Ankaj Thakur

Dr. Ankaj Thakur

orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 March 2025 in Journal of Veterinary Behavior
Verified
Journal Article
Closed access
ATAnkaj Thakur
Ankaj Thakur
MKMl Kamboj
Ml Kamboj
BVBrij Vanita
Brij Vanita
MRMeesam Raza
Meesam Raza

1 January 2021
Verified
Book Chapter
Closed access
PDF file
RKRavindra Kumar
Ravindra Kumar
ATAnkaj Thakur
Ankaj Thakur
RTRajneesh Thakur
Rajneesh Thakur
PDP. K. Dogra
P. K. Dogra

19 August 2025 in Annals of Medicine & Surgery
Verified
Journal Article
Open access
IAIshana Attri
Ishana Attri
BVBrij Vanita
Brij Vanita
RRRajesh Rajput
Rajesh Rajput
LALalit Kumar Awasthi
Lalit Kumar Awasthi
ATAnkaj Thakur
Ankaj Thakur
DGDivya Gupta
Divya Gupta
Early and accurate detection of animal diseases is critical in veterinary medicine and preclinical research, where timely intervention can influence both animal welfare and experimental outcomes. In this study, we introduce SAAM-VetNet, a novel Severity-Aware Attention-Based Multi-Task deep learning framework designed to simultaneously detect animal diseases and grade their severity from medical images. The proposed architecture integrates a convolutional block attention module to enhance feature localization and contextual representation, coupled with a multi-branch learning strategy for disease classification and severity assessment. We evaluate SAAM-VetNet using two publicly available datasets: the Animal Disease Classification dataset and the Mastitis Disease Detection dataset. Our model achieves superior performance with an accuracy of 91.2% and an F 1 score of 89.8%, outperforming established baselines including ResNet18, MobileNetV2, EfficientNet-B0, DenseNet121, and vision transformer (ViT). The results demonstrate that incorporating attention mechanisms and severity-aware multi-task learning significantly enhances model interpretability and diagnostic accuracy, offering a robust tool for automated preclinical model selection and veterinary diagnostics.

1 June 2016 in Indian Journal of Animal Research
Verified
Journal Article
Closed access
ATAnkaj Thakur
Ankaj Thakur
DMD. S. Malik
D. S. Malik
SKS. Kaswan
S. Kaswan
ASA.L. Saini
A.L. Saini
Present study was conducted to investigate the effect of different floor space allowances on performance and behavior of Beetal kids from 3 to 6 months of age. Twenty four spring born Beetal kids (3 month old) were randomly divided in to four groups (n=6 each group) on the basis of space allowances i.e. 0.6 m2, 0.7 m2, 0.8 m2 and 0.9 m2 covered area and 1.2 m2, 1.4 m2, 1.6 m2 and 1.8 m2 open area per kid. The results indicated that most of the performance parameters i.e. body weight (BW), average daily gain (ADG) and feed conversion ratio (FCR) were marginally higher with higher space allowance, but these did not differ statistically. However behavioural activities like moving, exploring pen, grooming and resting were significantly higher (p less than 0.05) in large space allowance groups whereas, eating, standing and negative social interactions were significantly better (p less than 0.05) in lower floor space allowance groups. It is concluded that the increase in floor space allowance had favorable effect on the performance and behavior of Beetal kids.

3 May 2025 in Journal of Veterinary Behavior
Verified
Journal Article
Closed access
ATAnkaj Thakur
Ankaj Thakur
RTRakesh Thakur
Rakesh Thakur
AKAadarsh Kumar
Aadarsh Kumar
BVBrij Vanita
Brij Vanita
VSVarun Sankhyan
Varun Sankhyan
SKShivani Katoch
Shivani Katoch

21 January 2025 in Journal of Applied Animal Welfare Science
Verified
Journal Article
Closed access
ATAnkaj Thakur
Ankaj Thakur
MKMl Kamboj
Ml Kamboj
PDPk Dogra
Pk Dogra
BVBrij Vanita
Brij Vanita
This study aimed to develop a welfare assessment protocol specifically for migratory goats, acknowledging that migratory pastoralism, while allowing natural behavior expression, can compormise welfare due to environmental stressors and malnutrition. Existing research predominantly focuses on intensive systems, leaving a gap in migratory system assessment. Adapted from the AWIN framework, the protocol was developed through a systematic literature review and expert consultation (N = 46), prioritizing welfare indicators using Likert scale and Weighted Average Index. The protocol includes five welfare domains - feeding, environment/facility around camping, health, behavior, and performance - with 32 indicators (5, 6, 9, 5, and 7 per domain,). Weighted scores were allocated as 25, 15, 30, 15, and 15,respectively, totalling100. Cronbach's alpha of 0.90 confirmed reliability and internal consistency, with content validity supported by 91.30% expert agreement. Feasibility testing across varying altitudes and physiological stages validated the protocol in high altitude, vertical migratory systems, However, further testing is required for low-altitude, horizontal migratory systems to address environmental and management differences. This protocol offers a taiilored framework for assessing welfare in migraotry goat systems..