ABSTRACT Recommendation systems are rapidly evolving from static interaction‐driven models to dynamic, knowledge‐augmented architectures. A key challenge in this evolution is accurately capturing users' fine‐grained preferences from unstructured review text, which directly impacts the explainability and personalization of recommendations. As an essential enabling technology, Aspect‐Based Sentiment Analysis (ABSA) extracts aspect‐level sentiment elements that can be explicitly mapped to user preference vectors or product attribute ratings. With the integration of semantic and syntactic information, current works have significantly enhanced the performance of ABSA. However, existing graph‐based approaches that rely on dependency‐tree structures often converge to suboptimal solutions when handling implicit sentiment in natural language. To address this gap, we propose a graph fusion network that leverages augmented semantic and syntactic graphs. Specifically, we explicitly model word‐dependency correlations via contextual augmentation, and incorporate selected part‐of‐speech (POS) features to refine semantic graph construction. Concurrently, a syntactic graph is constructed by pruning the nodes based on the distance to the aspect term. The resulting semantic and syntactic representations are then fused through a dual graph convolutional network block, whereas the gating mechanism is used to regulate information flow during graph construction. Experiments on seven benchmarks demonstrate that our approach outperforms baselines by up to and in Macro‐F1 scores, establishing new state‐of‐the‐art results and providing a more reliable sentiment extraction module for downstream recommendation tasks.

Hardware Trojans may cause security issues in cyber-physical systems (CPSs), and recently proposed mutual auditing frameworks have helped build trustworthy CPSs with untrustworthy devices by requiring neighboring devices from different vendors. However, this may cause severe multi-vendor integration challenges, such as expensive, hard-to-maintain, and insufficient vendors to purchase devices. In this work, we improve the mutual auditing framework by maintaining the security of the CPSs with fewer vendors. First, the vendor-constrained security auditing framework is introduced to enhance the security of the CPS network with limited vendors, where side auditing detects the hardware Trojan collusion between neighboring nodes and infected node isolation stops the spread of active HTs. Second, a multi-agent cooperative reinforcement learning-based method is proposed to assign devices with proper vendors in the context of security auditing, and it provides solutions with a minimized number of offline nodes due to the HT infection. The experimental results show that our proposed method reduces the number of vendors needed by 40.95%, and only causes an increment of 0.39% infected nodes.

In the field of the Internet of Unmanned Agents (IUA), autonomous devices often struggle to maintain stability, adaptability, and coordination in dynamic environments. Current control strategies are hindered by difficulties such as real-time adaptation to environmental changes, handling sensor noise, and managing the coordination of multiple agents under complex, variable task constraints. These challenges limit the practical deployment of robots in IUA systems, making it crucial to develop more robust and efficient control methods. To address these issues, we propose a reinforcement learning-based impedance coefficient optimization approach to improve robots’ stability and responsiveness. By integrating impedance control, the Divergent Component of Motion (DCM) model, reinforcement learning (RL), and quadratic programming (QP), this approach dynamically adjusts the robot’s stiffness, damping, and inertia coefficients in real-time. Specifically, the Soft Actor-Critic (SAC) algorithm is used for optimization, while QP ensures that control forces remain feasible across multiple tasks and constraints. This strategy enhances the robots’ adaptability and coordination in complex IUA. Experimental results validate the approach, significantly improving robot performance in IUA systems.

Aspect-based sentiment analysis (ABSA) aims to identify specific sentiment elements in social multimedia content. To address aspect extraction and sentiment prediction together, recent studies have utilized a sequence tagging approach, mainly leveraging pretrained language models (PLMs) with specific architecture and auxiliary subtasks. However, these approaches often overlook task-related knowledge and struggle to scale across different domains. With advances in large language models (LLMs), there is a rising trend in constructing generative ABSA models. Nevertheless, these techniques tend to emphasize specific frameworks and overlook comprehensive knowledge representation. To address these challenges while leveraging the advantages of LLM and PLM-based methods, we propose a hybrid knowledge integration framework (HFABGKI). It employs a parameter-efficient fine-tuning technique, allowing for plug-and-play integration with existing LLMs. To bridge the LLM and PLM-based models, HF-ABGKI incorporates a global label semantic representation for potential aspect tokens, in which a simplified gating mechanism is proposed to filter useful information. Experimental results from six public social multimedia datasets demonstrate that our approach can accurately extract aspect terms and predict their sentiment polarity, achieving state-of-the-art performance compared to existing ABSA methods.

Failure recovery is one of the most essential problems in Internet of Things (IoT) systems, and the conventional snapshot method is an effective way to solve this problem. However, snapshot methods lack specialized designs for heterogeneous IoT devices, and when implemented in edge devices, serious system interruptions occur and performance is impacted. To address these problems, a dynamic checkpointing strategy is proposed for IoT systems that consist of heterogeneous devices. Firstly, an anomaly detection network for snapshots (i.e., ADSnet) that combines long short-term memory networks with multilayer convolutional networks is used to learn the multidimensional features of system resource usage. Secondly, ADSnet is tuned during deployment to learn the behaviors of target devices, so that ADSnet can report the anomalies of target devices in the near future. Finally, a dynamic checkpointing strategy is proposed to dynamically create snapshots on the basis of the anomaly detection results. The experimental results show that the proposed ADSnet achieves 97.73% accuracy in detecting anomalies in the target device; furthermore, our proposed dynamic checkpointing strategy reduces 25.4% snapshots than that created by the recently proposed ResCheck.

Weakly supervised referring expression grounding aims to train a model without the manual labels between image regions and referring expressions during the training phase. Current predominant models often adopt deep structures to reconstruct the region-expression correspondence. A crucial deficiency of the existing approaches lies in that these models neglect to exploit potential valuable information to further improve their grounding performance. To address this issue, we leverage knowledge distillation as a unique scheme to excavate and transfer helpful information for acquiring a better model. Specifically, we propose a target-guided knowledge distillation framework that accounts for region-expression pairs reconstruction and matching. We reactivate the target-related prediction information learned by a pre-trained teacher model and transfer the target-related prediction knowledge from the teacher to guide the training process and boost the performance of the student model. We conduct extensive experiments on three benchmark datasets, i.e., RefCOCO, RefCOCO+, and RefCOCOg. Without bells and whistles, our approach achieves state-of-the-art results on several splits of benchmark datasets. The implementation codes and trained models are available at: https://github.com/dami23/WREG_KD.

The ability to adapt their perception to changing environments is a core characterization of intelligent robots. At present, Unsupervised Domain Adaptation (UDA) methods are used to address this problem where the adaptation task is formulated as a transfer problem from a well-described scenario (source domain) to a new scenario (target domain). In order to implement the domain adaptation, these methods require access to the source data for achieving the distribution matching between both domains. However, in many real-world applications, the source data is inaccessible and only a source model pre-trained on the source domain is available during the transfer process. Therefore, the traditional UDA methods cannot support the challenging setting. This paper developed a new hypothesis transfer method to achieve model adaptation with gradual knowledge distillation. Specifically, we first prepare a source model through training a deep network on the labeled source domain by supervised learning. Then, we transfer the source model to the unlabeled target domain by self-training. To implement gradual knowledge distillation, we sliced the self-training into several epochs and then used the soft pseudo-labels from the latest epoch to guide the current epoch. In this process, the soft labels were generated by a semantic fusion on a proposed geometry of the neighborhood. To regulate the self-training, we developed a new objective constructed on the neighborhood. Experiments on three benchmarks have confirmed the state-of-the-art results of our method.

Registering a wrong hospital department is common when patients use on-line registering systems. Currently, there are some systems in practice. However, patients are unable to choose the best department due to different names and authorities of hospitals. To help solve the problem, we build a symptom-disease-disciplinary knowledge graph to recommend appropriate departments for patients. We obtain real disease-disciplinary information based on the regional health platform electronic health records (EHRs). Besides, we synthesize the symptom-disease relationship between ICD codes and medical encyclopedia websites. To further help the system predict the diseases based on patients' complaints, we update the weights of diseases through patients' choices in multi-round conversations. Experimental results show that the accuracy of final prediction is up to 92%.

Clinical text structuring is a critical and fundamental task for clinical research. Traditional methods such as task-specific end-to-end models and pipeline models usually suffer from the lack of dataset and error propagation. In this paper, we present a question answering based clinical text structuring (QA-CTS) task to unify different specific CTS tasks and make dataset shareable. A novel model that aims to introduce domain-specific features (e.g., clinical named entity information) into pre-trained language model is also proposed for QA-CTS task. Experimental results on Chinese pathology reports collected from Ruijing Hospital demonstrate our presented QA-CTS task is very effective to improve the performance on specific tasks. Our proposed model also competes favorably with strong baseline models in specific tasks.

Entity and relation extraction is the necessary step in structuring medical text. However, the feature extraction ability of the bidirectional long short term memory network in the existing model does not achieve the best effect. At the same time, the language model has achieved excellent results in more and more natural language processing tasks. In this paper, we present a focused attention model for the joint entity and relation extraction task. Our model integrates well-known BERT language model into joint learning through dynamic range attention mechanism, thus improving the feature representation ability of shared parameter layer. Experimental results on coronary angiography texts collected from Shuguang Hospital show that the F1-scores of named entity recognition and relation classification tasks reach 96.89% and 88.51%, which outperform state-of-the-art methods by 1.65% and 1.22%, respectively.

Electronic health record is an important source for clinical researches and applications, and errors inevitably occur in the data, which lead to severe damages to both patients and hospital services. One of such errors is the mismatch between diagnose and prescription, which we address as “medication anomaly” in the paper, and clinicians used to manually identify and correct them. With the development of machine learning techniques, researchers are able to train specific model for the task, but the process still requires expert knowledge to construct proper features, and few semantic relations are considered. In this paper, we propose a simple, yet effective detection method that tackles the problem by detecting the semantic inconsistency between diagnoses and prescriptions. Unlike traditional outlier or anomaly detection, the scheme uses continuous bag of words to construct the semantic connection between specific central words and their surrounding context. The detection of medication anomaly is transformed into identifying the least possible central word based on given context. To help distinguish the anomaly from normal context, we also incorporate a ranking accumulation strategy. The experiments were conducted on two real hospital electronic medical records, and the topN accuracy of the proposed method increased by 3.91 to 10.91% and 0.68 to 2.13% on the datasets, respectively, which is highly competitive to other traditional machine learning-based approaches.

Machine learning approaches have been widely used to tackle the problem of sensor array drift in E‐Nose systems. However, labeled data are rare in practice, which makes supervised learning methods hard to be applied. Meanwhile, current solutions require updating the analytical model in an offline manner, which hampers their uses for online scenarios. In this paper, we extended Target Domain Adaptation Extreme Learning Machine (DAELM_T) to achieve high accuracy with less labeled samples by proposing a Weighted Domain Transfer Extreme Learning Machine, which uses clustering information as prior knowledge to help select proper labeled samples and calculate sensitive matrix for weighted learning. Furthermore, we converted DAELM_T and the proposed method into their online learning versions under which scenario the labeled data are selected beforehand. Experimental results show that, for batch learning version, the proposed method uses around 20% less labeled samples while achieving approximately equivalent or better accuracy. As for the online versions, the methods maintain almost the same accuracies as their offline counterparts do, but the time cost remains around a constant value while that of offline versions grows with the number of samples.