Automatic animal detection has become a critical capability in ecology, conservation, agriculture, and public safety, driven by the rapid growth of visual data collected through camera traps, UAVs, and remote sensors. The necessity of this study arises from the increasing demand to understand and apply these underlying detection techniques in practical domains such as animal husbandry, farming, and livestock management, where timely and accurate animal identification directly impacts productivity, welfare, and safety. Traditional convolutional neural networks (CNNs) have demonstrated strong accuracy in static or controlled environments but often face limitations in computational cost and inference speed. In contrast, the You Only Look Once (YOLO) family of one-stage detectors has revolutionized animal detection by achieving real-time performance while maintaining competitive accuracy across challenging geospatial environments. This review provides a chronological synthesis of detection approaches, tracing the evolution from handcrafted features and two-stage CNN-based models to modern YOLO architectures and transformer-enhanced frameworks. A detailed comparative analysis is presented, highlighting trade-offs in accuracy, speed, robustness, and deployment feasibility across diverse datasets, including camera trap imagery, UAV-based surveys, and satellite observations. Persistent challenges such as small-object detection, class imbalance, and limited cross-geographical generalization are discussed alongside enhancement strategies, including attention mechanisms, few-shot learning, and domain adaptation. Furthermore, practical deployment considerations are explored, with emphasis on edge computing platforms such as Jetson Nano, Coral TPU, and UAV-embedded systems. This review adopts a systematic methodology following PRISMA guidelines, covering studies published between 2015 and 2025, from which 142 were included after screening. Comparative findings show that on camera-trap datasets, transformer-augmented YOLO variants achieve up to 94% mAP under controlled illumination, while lightweight YOLOv7-SE and YOLOv8 architectures offer superior real-time performance (\(\ge\) 60 FPS) on UAV-based imagery. However, large-scale deployment remains constrained by edge-device memory limits and cross-domain generalization challenges.

The study centered on Quantitative Structure Property Relationship (QSPR) analysis with a focus on various graph energies, investigating drugs like Mefloquinone, Sertraline, Niclosamide, Tizoxanide, PHA-690509, Ribavirin, Emricasan, and Sofosbuvir. Employing computational modeling techniques, the research aimed to uncover the correlations between the chemical structures of these medications and their unique properties. The results illuminated the quantitative relationships between structural characteristics and pharmacological traits, advancing our predictive capabilities. This research significantly contributes to medication discovery and design by providing essential insights into the structure-property connections of these medicinal compounds. Notably, certain spectrum-based descriptors, such as positive inertia energy, adjacency energy, arithmetic-geometric energy, first zegrab energy, and the harmonic index, exhibited strong correlation coefficients above 0.999. In contrast, well-known descriptors like the Extended adjacency, Laplacian and signless Laplacian spectral radii, and the first and second Zagreb Estrada indices showed weaker performance. The article emphasizes the application of graph energies and a linear regression model to predict pharmacological features effectively, enhancing the drug discovery process and aiding in targeted drug design by elucidating the relationship between molecular structure and pharmacological characteristics.

In this study, we introduce a novel valency-based index, the neighborhood face index (NFI), designed to characterize the structural attributes of benzenoid hydrocarbons. To assess the practical applicability of NFI, we conducted a linear regression analysis utilizing numerous physiochemical properties associated with benzenoid hydrocarbons. Remarkably, the results revealed an extraordinary correlation exceeding 0.9991 between NFI and these properties, underscoring the robust predictive capability of the index. The NFI, identified as the best-performing descriptor, is subsequently investigated within certain infinite families of carbon nanotubes. This analysis demonstrates the index’s exceptional predictive accuracy, suggesting its potential as a versatile tool for characterizing and predicting properties across diverse molecular structures, particularly in the context of carbon nanotubes.

In quantitative structure-property and structure-activity relationships studies, several graph invariants, namely, topological indices have been defined and studied due to their numerous applications in computer networks, biotechnology, and nanochemistry. Topological indices are numeric parameters that describe the biological, physical, and chemical properties depending on the structure and topology of different chemical compounds. In this article, we inaugurated some degree-based novel indices, namely, geometric-harmonic , harmonic-geometric , neighborhood harmonic-geometric , and neighborhood geometric-harmonic indices and verified their chemical applicability. Furthermore, an attempt is made to calculate analytical closed formulas for different variants of silicon carbides and analyze the obtained results graphically.

Automated crack detection plays a vital role in the structural health monitoring of civil infrastructure, yet existing methods often remain limited to binary crack identification and are computationally demanding for real-time or edge deployment. This study presents a lightweight convolutional neural network, developed through the CNN-Block Development Mechanism (CNN-BDM), for multi-class crack and surface-type classification across six categories: cracked and uncracked concrete, plaster, and wall surfaces. The proposed framework integrates domain-driven data augmentation, balanced label design, and systematic regularization to achieve a compact yet high-performing model. Through iterative refinement, the final Lite-V2 architecture achieves a macro-F1 score of 0.928 and a test accuracy of 0.957 on the SDNET2018 dataset using only 0.28 million parameters. Cross-domain evaluations further validate the model’s generalization, attaining F1-scores of 0.975 on CrackForest (CFD) and 0.96 on DeepCrack. Grad-CAM visualizations confirm interpretable feature localization, while perturbation experiments under brightness and blur variations demonstrate robust resilience to real-world distortions. Comparative analysis against MobileNetV2, EfficientNet-B0, and ResNet-18 reveals that Lite-V2 delivers the highest accuracy and efficiency with up to 40 $$\times$$ fewer parameters and significantly reduced inference latency (11 ms) on a Raspberry Pi 4. These results establish Lite-V2 as an efficient, explainable, and deployment-ready framework for practical crack classification and condition monitoring in resource-constrained environments.