Small object detection is a critical challenge in Unmanned Aerial Vehicles (UAVs) due to the limited pixel representation of small objects and the impact of successive pooling operations, which frequently results in the disappearance of small objects within intricate backgrounds. To tackle this issue, we propose the Small Object Enhancement Pyramid (SOEP) module, which first transforms feature representations (i.e., in the spatial domain) into the frequency domain to better capture small objects typically characterized by high-frequency components. These feature representations are then fused in the spatial domain using a frequency-based attention map, enhancing small object representations by integrating information from both complementary domains. Furthermore, we introduce a Task Aligned Head (TAH) that integrates classification and localization tasks interactively, reducing the misalignment that occurs when these tasks are learned independently, particularly in the context of small objects. Experimental results on the Visdrone dataset verify that our proposed method (D2FTA) outperforms the baseline method by 12.7%, 14.19% on mAP0.5and mAP0.5:0.95.

The present work has proposed a novel approach for autonomous vehicle path tracking, as well as integrated vehicle dynamics management. Our approach adopts the nonlinear model-based control (NMPC) model to account for the unknown nonlinearity in vehicle dynamics, together with a cost function to enable minimum input parameters for our NMPC model. An improved Random Projection Neural Network (RPNN) is then proposed, featuring a novel weight adaptation method utilizing gradient descent from the input to the hidden layer, and an adaptive law grounded in Lyapunov stability theory from the hidden to the output layer. This improvement aims to address computational burdens and the challenges posed by unknown nonlinear uncertainties in lateral tyre forces, which are not adequately managed by Nonlinear Model Predictive Control (NMPC). Experimental results demonstrate that the developed approach, integrating the improved RPNN with NMPC, achieves accurate path-tracking performance with a minimal amount of data. This is attributed to the high adaptability of the enhanced RPNN algorithm, which updates weights in real time using incoming data.

Logs are one of the most valuable data to describe the running state of services. Failure diagnosis through logs is crucial for service reliability and security. The current automatic log failure diagnosis methods cannot fully use the multiple fields of logs, which fail to capture the relation between them. In this article, we propose LogKG, a new framework for diagnosing failures based on knowledge graphs (KG) of logs. LogKG fully extracts entities and relations from logs to mine multi-field information and their relations through the KG. To fully use the information represented by KG, we propose a failure-oriented log representation (FOLR) method to extract the failure-related patterns. Utilizing the OPTICS clustering method, LogKG aggregates historical failure cases, labels typical failure cases, and trains a failure diagnosis model to identify the root cause. We evaluate the effectiveness of LogKG on a real-world log dataset and a public log dataset, respectively, showing that it outperforms existing methods. With the deployment in a top-tier global Internet Service Provider (ISP), we demonstrate the performance and practicability of LogKG.

System logs, which describe a variety of events of software systems, are becoming increasingly popular for anomaly detection. However, for a large software system, current unsupervised learning-based methods are suffering from low accuracy due to the high diversity of logs, while the supervised learning methods are nearly infeasible to be used in practice because it is time-consuming and labor-intensive to obtain sufficient labels for different types of software systems. In this paper, we propose a novel framework, LogTransfer, which applies transfer learning to transfer the anomalous knowledge of one type of software system (source system) to another (target system). We represent every template using Glove, which considers both global word co-occurrence and local context information, to address the challenge that different types of software systems are different in log syntax while the semantics of logs should be reserved. We apply an LSTM network to extract the sequential patterns of logs, and propose a novel transfer learning method sharing fully connected networks between source and target systems, to minimize the impact of noises in anomalous log sequences. Extensive experiments have been performed on switch logs of different vendors collected from a top global cloud service provider. LogTransfer achieves an averaged 0.84 F1-score and outperforms the state-of-the-art supervised and unsupervised log-based anomaly detection methods, which are consistent with the experiments conducted on the public HDFS and Hadoop application datasets.