The interconnection of electronic health devices through the Internet of Things (IoT) technology plays a crucial role in improving healthcare services. The existing schemes usually use traditional cryptographic algorithms and secret sharing to protect the privacy of user health data records generated by smart electronic devices. However, key transmission is exposed to the risk of leakage, and it is vulnerable to quantum attacks. To address these issues, this paper proposes a novel data privacy protection named Lattice-based Threshold Encryption for Data Privacy Protection with Zero Trust in Internet of Medical Things (LTEN-ZTIoMT). Specifically, this paper proposes a lattice-based encryption algorithm by introducing zero trust and threshold secret sharing in managing users and IoT devices, distributing private keys, thus enhancing the ability to resist quantum attacks in LTEN-ZTIoMT. To prevent tampering in transmitting private key sub-shares, this paper adopts the oblivious transfer protocol, where the private key sub-shares escrow only receives his select private key sub-shares without gaining other private key sub-shares information. Moreover, we design a dynamic authentication and authorization mechanism based on a whitelist, which enables the dynamic verification of IoT devices and the revocation of certificates. To prevent unauthorized users from accessing the private key sub-shares and data ciphertexts, we have introduced the token verification mechanism, in which the user identity can be verified by the private key sub-shares escrow. The formal security analysis in Scyther tool and theory analysis of the proposed scheme are provided. The thorough performance simulation experiments on private key share distribution, private key recovery, encryption, decryption, throughput, and energy consumption are conducted, demonstrating the effectiveness of the proposed LTEN-ZTIoMT.

Text representation models, such as Transformers and RNNs, are foundational to natural language processing research and play a crucial role in a wide range of downstream tasks. However, most existing large models rely on the self-attention mechanism, which involves frequent token interactions, a large parameter scale, and substantial hardware and data resource requirements—posing significant challenges for deployment on mobile and edge devices with limited computing power, high communication latency, or intermittent connectivity. To address these practical constraints, this study proposes an ultra- lightweight text representation model based on Causal Recurrent Convolutional Networks (CausalRCN), specifically engineered for efficient inference in resource-constrained mobile environments. Rather than introducing new atomic modules, our innovation lies in the systematic integration of causal convolution and self-enhancement mechanisms into a compact recurrent architecture that eliminates attention-driven computation entirely. By replacing self-attention with parallelized causal convolutions and recurrent feature propagation, the model achieves dramatically lower computational complexity and memory footprint, enabling real-time inference on commodity edge hardware. The design leverages local causality to approximate global contextual dependencies and employs feature self-enhancement to strengthen nonlinear expressiveness, effectively balancing accuracy and efficiency. Experimental results show that with only 666 K parameters, the proposed model achieves over 10× higher throughput and 50% less memory usage compared to competitive baselines, while improving accuracy by more than 1%. Validated on real-world platforms including Raspberry Pi 4B and Qualcomm Snapdragon Gen 1, the system demonstrates up to a 90× speedup over ALBERT in end-to-end latency, underscoring its suitability for mobile intelligent computing.

Deploying autonomous aerial vehicles (AAVs) as aerial base stations enhances the coverage and performance of communication networks in vehicular edge computing scenarios. However, due to the limited communication range and energy capacity of AAVs, they cannot continuously cover entire areas or sustain long flights. Therefore, achieving full communication coverage of a target area with a minimal number of AAVs and efficient task offloading remains a significant challenge. To address this problem, the AAV-assisted two-stage intelligent collaboration (UTIC) method is proposed in this article to tackle the joint position optimization and task scheduling issue. First, a AAV-assisted two-stage task scheduling system model is designed to optimize the allocation process. Second, an Enhanced Particle Swarm Optimization algorithm is designed to determine the optimal positions of AAVs, ensuring complete coverage of all mobile vehicles (MVs) with the minimum number of AAVs. Third, deep deterministic policy gradient method is employed to find the optimal scheduling decisions for MVs, considering energy consumption, delay, and task priorities. Simulation results demonstrate that the proposed UTIC method can achieve nearly 20% reduction in AAV deployment and outperform three other classical reinforcement learning algorithms in terms of reducing system cost.

The task of recognizing Chinese variant characters aims to address the challenges of semantic ambiguity and confusion, which potentially cause risks to the security of Web content and complicate the governance of sensitive words. Most existing approaches predominantly prioritize the acquisition of contextual knowledge from Chinese corpora and vocabularies during pretraining, often overlooking the inherent phonological and morphological characteristics of the Chinese language. To address these issues, we propose a shared-weight multimodal translation model (SMTM) based on multimodal information of Chinese characters, which integrates the phonology of Pinyin and the morphology of fonts into each Chinese character token to learn the deeper semantics of variant text. Specifically, we encode the Pinyin features of Chinese characters using the embedding layer, and the font features of Chinese characters are extracted based on convolutional neural networks directly. Considering the multimodal similarity between the source and target sentences of the Chinese variant-character-recognition task, we design the shared-weight embedding mechanism to generate target sentences using the heuristic information from the source sentences in the training process. The simulation results show that our proposed SMTM achieves remarkable performance of 89.550% and 79.480% on bilingual evaluation understudy (BLEU) and F1 metrics respectively, with significant improvement compared with state-of-the-art baseline models.

Enabling machines to possess commonsense reasoning within the intelligent Internet of Things (IoT) ecosystem plays a pivotal role in their capacity to attain autonomous decision-making and execution in complex tasks. The Winograd Schema Challenge (WSC) is a fundamental and challenging task in the field of commonsense reasoning, whose pairwise mutually exclusive properties and lack of contextual cues require machines with strong intelligence and skillful inference. Previous works that relied on pretrained models exhibited limited comprehension in commonsense because of overlooking the special property of the WSC task and solely relying on linguistic tendencies to learn superficial cues, failing to grasp the potential commonsense embedded within sentences. To address this issue, we propose a novel triple-wise perspective knowledge learning (TPKL) model for commonsense reasoning. Specifically, we introduce a new paradigm for addressing the WSC task by employing triplets instead of the conventional single or contrastive sentence inputs, which enables better compatibility with pairwise mutually exclusive features in WSC tasks. Additionally, we propose a triple-wise perspective that leverages anchor, positive, and negative sentences in a triplet construction to enable the model to comprehensively learn the pairwise mutually exclusive sentences, which can capture and utilize commonsense knowledge to distinguish between the various word senses under consideration. Extensive experiments conducted on three benchmark data sets demonstrate the superiority of our model over state-of-the-art baselines, improving PDP-60, WSC, and KnowRef benchmark with 3.3%, 4.4%, and 8.1%, respectively.

Text generation is an essential research area in artificial intelligence (AI) technology and natural language processing and provides key technical support for the rapid development of AI-generated content (AIGC). It is based on technologies such as natural language processing, machine learning, and deep learning, which enable learning language rules through training models to automatically generate text that meets grammatical and semantic requirements. In this paper, we sort and systematically summarize the main research progress in text generation and review recent text generation papers, focusing on presenting a detailed understanding of the technical models. In addition, several typical text generation application systems are presented. Finally, we address some challenges and future directions in AI text generation. We conclude that improving the quality, quantity, interactivity, and adaptability of generated text can help fundamentally advance AI text generation development.

Keyphrase generation (KG) is an essential problem in many natural language processing (NLP) tasks. Deep learning keyphrase generation methods often combine the copy and generating action-aware probabilities to model keyphrase accuracy, ignoring the copy and generating specificities for each keyword. In this work, we design a novel KG method that utilizes reinforcement learning (RL), namely KGAgent, where a relative reward based RL agent makes effective controllable manipulations on the decoupled action-aware policies to further improve the keyphrase generability. While RL is unstable and hard to train, several strategies, including momentum mechanism, distribution alignment and proximal policy optimization, are employed to stabilize the actor-critic network. Additionally, the proposed method reflects algorithm scalability that it can be plugged into any existing deep learning methods under different training paradigms, and consistently achieves higher accuracy than the state-of-the-art methods on the scientific article and social media datasets.

Keyphrase generation is one of the most fundamental tasks in natural language processing (NLP). Most existing works on keyphrase generation mainly focus on using holistic distribution to optimize the negative log-likelihood loss, but they do not directly manipulate the copy and generating spaces, which may reduce the generability of the decoder. Additionally, existing keyphrase models are either unable to determine the dynamic numbers of keyphrases or produce the number of keyphrases implicitly. In this article, we propose a probabilistic keyphrase generation model from copy and generating spaces. The proposed model is built upon the vanilla variational encoder-decoder (VED) framework. On top of VED, two separate latent variables are adopted to model the distribution of data within the latent copy and generating spaces, respectively. Specifically, we adopt a von Mises-Fisher (vMF) distribution to obtain a condensed variable for modifying the generating probability distribution over the predefined vocabulary. Meanwhile, we utilize a clustering module, which is designed to promote Gaussian Mixture learning and subsequently extract a latent variable for the copy probability distribution. Moreover, we utilize a natural property of the Gaussian mixture network and use the number of filtered components to determine the number of keyphrases. The approach is trained based on latent variable probabilistic modeling, neural variational inference, and self-supervised learning. Experiments on social media and scientific article datasets outperform the state-of-the-art baselines in generating accurate predictions and controllable keyphrase numbers.

Keyphrase generation (KG) aims at condensing the content from the source text to the target concise phrases. Though many KG algorithms have been proposed, most of them are tailored into deep learning settings with various specially designed strategies and may fail in solving the bias exposure problem. Reinforcement Learning (RL), a class of control optimization techniques, are well suited to compensate for some of the limitations of deep learning methods. Nevertheless, RL methods typically suffer from four core difficulties in keyphrase generation: environment interaction and effective exploration, complex action control, reward design, and task-specific obstacle. To tackle this difficult but significant task, we present RegRL-KG, including actor-critic based-reinforcement learning control and L1 policy regularization under the first principle of minimizing the maximum likelihood estimation (MLE) criterion by a sequence-to-sequence (Seq2Seq) deep learnining model, for efficient keyphrase generation. The agent utilizes an actor-critic network to control the generated probability distribution and employs L1 policy regularization to solve the bias exposure problem. Extensive experiments show that our method brings improvement in terms of the evaluation metrics on five scientific article benchmark datasets.

Text summarization on non-factoid question answering (NQA) aims at identifying the core information of redundant answer guidance using questions, which can dramatically improve answer readability and comprehensibility. Most existing approaches focus on extracting query-related sentences to construct a summary, where the logical connection of natural language and the hierarchical interpretable semantic association are often neglected, thus degrading performance. To address these issues, we propose a novel question-driven abstractive answer summarization model, called the H ierarchical S liding I nference G enerator (HSIG), to form inferable and interpretable summaries by explicitly introducing hierarchical information reasoning between questions and corresponding answers. Specifically, we first apply an elaborately designed hierarchical sliding fusion inference model to determine the most relevant question sentence-level representation that provides a deeper interpretable basis for sentence selection in summarization, which further increases computational performance on the premise of following the semantic inheritance structure. Additionally, to improve summary fluency, we construct a double-driven selective generator to integrate various semantic information from two mutual question-and-answer perspectives. Experimental results illustrate that compared with state-of-the-art baselines, our model achieves remarkable improvement on two benchmark datasets and specifically improves the 2.46 ROUGE-1 points on PubMedQA, which demonstrates the superiority of our model on abstractive summarization with hierarchical sequential reasoning.

Table-based fact verification aims to verify whether a statement sentence is trusted or fake. Most existing methods rely on graph feature or data augmentation but fail to investigate evidence correlation between the statement and table effectively. In this paper, we propose a self-Labeled Keypoint Alignment model, named LKA, to explore the correlation between the two. Specifically, a dual-view alignment module based on the statement and table views is designed to discriminate the salient words through multiple interactions, where one regular and one adversarial alignment network cooperatively character the alignment discrepancy. Considering the interaction characteristic inherent in the alignment module, we introduce a novel mixture-of experts block to elaborately integrate the interacted information for supporting the alignment and final classification. Furthermore, a contrastive learning loss is utilized to learn the precise representation of the structure-involved words, encouraging the words closer to words with the same table attribute and farther from the words with the unrelated attribute. Experimental results on three widely-studied datasets show that our model can outperform the state-of-the-art baselines and capture interpretable evidence words.

Keyphrase generation aims to generate a set of condensed phrases given a source document.Although maximum likelihood estimation (MLE) based keyphrase generation methods have shown impressive performance, they suffer from the bias on the source-prediction pair and the bias on the prediction-target pair.To tackle the above biases, we propose a novel correction model CorrKG on top of the MLE pipeline, where the biases are corrected via the optimal transport (OT) and a frequency-based filtering-and-sorting (FreqFS) strategy.Specifically, OT is introduced as the soft correction to facilitate the alignment of salient information and rectify the semantic bias on the source document and predicted keyphrases pair.An adaptive semantic mass learning scheme is conducted on the vanilla OT to achieve a proper pair-wise optimal transport procedure, which promotes the OT calculation brought by rectifying semantic masses dynamically.Besides, the FreqFS strategy is designed as the hard correction to reduce the bias of predicted and target keyphrases, and thus generate accurate and sufficient keyphrases.Extensive experiments over multiple benchmark datasets show that our model achieves superior keyphrase generation as compared with the state-of-the-arts.

Leveraging watchtowers to monitor payment channel networks (PCNs) is regarded to be a promising option to ensure off-chain transaction security and boost cryptocurrency scalability. However, existing solutions have two major limitations: First, since the watchtower’s inaction or collusion with counterparties, the deposits in off-chain transactions will be threatened; Second, due to occasional false positives, the efficiency of the single watchtower in monitoring the payment channels for fraud is questionable. To solve this, we present anti-collusion multiparty smart contracts for distributed watchtowers in PCNs. Specifically, we first design the distributed watchtower mechanism to solve the false positive problem in regulating PCNs. In addition, we utilize smart contracts to constrain and force counterparties to relinquish collusion in the distributed watchtower mechanism, thus making collusion impossible for rational parties. We further offer a mathematical proof and contract implementation in Solidity. Finally, extensive experiments and contracts executed on Ethereum under various benchmarks with baseline comparison demonstrate the validity of our proposals. Specifically, our scheme can both improve the throughput and accuracy by up to 20-25% and 10-15%, respectively, and reduce the false positive rate by up to 10% compared with existing single watchtower mechanism.

Stance detection on social media aims to identify the stance of social media users toward a topic or claim, which can provide powerful information for various downstream tasks. Many existing stance detection approaches neglect to model the deep semantic representation information in tweets and do not explore aggregating the hierarchical features among words, thus degrading performance. To address these issues, this article proposes a novel deep learning approach P retrained E mbeddings for Stance Detection with H ierarchical C apsule N etwork (PE-HCN) without complicated preprocessing. Specifically, PE-HCN first adopts a pretrained language model and then uses a related textual entailment task for fine-tuning to obtain the deep textual representations of tweets. The PE-HCN approach extends the dynamic routing scheme to cope with these deep textual representations by utilizing primary capsules for routing the information among words in each tweet and applying secondary capsules to transmit the aggregated features to each category capsule accordingly. Moreover, to improve the confidences of the category capsules, we design an adaptive feedback mechanism to dynamically strengthen the routing signals. Through experiments on three benchmark datasets, compared with the state-of-the-art baselines, the extensive results exhibit that PE-HCN achieves competitive improvements of up to 6.32%, 2.09%, and 1.8%, respectively.

Dual-Structural Network (DSN), pioneered by our group for content sharing, is a networking paradigm with the Internet as primary structure and the broadcast-storage network (BSN) as secondary structure. In order to quantitatively evaluate its content sharing capability, in this paper, we generally adopt a deductive methodology, namely that DSN is formalized as a complex network and then its sharing capability is derived according to graph theory. In specific, according to bipartite graph theory, we first construct a bipartite dual-structural network model to obtain an abstract content sharing graph through top-down projection, and then content sharing hops (CSH) in the graph is capitalized as a metric to evaluate the sharing capability between any two content nodes. Furthermore, we leverage the general random graph theory to generate the sharing graph for deriving quantitative upper bounds on average content sharing hops (ACSH) and maximum content sharing hops (MCSH) of DSN. Lastly, the theoretical derivations are validated by numerical simulation. Moreover, compared with content delivery network (CDN), content centric network (CCN) and information-centric mobile ad hoc networks (ICMANET), DSN is demonstrated to be superior in terms of the sharing capability.

Recommendation systems, as efficient measures to handle the information overload and personalized service problems, have attracted considerable attention in research community. Collaborative filtering is one of the most successful techniques based on the user-item matrix in recommendation systems. Usually the matrix is extremely sparse due to the massive number of users and items. And the sparsity of users and items tends to differ significantly in degree. The feature of the matrix changes with the variation of users/items data and hence, leads to poor scalability of the recommendation method. This paper proposes a dynamic-weighted collaborative filtering approach (DWCF) to address sparsity and adaptivity issues. In this approach, the relationship between the distributions of similar users and items is considered to get better recommendation, i.e., the contributions of the user part and the item part to recommendation results depend on their similarity ratios. Moreover, the effect strength of different parts is controlled by an averaging parameter. Experiments on MovieLens dataset illustrate that the DWCF approach proposed in this paper can obtain good recommendation result given different conditions of data sparsity and perform better than a user-based predictor, an item-based predictor and a conventional hybrid approach.