Given the vast diversity of bee species and the limited availability of taxonomy experts, bee species identification has become increasingly important, especially with the rise of apiculture practice. This review systematically explores the application of machine learning (ML) techniques in bee species determination, shedding light on the transformative potential of ML in entomology. Conducting a keyword-based search in the Scopus and Web of Science databases with manual screening resulted in 26 relevant publications. Focusing on shallow and deep learning studies, our analysis reveals a significant inclination towards deep learning, particularly post-2020, underscoring its ability to handle complex, high-dimensional data for accurate species identification. Most studies have utilized images of stationary bees for the determination task, despite the high computational demands from image processing, with fewer studies utilizing the sound and movement of the bees. This emerging field faces challenges in terms of dataset scarcity with limited geographical coverage. Additionally, research predominantly focuses on honeybees, with stingless bees receiving less attention, despite their economic potential. This review encapsulates the state of ML applications in bee species determination. It also emphasizes the growing research interest and technological advancements, aiming to inspire future explorations that bridge the gap between computational science and biodiversity conservation.

Honey bees are vital for humans and the ecosystem; humans use bee products for various purposes and honey bees play an essential role in pollination. Identifying the subspecies of honey bees is essential for beekeepers, bee breeders, and researchers. Conventional methods of identification are time-consuming and expensive, as such, a more efficient and accurate technique is required. This paper proposes a computer vision-based method to classify subspecies of honey bees, with a dataset consisting of seven honey bee subspecies utilised. Due to the unavailability of a sufficient amount of labelled images to train a model, Transfer Learning (TL) technique has been employed. The Inception v3 model has been utilized as the main Convolutional Neural Network architecture; trained initially using the ImageNet dataset and then fine-tuned using the honey bee dataset. Image augmentation technique has also been used to reduce the impact of an imbalanced and small dataset. The Transfer Learning-based Inception v3 model was trained using the Sigmoid Focal loss function and demonstrated an accuracy of 94% with a weighted average F1 score of 0.94. This demonstrates the applicability of computer vision in the classification of honey bees.

Heterotrigona itama, a widely reared stingless bee species, produces highly valued honey. These bees naturally secure their colonies within logs, accessed via a single entrance tube, but remain vulnerable to intruders and predators. Guard bees play a critical role in colony defense, exhibiting the ability to discriminate between nestmates and non-nestmates and employing strategies such as pheromone release, buzzing, hissing, and vibrations to alert and recruit hive mates during intrusions. This study investigated the acoustic signals produced by H. itama guard bees during intrusions to determine their potential for intrusion detection. Using a Jetson Nano equipped with a microphone and camera, guard bee sounds were recorded and labeled. After preprocessing the sound data, Mel Frequency Cepstral Coefficients (MFCCs) were extracted as features, and various dimensionality reduction techniques were explored. Among them, Linear Discriminant Analysis (LDA) demonstrated the best performance in improving class separability. The reduced feature set was used to train both Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) classifiers. KNN outperformed SVM, achieving a Precision of 0.9527, a Recall of 0.9586, and an F1 Score of 0.9556. Additionally, KNN attained an Overall Cross-Validation Accuracy of 95.54% (±0.67%), demonstrating its superior classification performance. These findings confirm that H. itama produces distinct alarm sounds during intrusions, which can be effectively classified using machine learning; thus, demonstrating the feasibility of sound-based intrusion detection as a cost-effective alternative to image-based approaches. Future research should explore real-world implementation under varying environmental conditions and extend the study to other stingless bee species.

Beekeeping is a profitable and mind-relaxing practice; however, monitoring beehives poses significant challenges, such as consuming time and potentially disturbing hive equilibrium, which may lead to colony collapse. Developing precision beekeeping (PB) systems is crucial to assist beekeepers in decision-making, automate redundant hive maintenance, and enhance the security and comfort of bee life. This review systematically explores research on PB systems, based on a keyword-driven search of Scopus and Web of Science databases, yielding 46 relevant publications. The analysis highlights a notable increase in research activity in the field since 2016. The integration of advanced technologies, including machine learning, cloud computing, IoT, and scenario-based communication methods, has proven instrumental in predicting hive states such as queen status, enemy attacks, readiness for harvest, swarming events, and population decline. Commonly measured parameters include hive weight, temperature, and relative humidity, with various sensors employed to ensure precision while minimizing bee disturbance. Additionally, bee traffic monitoring has emerged as a critical approach to assessing hive health. Most studies focus on honeybees rather than stingless bees and, in the context of enemy identification, Varroa destructor is the primary target. This review underscores the potential of novel technologies to revolutionize apiculture and enhance hive management practices.

Stingless bee colonies are vulnerable to predators of widely varying sizes, and repeated intrusions can cause stress, reduce productivity, and trigger colony absconding. Existing automated surveillance systems detect only a limited range of predators and often struggle with multi-scale object detection in high-resolution images. This study proposes a real-time predator monitoring system that integrates a Multi-Scale Attention module into the YOLOv11-nano architecture (MSYOLO11) to enhance detection performance across both small and large predators. The proposed model combines convolutional features with an attention mechanism to improve global–local feature fusion. Experimental evaluation shows that MSYOLO11 increases overall Recall from 0.830 to 0.853 compared to YOLOv11-nano, with substantial improvements for small-object classes such as ants (+0.096), humans (+0.083), and H. itama (+0.026), while maintaining comparable Precision (0.868 vs 0.842) and mAP50 (0.898 vs 0.896) at a nearly identical computational cost (6.3 GFLOPs). The system operates at 5 FPS on a Jetson Orin Nano, with an end-to-end latency of 181 ms. A Firebase-integrated mobile application delivers instant push notifications, displays detected predators with bounding boxes, and provides real-time data synchronization. The results demonstrate that MSYOLO11 offers a practical and efficient solution for multi-scale predator detection, supporting continuous hive surveillance and timely beekeeper intervention.