Direct correlation of these baseline patterns with later production metrics or health events would strengthen their value for on-farm decisions.

Load-bearing premise

That detailed measurements taken in one representative room will apply to the other rooms and that the observed temperature, sound, and movement shifts directly reflect meaningful welfare states rather than routine growth.

What would settle it

Repeating the same weekly feature extraction across multiple independent flocks and rooms would fail to produce the same age-related temperature increases, acoustic shifts, or reactivity decline, or the sensor readings would show no correlation with independent welfare indicators such as mortality or stress behaviors.

Figures

Figures reproduced from arXiv: 2604.16307 by Daniel Essien, Suresh Neethirajan, Yashan Dhaliwal.

Figure 4
Figure 4. Figure 4: Environmental monitoring apparatus. Portable multi [PITH_FULL_IMAGE:figures/full_fig_p008_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Ambient environmental conditions during rearing. Daily morning (08:00) and afternoon (16:00) temperature and relative humidity recorded in Room 1 from June to October. Seasonal variation is evident, with higher temperatures in early summer and more stable conditions in August. Environmental context informed interpretation of multimodal developmental trajectories. 3.2 Thermoregulatory maturation: quantitati… view at source ↗
Figure 6
Figure 6. Figure 6: Thermoregulatory development across early life. Weekly mean head and foot surface [PITH_FULL_IMAGE:figures/full_fig_p013_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Acoustic feature trajectories across development. Z [PITH_FULL_IMAGE:figures/full_fig_p016_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Behavioural response to caretaker entry. Weekly mean optical flow magnitude before, during, [PITH_FULL_IMAGE:figures/full_fig_p018_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Integrated multimodal developmental trajectories. Z [PITH_FULL_IMAGE:figures/full_fig_p019_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Cross-modal correlation structure. Heatmap of Pearson correlation coefficients between thermal, acoustic, behavioural (optical flow), and environmental features across weeks 5–20. Asterisks indicate significance after false discovery rate correction (q < 0.05). Strong within-modality correlations demonstrate internal consistency, while selective cross-modal associations highlight partially independent dev… view at source ↗
Figure 11
Figure 11. Figure 11: Conceptual synthesis of multimodal development in laying hens. Schematic representation of [PITH_FULL_IMAGE:figures/full_fig_p023_11.png] view at source ↗
read the original abstract

Early-life development strongly influences long-term welfare in laying hens, yet monitoring remains limited by subjective assessment and single-modality tools. This pilot study evaluated the feasibility of a multimodal sensing framework integrating thermal imaging, acoustic recording, optical-flow-based video analysis, and environmental monitoring to characterize physiological and behavioural development from hatch to 20 weeks. One hundred fifty Lohmann LSL-Lite chicks were housed across five controlled rooms; thermal and environmental data were collected system-wide, while detailed audio and video analyses focused on one representative room. Weekly aggregated features included head and foot surface temperatures, acoustic spectral descriptors, optical-flow movement responses to caretaker entry, and ambient conditions. Thermal imaging showed age-related increases and stabilization of peripheral temperatures, with foot temperature exhibiting a strong developmental effect (eta squared = 0.51). Acoustic features changed systematically across weeks (p < 0.001), consistent with vocal maturation. Optical-flow analysis revealed pronounced early reactivity to caretaker presence that declined with age (weeks 5 to 10 versus 11 to 20: t = 28.12, p = 0.00126). Z-score-normalized multimodal trajectories and correlation analysis (false discovery rate q < 0.05) showed strong within-modality consistency (r = 0.85 to 0.96) and selective associations between humidity and acoustic features (r = 0.65 to 0.70), while thermal, acoustic, and behavioural domains remained largely independent. This pilot establishes baseline multimodal developmental patterns and supports parallel sensing for welfare-relevant monitoring in precision poultry farming.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The manuscript reports a pilot study on 150 Lohmann LSL-Lite chicks housed in five rooms, using system-wide thermal imaging and environmental sensors together with detailed acoustic spectral descriptors and optical-flow video analysis restricted to one representative room. It presents age-related developmental trajectories from hatch to 20 weeks, including a strong effect on foot surface temperature (η² = 0.51), systematic weekly changes in acoustic features (p < 0.001), a decline in optical-flow reactivity to caretaker entry (t = 28.12, p = 0.00126), and z-score-normalized multimodal correlations showing high within-modality consistency (r = 0.85–0.96) but largely independent domains with selective humidity-acoustic links (r = 0.65–0.70). The central claim is that these data establish baseline multimodal patterns supporting parallel sensing for welfare monitoring in precision poultry farming.

Significance. If the reported statistical patterns hold, the work supplies concrete, reproducible baselines (η², t-statistics, FDR-controlled correlations) derived directly from raw sensor streams without model fitting or circular derivations. The multimodal integration and explicit effect-size reporting constitute a useful reference for computational sensing frameworks in animal welfare, particularly the demonstration of early reactivity decline and peripheral temperature stabilization.

major comments (2)
  1. [Methods] Methods section on sensor deployment and analysis scope: acoustic spectral descriptors and optical-flow features were extracted from only one of the five rooms, while thermal and environmental data were collected system-wide. The headline results (acoustic p < 0.001, optical-flow t = 28.12) therefore rest on a single-room sample with no reported mixed-effects model, room-as-factor test, or inter-room consistency check. This directly limits the strength of the generalizability claim for baseline patterns in the abstract and discussion.
  2. [Results] Results section on multimodal trajectories and correlation analysis: the reported domain independence and humidity-acoustic associations (r = 0.65–0.70, FDR q < 0.05) combine system-wide thermal data with single-room audio/video data. Without room-effect modeling, it is unclear whether the observed independence and selective correlations are robust to micro-environmental variation across rooms.
minor comments (2)
  1. [Abstract] Abstract: the selection criteria for the 'representative room' are not stated; adding a brief clause on how the room was chosen would improve transparency.
  2. Figure captions and results text: z-score normalization procedure and exact weekly sample sizes per modality should be stated explicitly to allow direct replication of the aggregated features.

Simulated Author's Rebuttal

2 responses · 1 unresolved

We thank the referee for the constructive comments on the scope and generalizability of our pilot study. We address each major point below, acknowledging the single-room limitation for acoustic and optical-flow data, and have revised the manuscript to clarify this while preserving the reported baselines.

read point-by-point responses

  1. Referee: [Methods] Methods section on sensor deployment and analysis scope: acoustic spectral descriptors and optical-flow features were extracted from only one of the five rooms, while thermal and environmental data were collected system-wide. The headline results (acoustic p < 0.001, optical-flow t = 28.12) therefore rest on a single-room sample with no reported mixed-effects model, room-as-factor test, or inter-room consistency check. This directly limits the strength of the generalizability claim for baseline patterns in the abstract and discussion.

    Authors: We agree this is a key limitation of the pilot design, driven by computational and storage constraints for full audio/video processing. We have revised the abstract to specify that acoustic and optical-flow results derive from the representative room and updated the discussion to frame these as initial developmental baselines rather than fully generalizable across rooms. Mixed-effects models with room as a factor cannot be applied to the single-room modalities, but we have added an explicit caveat and recommendation for multi-room validation in future studies. revision: partial

  2. Referee: [Results] Results section on multimodal trajectories and correlation analysis: the reported domain independence and humidity-acoustic associations (r = 0.65–0.70, FDR q < 0.05) combine system-wide thermal data with single-room audio/video data. Without room-effect modeling, it is unclear whether the observed independence and selective correlations are robust to micro-environmental variation across rooms.

    Authors: The correlations were computed on aligned z-score-normalized features from the available streams. We have clarified in the results that acoustic-related associations reflect the representative room aligned to system-wide environmental data and added discussion of potential micro-environmental variation as a limitation. Separate within-modality checks for thermal data across rooms will be noted where feasible, but full cross-room modeling for all domains requires expanded data collection. revision: partial

standing simulated objections not resolved
  • Inter-room consistency checks and room-as-factor tests cannot be performed for acoustic and optical-flow features, as these were collected from only one room in the pilot.

Circularity Check

0 steps flagged

No circularity: results are direct empirical outputs from sensor data and standard statistical tests with no derivations or fitted predictions

full rationale

The manuscript describes a pilot observational study that collects raw multimodal sensor streams (thermal imaging, acoustic recordings, optical-flow video, environmental logs), aggregates weekly features, and applies off-the-shelf statistical procedures (eta-squared, ANOVA-style week effects, t-tests, Pearson correlations with FDR). No equations, models, or parameters are fitted and then reused to 'predict' the same quantities; no self-citations supply load-bearing uniqueness theorems or ansatzes; no renaming of known results occurs. The single-room restriction on audio/video analysis is a sampling limitation that affects external validity but does not create any self-referential loop in the reported statistics. The derivation chain is therefore self-contained and non-circular.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The study rests on empirical data collection and conventional statistical procedures without introducing fitted parameters, new physical entities, or non-standard axioms.

axioms (1)
  • standard math Standard assumptions of ANOVA, t-tests, and correlation analysis (normality, independence, and appropriate multiple-testing correction) hold for the collected data.
    Invoked by the reporting of eta squared, p-values, t-statistics, and FDR-corrected correlations.

pith-pipeline@v0.9.0 · 5602 in / 1232 out tokens · 31644 ms · 2026-05-16T11:00:05.999967+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

38 extracted references · 38 canonical work pages

  1. [1]

    Influence of age, time of day, and environmental changes on vocalization patterns in broiler chickens

    de Carvalho PS, Grzywalski T, Buyse K, Thomas P, Carvalho CL, Khan I, et al. Influence of age, time of day, and environmental changes on vocalization patterns in broiler chickens. Poultry Science. 2025;104(8):105298. https://doi.org/10.1016/j.psj.2025.105298

    work page doi:10.1016/j.psj.2025.105298 2025

  2. [2]

    Optimizing poultry production through advanced monitoring and control systems

    George AS, George ASH. Optimizing poultry production through advanced monitoring and control systems. Partners Universal International Innovation Journal. 2023;1(5):77 -97. https://doi.org/10.5281/zenodo.10050352

    work page doi:10.5281/zenodo.10050352 2023

  3. [4]

    Rearing laying hens: Early environmental complexity and genetic strain have life-long effects on keel bone size and fractures

    Rentsch AK, Aingkaran V , Ross E, Widowski TM. Rearing laying hens: Early environmental complexity and genetic strain have life-long effects on keel bone size and fractures. Poultry Science. 2024;103(12):104481. https://doi.org/10.3389/fvets.2022.1105653

    work page doi:10.3389/fvets.2022.1105653 2024

  4. [5]

    Adapting a Large -Scale Transformer Model to Decode Chicken V ocalizations: A Non -Invasive AI Approach to Poultry Welfare

    Neethirajan S. Adapting a Large -Scale Transformer Model to Decode Chicken V ocalizations: A Non -Invasive AI Approach to Poultry Welfare. AI. 2025;6(4):65. https://doi.org/10.3390/ai6040065

    work page doi:10.3390/ai6040065 2025

  5. [6]

    Environmental change or choice during early rearing improves behavioural adaptability in laying hen chicks

    Skånberg L, Newberry RC, Estevez I, Keeling LJ. Environmental change or choice during early rearing improves behavioural adaptability in laying hen chicks. Scientific Reports. 2023;13(1):6178. https://doi.org/10.1038/s41598-023-33212-0

    work page doi:10.1038/s41598-023-33212-0 2023

  6. [7]

    Early life environment affects behavior, welfare, gut microbiome composition, and diversity in broiler chickens

    De Jong IC, Schokker D, Gunnink H, Van Wijhe M, Rebel JM. Early life environment affects behavior, welfare, gut microbiome composition, and diversity in broiler chickens. Frontiers in Veterinary Science. 2022;9:977359. https://doi.org/10.3389/fvets.2022.977359

    work page doi:10.3389/fvets.2022.977359 2022

  7. [8]

    Farm environmental enrichments improve the welfare of layer chicks and pullets: A comprehensive review

    Xu D, Shu G, Liu Y , Qin P, Zheng Y , Tian Y , et al. Farm environmental enrichments improve the welfare of layer chicks and pullets: A comprehensive review. Animals. 2022;12(19):2610. https://doi.org/10.3390/ani12192610

    work page doi:10.3390/ani12192610 2022

  8. [9]

    Assessment of Welfare Problems in Broilers: Focus on Musculoskeletal Problems Associated with Their Rapid Growth

    Kwon BY , Park J, Kim DH, Lee KW. Assessment of Welfare Problems in Broilers: Focus on Musculoskeletal Problems Associated with Their Rapid Growth. Animals (Basel). 2024;14(7). https://doi.org/10.3390/ani14071116

    work page doi:10.3390/ani14071116 2024

  9. [10]

    Reliability, practicability and farmers’ acceptance of an animal welfare assessment protocol for broiler chickens and turkeys

    Michaelis S, Gieseke D, Knierim U. Reliability, practicability and farmers’ acceptance of an animal welfare assessment protocol for broiler chickens and turkeys. Poultry Science. 2024;103(10):103900. https://doi.org/10.1016/j.psj.2024.103900

    work page doi:10.1016/j.psj.2024.103900 2024

  10. [11]

    A peep into the future: artificial intelligence for on - farm poultry welfare monitoring

    Ajibola G, Kilders V , Erasmus MA. A peep into the future: artificial intelligence for on - farm poultry welfare monitoring. Animal Frontiers. 2024;14(6):72 -5. https://doi.org/10.1093/af/vfae031

    work page doi:10.1093/af/vfae031 2024

  11. [12]

    Lin X, Zhu W, Liu L, Zhou Z. Decoding Laying Hen Behavior and Physiological Status through Acoustic Biomarkers: Temporal Patterns, Rooster -Hen V ocalization Identification in Group Housing, and Environmental Adaptation. Poultry Science. 2025:105697. https://doi.org/10.1016/j.psj.2025.105697

    work page doi:10.1016/j.psj.2025.105697 2025

  12. [13]

    Precision livestock farming technology: applications and challenges of animal welfare and climate change

    Papakonstantinou GI, V oulgarakis N, Terzidou G, Fotos L, Giamouri E, Papatsiros VG. Precision livestock farming technology: applications and challenges of animal welfare and climate change. Agriculture. 2024;14(4):620. https://doi.org/10.3390/agriculture14040620

    work page doi:10.3390/agriculture14040620 2024

  13. [14]

    Precision livestock farming: What does it contain and what are the perspectives? Animals

    Kleen JL, Guatteo R. Precision livestock farming: What does it contain and what are the perspectives? Animals. 2023;13(5):779. https://doi.org/10.3390/ani13050779

    work page doi:10.3390/ani13050779 2023

  14. [15]

    Emerging precision management methods in poultry sector

    Olejnik K, Popiela E, Opaliński S. Emerging precision management methods in poultry sector. Agriculture. 2022;12(5):718. https://doi.org/10.3390/agriculture12050718 28

    work page doi:10.3390/agriculture12050718 2022

  15. [16]

    A computer vision approach to monitor activity in commercial broiler chickens using trajectory - based clustering analysis

    Campbell M, Miller P, Díaz -Chito K, Hong X, McLaughlin N, Parvinzamir F, et al. A computer vision approach to monitor activity in commercial broiler chickens using trajectory - based clustering analysis. Computers and Electronics in Agriculture. 2024;217:10 8591. https://doi.org/10.1016/j.compag.2023.108591

    work page doi:10.1016/j.compag.2023.108591 2024

  16. [17]

    A review on computer vision systems in monitoring of poultry: A welfare perspective

    Okinda C, Nyalala I, Korohou T, Okinda C, Wang J, Achieng T, et al. A review on computer vision systems in monitoring of poultry: A welfare perspective. Artificial Intelligence in Agriculture. 2020;4:184-208. https://doi.org/10.1016/j.aiia.2020.09.002

    work page doi:10.1016/j.aiia.2020.09.002 2020

  17. [18]

    Rethinking Poultry Welfare —Integrating Behavioral Science and Digital Innovations for Enhanced Animal Well -Being

    Neethirajan S. Rethinking Poultry Welfare —Integrating Behavioral Science and Digital Innovations for Enhanced Animal Well -Being. Poultry. 2025;4(2):20. https://doi.org/10.3390/poultry4020020

    work page doi:10.3390/poultry4020020 2025

  18. [19]

    A systematic review linking welfare and automated analysis of acoustic signals in broiler chickens and layers

    Soster P, Devos P, Smets R, Tuyttens FA, Andretta I, Buyse K, et al. A systematic review linking welfare and automated analysis of acoustic signals in broiler chickens and layers. World's Poultry Science Journal. 2025;81(4):1049-80. https://doi.org/10.1080/00439339.2025.2543042

    work page doi:10.1080/00439339.2025.2543042 2025

  19. [20]

    Acoustic based chicken health monitoring in smart poultry farms

    Bhandekar A, Udutalapally V , Das D, editors. Acoustic based chicken health monitoring in smart poultry farms. 2023 IEEE International Symposium on Smart Electronic Systems (iSES); 2023: IEEE. http://doi.org/10.1109/iSES58672.2023.00054

    work page doi:10.1109/ises58672.2023.00054 2023

  20. [21]

    Systematic Review and Meta -Analysis of Thermal Stress Assessment in Poultry Using Infrared Thermography in Specific Body Areas

    Hernández-Sánchez RC, Martínez-Castañeda FE, Domínguez-Olvera DA, Trujillo-Ortega ME, Díaz -Sánchez VM, Sánchez -Ramírez E, et al. Systematic Review and Meta -Analysis of Thermal Stress Assessment in Poultry Using Infrared Thermography in Specific Body Areas . Animals. 2024;14(22):3171. https://doi.org/10.3390/ani14223171

    work page doi:10.3390/ani14223171 2024

  21. [22]

    YOLO-based model for automatic detection of broiler pathological phenomena through visual and thermal images in intensive poultry houses

    Elmessery WM, Gutiérrez J, Abd El-Wahhab GG, Elkhaiat IA, El-Soaly IS, Alhag SK, et al. YOLO-based model for automatic detection of broiler pathological phenomena through visual and thermal images in intensive poultry houses. Agriculture. 2023;13(8):1527. https://doi.org/10.3390/agriculture13081527

    work page doi:10.3390/agriculture13081527 2023

  22. [23]

    Environmental factor detection and analysis technologies in livestock and poultry houses: a review

    Qi F, Zhao X, Shi Z, Li H, Zhao W. Environmental factor detection and analysis technologies in livestock and poultry houses: a review. Agriculture. 2023;13(8):1489. https://doi.org/10.3390/agriculture13081489

    work page doi:10.3390/agriculture13081489 2023

  23. [24]

    Wireless Environmental Monitoring and Control in Poultry Houses: A Conceptual Study

    Godinho A, Vicente R, Silva S, Coelho PJ. Wireless Environmental Monitoring and Control in Poultry Houses: A Conceptual Study. IoT. 2025;6(2):32. https://doi.org/10.3390/iot6020032

    work page doi:10.3390/iot6020032 2025

  24. [25]

    Multimodal Neural Network for Detecting and Classifying Deviations in Poultry Behavior

    Markarian G, Kolev G, Kolev D, Polushkina N, editors. Multimodal Neural Network for Detecting and Classifying Deviations in Poultry Behavior. 2024 IEEE 2nd Conference on AgriFood Electronics (CAFE); 2024: IEEE. http://doi.org/10.1109/CAFE63183.2024.11069356

    work page doi:10.1109/cafe63183.2024.11069356 2024

  25. [26]

    A multimodal detection method for caged diseased hens integrating behavioral and thermal features via instance segmentation

    Sun R, Wang Q, Yu C, Yang Z, Wu J, Fan W. A multimodal detection method for caged diseased hens integrating behavioral and thermal features via instance segmentation. Computers and Electronics in Agriculture. 2025;239:110926. https://doi.org/10.1016/j.compag.2025.110926

    work page doi:10.1016/j.compag.2025.110926 2025

  26. [28]

    Towards Smart Health Monitoring: Multimodal Sensing and Intelligent Disease Diagnosis in Poultry and Livestock

    Ma J, Yang X, Liu Y , Xin P, Tong Q, Liang C, et al. Towards Smart Health Monitoring: Multimodal Sensing and Intelligent Disease Diagnosis in Poultry and Livestock. Animal Frontiers. 2026:vfaf060. https://doi.org/10.1016/j.atech.2025.101564

    work page doi:10.1016/j.atech.2025.101564 2026

  27. [29]

    Early phenotype programming in birds by temperature and nutrition: a mini-review

    Andrieux C, Petit A, Collin A, Houssier M, Métayer -Coustard S, Panserat S, et al. Early phenotype programming in birds by temperature and nutrition: a mini-review. Frontiers in Animal Science. 2022;2:755842. https://doi.org/10.3389/fanim.2021.755842 29

    work page doi:10.3389/fanim.2021.755842 2022

  28. [30]

    Decoding Poultry Welfare from Sound —A Machine Learning Framework for Non -Invasive Acoustic Monitoring

    Manikandan V , Neethirajan S. Decoding Poultry Welfare from Sound —A Machine Learning Framework for Non -Invasive Acoustic Monitoring. Sensors. 2025;25(9):2912. https://doi.org/10.3390/s25092912

    work page doi:10.3390/s25092912 2025

  29. [31]

    Decoding vocal indicators of stress in laying hens: A CNN -MFCC deep learning framework

    Neethirajan S. Decoding vocal indicators of stress in laying hens: A CNN -MFCC deep learning framework. Smart Agricultural Technology. 2025;11:101056. https://doi.org/10.1016/j.atech.2025.101056

    work page doi:10.1016/j.atech.2025.101056 2025

  30. [32]

    AI-Powered V ocalization Analysis in Poultry: Systematic Review of Health, Behavior, and Welfare Monitoring

    Manikandan V , Neethirajan S. AI-Powered V ocalization Analysis in Poultry: Systematic Review of Health, Behavior, and Welfare Monitoring. Sensors. 2025;25(13):4058. https://doi.org/10.3390/s25134058

    work page doi:10.3390/s25134058 2025

  31. [33]

    Spectral entropy of early-life distress calls as an iceberg indicator of chicken welfare

    Herborn KA, McElligott AG, Mitchell MA, Sandilands V , Bradshaw B, Asher L. Spectral entropy of early-life distress calls as an iceberg indicator of chicken welfare. Journal of the Royal Society Interface. 2020;17(167):20200086. https://doi.org/10.1098/rsif.2020.0086

    work page doi:10.1098/rsif.2020.0086 2020

  32. [34]

    V ocalization patterns in laying hens -an analysis of stress -induced audio responses

    Neethirajan S. V ocalization patterns in laying hens -an analysis of stress -induced audio responses. bioRxiv. 2023:2023.12. 26.573338. https://doi.org/10.1101/2023.12.26.573338

    work page doi:10.1101/2023.12.26.573338 2023

  33. [35]

    Environmental complexity: Additional human visual contact reduced meat chickens’ fear of humans and physical items altered pecking behavior

    Taylor PS, Hemsworth PH, Rault J-L. Environmental complexity: Additional human visual contact reduced meat chickens’ fear of humans and physical items altered pecking behavior. Animals. 2022;12(3):310. https://doi.org/10.3390/ani12030310

    work page doi:10.3390/ani12030310 2022

  34. [36]

    Modern technologies for improving broiler production and welfare: A Review

    Brassó LD, Komlósi I, Várszegi Z. Modern technologies for improving broiler production and welfare: A Review. Animals. 2025;15(4):493. https://doi.org/10.3390/ani15040493

    work page doi:10.3390/ani15040493 2025

  35. [37]

    ChickTrack –A quantitative tracking tool for measuring chicken activity

    Neethirajan S. ChickTrack –A quantitative tracking tool for measuring chicken activity. Measurement. 2022;191(110819):3. https://doi.org/10.1016/j.measurement.2022.110819

    work page doi:10.1016/j.measurement.2022.110819 2022

  36. [38]

    Endocrinology of thermoregulation in birds in a changing climate

    Ruuskanen S, Hsu B-Y , Nord A. Endocrinology of thermoregulation in birds in a changing climate. Molecular and Cellular Endocrinology. 2021;519:111088. https://doi.org/10.1016/j.mce.2020.111088

    work page doi:10.1016/j.mce.2020.111088 2021

  37. [39]

    The impact of multiple exposures and movement on the fear response of poultry

    Jackson A, Quino M, Gautam A, Gilpin M, Still K, Landers D, et al. The impact of multiple exposures and movement on the fear response of poultry. Poultry Science. 2025;104(1):104594. https://doi.org/10.1016/j.psj.2024.104594

    work page doi:10.1016/j.psj.2024.104594 2025

  38. [40]

    Individual differences in habituation: Innate covariation between habituation, exploration, and body size in naïve chicks (Gallus gallus)

    Dissegna A, Grassi M, Chiandetti C. Individual differences in habituation: Innate covariation between habituation, exploration, and body size in naïve chicks (Gallus gallus). Behavioural Processes. 2022;200:104705. https://doi.org/10.1016/j.beproc.2022.104705

    work page doi:10.1016/j.beproc.2022.104705 2022