Video-based insect tracking provides vital insights into insect behavior and ecology, enhancing our understanding of their movements and interactions. Therefore, examining trends in this field over the last few years is essential. This study aims to conduct a bibliometric analysis to unveil the growing interest in video-based insect tracking with a short review based on documents used for bibliometric analysis. To achieve this, 453 documents were extracted from Scopus on 12 June 2023. Only documents in English published between 2010 and 2023, resulting in a dataset of 318 documents, were analyzed. The findings illustrate a consistent growth in video-based insect research over the last years, with a significant peak in 2021, comprising 32 documents. The journal PLOS ONE stands out as the most productive source. The USA exhibited the most significant interest in video-based insect tracking over the last years. Keyword analysis reflects the multidisciplinary nature of insect tracking research. The review demonstrated that video-based insect tracking serves two primary objectives: pose estimation and trajectory information. However, the main challenge in video-based insect tracking is to preserve the identity of multiple individuals in situations involving occlusions or complex interactions.
Internet traffic classification is a fundamental task for network services and management. There are good machine learning models to identify the class of traffic. However, finding the most discriminating features to have efficient models remains essential. In this paper, we use interpretable machine learning algorithms such as decision tree, random forest and eXtreme gradient boosting (XGBoost) to find the most discriminating features for internet traffic classification. The dataset used contains 377,526 traffics. Each traffic is described by 248 features. From these features, we propose a 12-feature model with an accuracy of up to 99.76%. We tested it on another dataset with 19626 flows and obtained 98.40% of accuracy. This shows the efficiency and stability of our model. Also, we identify a set of 14 important features for internet traffic classification, including two that are crucial: port number (server) and minimum segment size (client to server).