Coded computing has received significant attention thanks to its advantage in alleviating the straggler effect in distributed computation framework, which would be one of the key fundamental techniques to enable the distributed and decentralized network architectures towards 5G-advanced and 6G era. Specifically, considering the scenario that multiple tasks randomly arrive at the network, the additional task queuing makes the delay analysis of coded computing more challenging. In this paper, we consider the impacts of task queuing and characterize the end-to-end delay for coded computing systems under the multi-task scenario. To this end, we first model the end-to-end coded computing system. Then, based on the redundant task processing strategies, we consider both purging and non-purging coded computing schemes. Although the expected end-to-end delay for both schemes are intractable, we obtain closed-form expressions for their respective lower and upper bounds, which generalizes the delay results of the single-task scenario. Moreover, we show that the multi-task coded computing has a coding gain of Θ(logn) wherendenotes the number of worker nodes, even with task queues considered. Simulation results verify the accuracy of the derived delay bounds and show the effectiveness of coded computing in the multi-task scenario.

The coronavirus disease of 2019 pandemic has catalyzed the rapid development of mRNA vaccines, whereas, how to optimize the mRNA sequence of exogenous gene such as severe acute respiratory syndrome coronavirus 2 spike to fit human cells remains a critical challenge. A new algorithm, iDRO (integrated deep-learning-based mRNA optimization), is developed to optimize multiple components of mRNA sequences based on given amino acid sequences of target protein. Considering the biological constraints, we divided iDRO into two steps: open reading frame (ORF) optimization and 5' untranslated region (UTR) and 3'UTR generation. In ORF optimization, BiLSTM-CRF (bidirectional long-short-term memory with conditional random field) is employed to determine the codon for each amino acid. In UTR generation, RNA-Bart (bidirectional auto-regressive transformer) is proposed to output the corresponding UTR. The results show that the optimized sequences of exogenous genes acquired the pattern of human endogenous gene sequence. In experimental validation, the mRNA sequence optimized by our method, compared with conventional method, shows higher protein expression. To the best of our knowledge, this is the first study by introducing deep-learning methods to integrated mRNA sequence optimization, and these results may contribute to the development of mRNA therapeutics.

In real-world applications, the effective integration of learning and reasoning in a cognitive agent model is a challenging mission. However, such integration may lead to a better understanding, practice, and construction of more realistic models, especially for mathematical learning. Unfortunately, existing models are either oversimplified or require much processing time, which is unsuitable for online learning and education. Therefore, we propose a novel cognitive learning model, called Mathematical Cognitive Learning Model (MathCLM) based on the evolution of knowledge graph, for online mathematical learning that seeks to effectively represent, learn, and reason in online learning environments. The model's architecture combines cognitive learning with symbolic knowledge representation based on natural language processing (NLP). We introduce the mathematical instance concept to build the strategies by mathematical knowledge, such as theorems, axioms, etc., and infer new custom instances based on the learning knowledge. Furthermore, it can deal with uncertainty and errors from instances recommendation using a graph matching model and displays the inference progressing with different combinations of instances. We build a platform to promote and validate our model. The validation of the model on the real-world platform and the results presented here indicate the promise of the approach when performing online learning and reasoning in real-world scenarios, with possible applications in various areas.

The paper utilizes semantic Web and knowledge service technologies to construct a subject-oriented learning navigation system used in middle school education. The system inherently builds a knowledge base by ontology to store the relationship of subject knowledge points to learning resource and relationship between knowledge points , displays the reticulated structure of knowledge (navigation map) formed by visualizing knowledge base, and aggregates corresponding learning resource of knowledge point to enable learners practice their learning process according to the navigation map. The thesis build ontology for navigated learning to achieve pragmatic learning navigation, there are several advantages for this innovative research: the reticulated structure of knowledge in a certain subject could be displayed briefly and straightforward; the system could recommend related and further study materials for learners and intelligently discover the weak knowledge points of learners according to automated reasoning on knowledge base. The system also provides an interactive environment for both teachers to edit the knowledge structure and learners to study. As the most popular knowledge model, we mainly discusses the establishment of semantic knowledge Web, model of the knowledge base, knowledge storage for knowledge points in junior and senior schools, and the realization and utilization of the ontology-based navigation map.

We demonstrate a novel method to segment the tongue image automatically with the mouth location method and active appearance model (AAM). With the help of a particular feature of the mouth,we could locate the dark hole's position easily and quickly. For the close relationship between the mouth and tongue, we would predict the approximate area of the tongue. Then we apply the AAM to segment the tongue from the image completely, which uses texture and shape of an object. During the AAM search, we constrain the initial displacement and size in the approximate area. For those images that failed to locate the mouth, we use a multi-initial displacement method during the AAM search to optimize the result. The experiment shows that our method is accurate and effective.