Deep Neural Networks (DNNs) are crucial for enhancing environmental perception in embedded intelligent systems, particularly in applications such as drones and autonomous vehicles. These mission-critical applications necessitate both computational accuracy and real-time performance. A significant challenge arises from the unpredictable execution times of DNNs and the variable periods of perception tasks. To address this, we present RTDeepEnsemble, an innovative framework designed for the real-time execution of DNN ensembles. RTDeepEnsemble dynamically manages the DNN ensemble as an imprecise computation model, judiciously selecting the optimal DNN for execution at runtime. This framework effectively arranges the DNN execution sequence, estimating utility through a refined Boosting algorithm. Additionally, RTDeepEnsemble prioritizes mandatory subtasks based on the Earliest Deadline First scheduling and employs a dynamic programming method to schedule optional subtasks. Comprehensive evaluations on the Nvidia Jetson Xavier NX platform, within a real-time object detection context, demonstrate RTDeepEnsemble's superiority in both accuracy and deadline miss rate. Notably, while maintaining real-time performance, we observe an accuracy increase of approximately 10 %, underscoring RTDeepEnsemble's potential as a solution for real-time machine perception.

Designing scheduling policies for multiprocessor real-time systems is challenging since the multiprocessor scheduling problem is NP-complete. The existing heuristics are customized policies that may achieve poor performance under some specific task loads. Thus, a new design pattern is needed to make the multiprocessor scheduling policies perform well under various task loads. In this paper, we investigate a new realtime scheduling policy based on reinforcement learning. For any given real-time task set, our policy can automatically derive a high performance by online learning. Specifically, we model the real-time scheduling process as a multi-agent cooperative game and propose multi-agent self-cooperative learning that overcomes the curse of dimensionality and credit assignment problems. Simulation results show that our approach can learn high-performance policies for various task/system models.

SUMMARY: As the experiment techniques and strategies in quantitative proteomics are improving rapidly, the corresponding algorithms and tools for protein quantification with high accuracy and precision are continuously required to be proposed. Here, we present a comprehensive and flexible tool named PANDA for proteomics data quantification. PANDA, which supports both label-free and labeled quantifications, is compatible with existing peptide identification tools and pipelines with considerable flexibility. Compared with MaxQuant on several complex datasets, PANDA was proved to be more accurate and precise with less computation time. Additionally, PANDA is an easy-to-use desktop application tool with user-friendly interfaces. AVAILABILITY AND IMPLEMENTATION: PANDA is freely available for download at https://sourceforge.net/projects/panda-tools/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Summary: Compared with the numerous software tools developed for identification and quantification of -omics data, there remains a lack of suitable tools for both downstream analysis and data visualization. To help researchers better understand the biological meanings in their -omics data, we present an easy-to-use tool, named PANDA-view, for both statistical analysis and visualization of quantitative proteomics data and other -omics data. PANDA-view contains various kinds of analysis methods such as normalization, missing value imputation, statistical tests, clustering and principal component analysis, as well as the most commonly-used data visualization methods including an interactive volcano plot. Additionally, it provides user-friendly interfaces for protein-peptide-spectrum representation of the quantitative proteomics data. Availability and implementation: PANDA-view is freely available at https://sourceforge.net/projects/panda-view/. Supplementary information: Supplementary data are available at Bioinformatics online.