The integration of reconfigurable intelligent surfaces (RIS) with relays can enhance the quality and coverage of wireless communication. However, relays introduce extra energy consumption, and the transmission quality of RIS-aided relay systems can be further improved. Polarization-adjusted convolutional (PAC) codes exhibit superior error-correction performance at short code lengths, demonstrating potential to enhance the performance of RIS-aided relay systems. In this paper, we consider an energy-efficient RIS-aided coded cooperation (RIS-CC) system based on PAC codes to achieve wide coverage transmission with high reliability and low latency. First, a parity-check (PC) aided PAC-CC (PC-PAC-CC) scheme is designed to build the considered RIS-CC system for efficient relay forwarding. Using PC, the proposed PC-PAC-CC scheme avoids the unnecessary energy consumption on relays at high signal-to-noise ratio (SNR). Second, we propose a PC-aided low-complexity list (PC-LCL) decoding algorithm to reduce decoding complexity at receivers, thus decreasing transmission latency. Moreover, the proposed PC-LCL decoding algorithm is implemented by software to demonstrate its practicability. Third, we derive closed-form expressions for the tight upper bound of ergodic channel capacity (ECC) in the considered RIS-CC system under Nakagami-mfading, and conduct its asymptotic analysis at high SNR. Test results show that 1) the proposed PC-PAC-CC scheme has better error-correction performance than state-of-the-art (SOTA) work, and reduces energy consumption on relays by up to 81.02%; 2) the proposed PC-LCL software decoder has a 35.29% reduction on latency compared with the SOTA PAC software decoder. Besides, the derived closed-form expressions are verified by simulations.

Personalized learning represents a promising educational strategy within intelligent educational systems, aiming to enhance learners' practice efficiency. However, the scarcity of offline practice response data (e.g., answer correctness) and potential biases in human online practice create a significant gap between offline metrics and the actual online performance of personalized learning services. To address this challenge, we introduce Agent4Edu, a novel personalized learning simulator leveraging recent advancements in human intelligence through large language models (LLMs). Agent4Edu features LLM-powered generative agents equipped with learner profile, memory, and action modules tailored to personalized learning algorithms. The learner profiles are initialized using real-world response data, capturing practice styles and cognitive factors. Inspired by psychology theory, the memory module records practice facts and high-level summaries, integrating reflection mechanisms. The action module supports various behaviors, including exercise understanding, analysis, and response generation. Each agent can interact with personalized learning algorithms, such as computerized adaptive testing, enabling a multifaceted evaluation and enhancement of customized services. Through a comprehensive assessment, we explore the strengths and weaknesses of Agent4Edu, emphasizing the consistency and discrepancies in responses between agents and human learners.

Adaptive learning, also known as adaptive teaching, relies on learning path recommendations that sequentially suggest personalized learning items (such as lectures and exercises) to meet the unique needs of each learner. Despite the extensive research in this field, previous approaches have primarily modeled the interaction sequences between learners and items using simple indexing, leading to three issues: (1) The utilization of information from both learners and items is not sufficient. For instance, these models are unable to leverage the semantic information contained within the textual content of the items. (2) Models need to be retrained on different datasets separately, which makes it difficult to adapt to the continuously expanding item pool in online educational scenarios. (3) The existing recommendation paradigm based on trained reinforcement learning frameworks, suffers from unstable recommendation performance in sparse learning logs. To address these challenges, we propose a generalized Generative Agent for Adaptive Learning (GenAL), which integrates educational tools with LLMs' semantic understanding to enable effective and generalizable learning path recommendations across diverse data distributions. Specifically, our framework consists of two components: the Global Thinking Agent, which updates the learner profile and reflects on recommendation outcomes based on the learner's historical learning records. The other is the Local Teaching Agent, which recommends items using educational prior knowledge. Leveraging the LLM's robust semantic understanding, our framework does not rely on item indexing but instead extracts relevant information from the textual content. We evaluated our approach on three real-world datasets, and the experimental results demonstrate that our GenAL not only consistently outperforms all baselines but also exhibits strong generalization ability.

Graph In-Context Learning, with the ability to adapt pre-trained graph models to novel and diverse downstream graphs without updating any parameters, has gained much attention in the community. The key to graph in-context learning is to perform downstream graphs conditioned on chosen prompt examples. Existing methods randomly select subgraphs or edges as prompts, leading to noisy graph prompts and inferior model performance. Additionally, due to the gap between pre-training and testing graphs, when the number of classes in the testing graphs is much greater than that in the training, the in-context learning ability will also significantly deteriorate. To tackle the aforementioned challenges, we develop a multi-stage adaptive prompt optimization method GraphPrompter, which optimizes the entire process of generating, selecting, and using graph prompts for better in-context learning capabilities. Firstly, Prompt Generator introduces a reconstruction layer to highlight the most informative edges and reduce irrelevant noise for graph prompt construction. Furthermore, in the selection stage, Prompt Selector employs the k-nearest neighbors algorithm and pre-trained selection layers to dynamically choose appropriate sam-ples and minimize the influence of irrelevant prompts. Finally, we leverage a Prompt Augmenter with a cache replacement strategy to enhance the generalization capability of the pre-trained model on new datasets. Extensive experiments show that GraphPrompter effectively enhances the in-context learning ability of graph models. On average across all the settings, our approach surpasses the state-of-the-art baselines by over 8 %. Our code is released at https://ithub.com/karin0018/GraphPrompter.

In digital education, Cognitive Diagnosis (CD) is essential for modeling learners' cognitive states, such as problem-solving ability and knowledge proficiency, by analyzing their response data, like answer correctness. However, traditional CD methods struggle with effectiveness and efficiency. They fail to capture the diversity and uncertainty of learners' cognitive states. Additionally, response prediction can be time-consuming. To address these issues, we propose BoxCD, a contrastive probabilistic box embedding model for cognitive diagnosis. BoxCD utilizes high-dimensional axis-aligned hyper-rectangles (boxes) to represent learners and exercises, with the volume of intersecting boxes used to predict learners' responses. This approach effectively captures semantic diversity and uncertainty while enhancing diagnostic effectiveness. To stabilize box embeddings, we integrate contrastive learning objectives with response prediction goals, optimizing the distance between positive and negative samples of learner and exercise boxes to improve uniformity. Additionally, we develop a rank-based response prediction method that leverages the geometric properties of box embeddings to assess learners' response correctness efficiently. Comprehensive experiments on two real-world datasets demonstrate that BoxCD outperforms traditional CD models in effectiveness and efficiency. This showcases its potential to enhance personalized learning in digital education platforms.

Accurately predicting aortic valve movement under coronary influence is critical for personalized cardiac interventions and virtual surgery planning. Conventional Fluid-Structure Interaction (FSI) models tend to neglect modeling coronary arteries due to their complexities, leading to bias in leaflet motion simulations. To overcome this limitation, we propose a combination of spatiotemporal graph convolution and Transformer based gated (Gated-STGFormer) deep learning framework, which learns to reconstruct coronary-modulated leaflet motion from simulations without explicit coronary arteries. The framework integrates Graph Convolutional Networks (GCNs) for spatial dependency modeling and Transformer for temporal dependency, with both encoding and gating mechanisms to effectively capture spatiotemporal couplings. Quantitative evaluation demonstrated that it reproduces the spatiotemporal movements of leaflets under the coronary arteries with a high degree of fidelity. By addressing anatomical simplifications in conventional simulations, this method provides a physics-informed and computationally efficient surrogate model with strong clinical applicability. Our findings suggest that the Gated-STGFormer effectively incorporates spatiotemporal modal information, and can serve as a module for coronary artery compensation in a preoperative planning system, enabling more realistic and personalized valve biomechanical simulations.

This article draws inspiration from deep learning image restoration technology. If users involved in the rumor topic are regarded as pixels in an image, the uncertainty of user behavior is similar to the ambiguity of pixels in a mosaic image. The prediction of user behavior is influenced by the user and neighboring friends. Similarly, the recovery of mosaic image pixels is also influenced by these pixels and neighboring pixels. Thus, during rumor propagation, the prediction of user behavior is equivalent to the restoration of pixels in the mosaic image. Based on this inspiration, this study proposes a rumor propagation prediction model based on image restoration technology. First, we propose the concept of topic images and design the rumor2pixel algorithm to pixelate the topic of rumor propagation. Second, through the Generative Adversarial Network model, fuzzy pixels in the “rumor topic image” are compensated to learn more realistic rumor propagation trends. Finally, a dynamic approach for predicting the propagation of rumor and countering it based on evolutionary game theory is proposed, named Rumor-DPM (rumor dynamic propagation model). This approach is focused on reconstructing rumor images while taking into account the conflict between rumors and anti-rumors as well as its timeliness. The experimental findings demonstrate that this strategy can more accurately depict the internal dynamics between rumors and anti-rumors and effectively and successfully improve the ability to forecast user behavior throughout the rumor-propagation process.

Cognitive diagnosis (CD) aims to reveal the proficiency of students on specific knowledge concepts and traits of test exercises (e.g., difficulty). It plays a critical role in intelligent education systems by supporting personalized learning guidance. However, recent developments in CD mostly concentrate on improving the accuracy of diagnostic results and often overlook the important and practical task: domain-level zero-shot cognitive diagnosis (DZCD). The primary challenge of DZCD is the deficiency of student behavior data in the target domain due to the absence of student-exercise interactions or unavailability of exercising records for training purposes. To tackle the cold-start issue, we propose a two-stage solution named TechCD (Transferable knowledgE Concept grapH embedding framework for Cognitive Diagnosis). The fundamental notion involves utilizing a pedagogical knowledge concept graph (KCG) as a mediator to connect disparate domains, allowing the transmission of student cognitive signals from established domains to the zero-shot cold-start domain. Specifically, a naive yet effective graph convolutional network (GCN) with the bottom-layer discarding operation is initially employed over the KCG to learn transferable student cognitive states and domain-specific exercise traits. Moreover, we give three implementations of the general TechCD framework following the typical cognitive diagnosis solutions. Finally, extensive experiments on real-world datasets not only prove that Tech can effectively perform zero-shot diagnosis, but also give some popular applications such as exercise recommendation.

In recent years, fingerprint authentication systems have been extensively deployed in various applications, including attendance systems, authentications on smartphones, mobile payment authorizations, as well as various safety certifications. However, similar to the other biometric identification technologies, fingerprint recognition is vulnerable to artificial replicas made from cheap materials, such as silicon, gelatin, etc. Thus, it is especially necessary to distinguish whether a given fingerprint is a live or a spoof one prior to such authentication. In order to solve the problems above, a novel local descriptor named Weber local binary descriptor for fingerprint liveness detection (FLD) has been proposed in this paper. The method consists of two components: the local binary differential excitation component that extracts intensity-variance features and the local binary gradient orientation component that extracts orientation features. The co-occurrence probability of the two components is calculated to construct a discriminative feature vector, which is fed into support vector machine (SVM) classifiers. The effectiveness of the proposed method is intuitively analyzed on the image samples and numerically demonstrated by Mahalanobis distance. Experiments are performed on two public databases from FLD competitions from 2011 and 2013. The results have proved that the proposed method obtains the best detection accuracy among the existing image local descriptors in FLD.

In recent years, microblogging platforms have become good places to spread various spams, making the problem of gauging information credibility on social networks receive considerable attention especially under an emergency situation. Unlike previous studies on detecting rumors using tweets' inherent attributes generally, in this work, we shift the premise and focus on identifying event rumors on Weibo by extracting features from crowd responses that are texts of retweets (reposting tweets) and comments under a certain social event. Firstly the paper proposes a method of collecting theme data, including a sample set of tweets which have been confirmed to be false rumors based on information from the official rumor-busting service provided by Weibo. Secondly clustering analysis of tweets are made to examine the text features extracted from retweets and comments, and a classifier is trained based on observed feature distribution to automatically judge rumors from a mixed set of valid news and false information. The experiments show that the new features we propose are indeed effective in the classification, and especially some stop words and punctuations which are treated as noises in previous works can play an important role in rumor detection. To the best of our knowledge, this work is the first to detect rumors in Chinese via crowd responses under an emergency situation.

The paper proposed a new carrier frequency offset (CFO) estimation method for distributed line of sight (DLOS) millimeter wave MIMO systems. We assume a DLOS multipath MIMO channel with independent CFOs for both the transmitters and receivers. The proposed method consists of two stages. Firstly, with the assumption that only the target transmitter has CFO, while other transmitters don't have CFOs, the multi-dimensional estimation problem is reduced into one dimensional, based on which the new receiver model is deduced and the coarse CFO (CCFO) estimation algorithm is proposed. The residual CFOs are estimated after the equalizer with a multi-stages phase locked loop (MSPLL) approach. Simulation results show that the proposed method works well in the DLOS millimeter wave MIMO systems. There is nearly no performance loss due to the CFO impairments compared with Cramer-Rao bound at high signal to noise ratio (SNR).

A general parallel framework is presented in this paper for simplification of very large mesh models. This framework is implemented on a dedicated cluster. To guarantee not to thrash the virtual memory system, load balancing is performed in this framework by providing an intelligent partitioning of the inputting model using a parallel global sorting. This partitioning ensures a near optimal utilization of the computational resources, and then ensures high quality output, low runtime and high parallel efficiency. To test the usability of this framework, we have implemented a parallel version of an improved vertex clustering simplification. A serial of experimental results have demonstrated that using this framework the parallel simplification is memory efficient and can handle extremely large data set as well as speed up the execution obviously.