A spacecraft is a typical time-sensitive system, and the characteristics of hard real-time and limited resources make the design of real-time scheduling algorithms particularly crucial in spaceborne operating system. With the development of space technology, onboard computer has transformed from a closed system with a single type of task to an open system with mixed sets of tasks. The system allows new tasks to be dynamically loaded during operation, leading to real-time changes in the types and numbers of tasks, further increasing the difficulty of predicting and the uncertainty of the system. Sporadic tasks are more common in actual system and have special temporal characteristics of releasing by a random frequency, making the schedulability determination more complex than that of other types of tasks. Therefore, we focused on the schedulability of sporadic tasks in spaceborne operating system and first classified the situations in which schedulability needs to be determined. For each preemption case in different situations, corresponding determination strategies were proposed based on Response Time Analysis (RTA). Due to RTA’s high time complexity, we additionally utilized Interference Bound Function (IBF) to judge the schedulability, thus providing flexible choices for system design. By tracking task’s runtime information and analyzing at a finer granularity, our methods reduced pessimism and achieved a better schedulable ratio.

As a typical application of edge intelligence, 3D object detection in autonomous driving often requires multimodal information fusion to accurately perceive the environment. With images and point clouds serving as critical sensory data sources, 3D object detection integrates multimodal fusion to enhance detection accuracy. Generally, fusion algorithms leveraging attention mechanism can intelligently extract and integrate multimodal sensing information to overcome limitations posed by sensor calibration. However, attention mechanism may cause challenges such as slow model convergence and high false positives. Therefore, in this paper, we propose the deformable denoising (DefDeN) model to effectively integrate modules including gated information fusion networks, multi-scale deformable attention mechanisms, noise addition and denoising method, and contrastive learning for multi-sensor feature fusion. Experimental results on the nuScenes dataset demonstrate the superiority of DefDeN in detection accuracy, and the effectiveness of precise and stable perception for complex scenarios in autonomous driving systems.

Compared with traditional environments, the cloud environment exposes online services to additional vulnerabilities and threats of cyber attacks, and the cyber security of cloud platforms is becoming increasingly prominent. A piece of code, known as a Webshell, is usually uploaded to the target servers to achieve multiple attacks. Preventing Webshell attacks has become a hot spot in current research. Moreover, the traditional Webshell detectors are not built for the cloud, making it highly difficult to play a defensive role in the cloud environment. SmartEagleEye, a Webshell detection system based on deep learning that is successfully applied in various scenarios, is proposed in this paper. This system contains two important components: gray-box and neural network analyzers. The gray-box analyzer defines a series of rules and algorithms for extracting static and dynamic behaviors from the code to make the decision jointly. The neural network analyzer transforms suspicious code into Operation Code (OPCODE) sequences, turning the detection task into a classification problem. Comprehensive experiment results show that SmartEagleEye achieves an encouraging high detection rate and an acceptable false-positive rate, which indicate its capability to provide good protection for the cloud environment.

In recent years, in order to achieve the goal of “carbon peaking and carbon neutralization”, many countries have focused on the development of clean energy, and the prediction of photovoltaic power generation has become a hot research topic. However, many traditional methods only use meteorological factors such as temperature and irradiance as the features of photovoltaic power generation, and they rarely consider the multi-features fusion methods for power prediction. This paper first preprocesses abnormal data points and missing values in the data from 18 power stations in Northwest China, and then carries out correlation analysis to screen out 8 meteorological features as the most relevant to power generation. Next, the historical generating power and 8 meteorological features are fused in different ways to construct three types of experimental datasets. Finally, traditional time series prediction methods, such as Recurrent Neural Network (RNN), Convolution Neural Network (CNN) combined with eXtreme Gradient Boosting (XGBoost), are applied to study the impact of different feature fusion methods on power prediction. The results show that the prediction accuracy of Long Short-Term Memory (LSTM), stacked Long Short-Term Memory (stacked LSTM), Bi-directional LSTM (Bi-LSTM), Temporal Convolutional Network (TCN), and XGBoost algorithms can be greatly improved by the method of integrating historical generation power and meteorological features. Therefore, the feature fusion based photovoltaic power prediction method proposed in this paper is of great significance to the development of the photovoltaic power generation industry.

With the development of IoT and 5G technologies, more and more online resources are presented in trendy multimodal data forms over the Internet. Hence, effectively processing multimodal information is significant to the development of various online applications, including e-learning and digital health, to just name a few. However, most AI-driven systems or models can only handle limited forms of information. In this study, we investigate the correlation between natural language processing (NLP) and pattern recognition, trying to apply the mainstream approaches and models used in the computer vision (CV) to the task of NLP. Based on two different Twitter datasets, we propose a convolutional neural network based model to interpret the content of short text with different goals and application backgrounds. The experiments have demonstrated that our proposed model shows fairly competitive performance compared to the mainstream recurrent neural network based NLP models such as bidirectional long short-term memory (Bi-LSTM) and bidirectional gate recurrent unit (Bi-GRU). Moreover, the experimental results also demonstrate that the proposed model can precisely locate the key information in the given text.