In this research, an oxidative chemical copolymerization was employed to develop a composite based on porous graphitic carbon nitride (CN) coated with PANi/PPy (PP) copolymer. The objective was to create a synergy between the two organic and inorganic polymeric constituents to maximize the sorption efficiency of the resulting composite towards diclofenac sodium (DC) as a representative emerging contaminant. The as-fabricated CN@PP-1 composite was used as an adsorbent for decontaminating aquatic systems from DC. The maximum quantity of DC adsorbed at 298 K was found to be 308.12 mg/g. The maximum DC removal percentage of 95.09% was achieved for 20 mg/L of DC using 0.35 g/L of CN@PP-1 dose at pH 4 for 180 min. The Elovich model (R2 = 0.994, χ2 = 1.318 and RMSE = 1.148) and the Redlich-Peterson isotherm model (R2 = 0.995, χ2 = 54.747 and RMSE = 7.399) provided the best fit to the kinetic equilibrium data, respectively. The thermodynamic parameters indicated that the DC adsorption by CN@PP-1 was physical in nature and occurred spontaneously. The adsorption mechanism of DC onto CN@PP-1 is primarily driven by π-π stacking and hydrogen bonding. After five cycles, the CN@PP-1 maintained a good DC adsorption efficiency of 72.22%, thus confirming its excellent recyclability. Moreover, modeling and prediction of DC removal were carried out using artificial neural networks. The ANN model demonstrated excellent capability for predicting complex and nonlinear adsorption systems.
This review provides a comprehensive analysis of sEMG-IMU sensor fusion techniques for upper limb movement pattern recognition. It offers detailed insights into the signal generation mechanisms of both surface electromyography (sEMG) and inertial measurement units (IMU), and critically explores multisensory fusion strategies aimed at enhancing recognition accuracy and reliability. Key stages in the pattern recognition process, including signal acquisition, signal pre-processing, feature extraction and learning, are systematically examined. Significant advancements in tasks including hand gesture recognition (HGR), hand sign language recognition (HSLR), human activity recognition (HAR), joint angle estimation (JAE), and force/torque estimation (FE/TE) are discussed, emphasizing the role of sEMG-IMU integration in achieving improved performance. The review further explores the practical applications of these technologies in areas such as rehabilitation, prosthetic control, and human–machine interaction (HMI). Finally, this review identifies the main challenges in sEMG-IMU sensor fusion and proposed potential future research directions, focusing on overcoming current limitations and advancing the development of more robust and accurate sensor fusion models.
To generate accurate and reliable predictions, modern AI systems need to combine data from multiple modalities, such as text, images, audio, spreadsheets, and time series. However, collecting training and test data for many modalities is challenging and time-consuming, creating a need for cost-efficient multi-modal data acquisition. In this paper we advocate that this can be realized by disentangling epistemic and aleatoric uncertainty. It is commonly assumed in the machine learning community that epistemic uncertainty can be reduced by collecting more data, while aleatoric uncertainty is irreducible. We claim that this assumption can be challenged in modern multi-modal AI systems, and we introduces an innovative data acquisition framework where uncertainty disentanglement leads to actionable decisions, allowing cost-efficient sampling in two directions: sample size and data modality. The main hypothesis is that aleatoric uncertainty decreases as the number of modalities increases, while epistemic uncertainty decreases by collecting more observations. We provide a theoretical analysis and proof-of-concept implementations on various multi-modal datasets to prove the usefulness of our framework, which combines ideas from active learning, active feature acquisition and uncertainty quantification.
Recent advancements in machine learning have emphasized the need for transparency in model predictions, particularly as interpretability diminishes when using increasingly complex architectures. In this paper, we propose leveraging prediction uncertainty as a complementary approach to classical explainability methods. Specifically, we distinguish between aleatoric (data-related) and epistemic (model-related) uncertainty to guide the selection of appropriate explanations. Epistemic uncertainty serves as a rejection criterion for unreliable explanations and, in itself, provides insight into insufficient training (a new form of explanation). Aleatoric uncertainty informs the choice between feature-importance explanations and counterfactual explanations. This leverages a framework of explainability methods driven by uncertainty quantification and disentanglement. Our experiments demonstrate the impact of this uncertainty-aware approach on the robustness and attainability of explanations in both traditional machine learning and deep learning scenarios.
This paper investigates automated skill decomposition using Large Language Models (LLMs) and proposes a rigorous, ontology-grounded evaluation framework. Our framework standardizes the pipeline from prompting and generation to normalization and alignment with ontology nodes. To evaluate outputs, we introduce two metrics: a semantic F1-score that uses optimal embedding-based matching to assess content accuracy, and a hierarchy-aware F1-score that credits structurally correct placements to assess granularity. We conduct experiments on ROME-ESCO-DecompSkill, a curated subset of parents, comparing two prompting strategies: zero-shot and leakage-safe few-shot with exemplars. Across diverse LLMs, zero-shot offers a strong baseline, while few-shot consistently stabilizes phrasing and granularity and improves hierarchy-aware alignment. A latency analysis further shows that exemplar-guided prompts are competitive–and sometimes faster–than unguided zero-shot due to more schema-compliant completions. Together, the framework, benchmark, and metrics provide a reproducible foundation for developing ontology-faithful skill decomposition systems.
