This paper reviews the recent and most impactful advancements in the application of artificial neural networks in modeling the properties of ionic liquids. As salts that are liquid at temperatures below 100 °C, ionic liquids possess unique properties beneficial for various industrial applications such as carbon capture, catalytic solvents, and lubricant additives. The study emphasizes the challenges in selecting appropriate ILs due to the vast variability in their properties, which depend significantly on their cation and anion structures. The review discusses the advantages of using ANNs, including feed-forward, cascade-forward, convolutional, recurrent, and graph neural networks, over traditional machine learning algorithms for predicting the thermodynamic and physical properties of ILs. The paper also highlights the importance of data preparation, including data collection, feature engineering, and data cleaning, in developing accurate predictive models. Additionally, the review covers the interpretability of these models using techniques such as SHapley Additive exPlanations to understand feature importance. The authors conclude by discussing future opportunities and the potential of combining ANNs with other computational methods to design new ILs with targeted properties.
Although there are several methods for fabricating nanofibrous scaffolds for biomedical applications, electrospinning is probably the most versatile and feasible process. Electrospinning enables the preparation of reproducible, homogeneous fibers from many types of polymers. In addition, implementation of this technique gives the possibility to fabricated polymer-based composite mats embroidered with manifold materials, such as graphene. Flake graphene and its derivatives represent an extremely promising material for imparting new, biomedically relevant properties, functions, and applications. Graphene oxide (GO) and reduced graphene oxide (rGO), among many extraordinary properties, confer antimicrobial properties of the resulting material. Moreover, graphene oxide and reduced graphene oxide promote the desired cellular response. Tissue engineering and regenerative medicine enable advanced treatments to regenerate damaged tissues and organs. This review provides a reliable summary of the recent scientific literature on the fabrication of nanofibers and their further modification with GO/rGO flakes for biomedical applications.
4 April 2024 in IEEE Transactions on Nanotechnology
The production and verification of microwave absorbers are a subject of high priority. These are due to the fast development of telecommunication technologies and the need to reduce electromagnetic pollution. Such materials are implementable in multiple industries, including military, medical, and laboratory equipment. One should remember that the desired material should exhibit a high total shielding effectiveness SE $_{T}$ and controllable performance properties. In this work, an ultrathin graphene oxide paper is fabricated and verified as a wide-range, controllable microwave absorber. Stepwise (100 $^\circ$ C – 200 $^\circ$ C – 300 $^\circ$ C) thermally reduced G-Flake graphene oxide paper of 4.95 μm thickness revealed the conductivity of 1.86 S/cm. A mild level of reduction was proven with combustion elemental analysis, resulting in a 22.4 oxygen percentage (50.9 % before the reduction). Raman spectroscopy suggested the limitation of Stone-Wales defects after heat treatment. Microwave absorption was measured in the W-band frequency region, and the SE$_{T}$/t parameter reached 606 dB/mm for a c.a. 5-μm-thick individual reduced paper sheet. The controlled increase in conductivity resulted in conduction losses, and the occurrence of pores enabled scattering, while the absorption remained the primary shielding mechanism.
Query performance prediction (QPP) is a technique for evaluating the retrieval quality of a search system for a given query without relying on human relevance judgment. Recently, large language models (LLMs) presented a promising avenue for this task. However, while existing pointwise methods have proven effective, they do not fully exploit the potential advantages offered by comparative analyses, such as pairwise comparisons between retrieved elements. Our study evaluates the suitability of these approaches for post-retrieval, LLM-based QPP. We conducted a comprehensive analysis comparing LLMs’ (Llama-3.1-8B-Instruct and Qwen3-8B) outputs with human-judged performance using correlations of metrics such as NDCG@10 and RR@10 and assessed computational efficiency regarding the number of LLM inferences. When evaluated on the correlation between actual retrieval performance and performance predicted by LLM methods, nearly all pairwise approaches outperform the pointwise baseline in the setting without fine-tuning, and in selected fine-tuning scenarios. Furthermore, pairwise approaches show substantially higher correlation with the ANCE retriever, while their correlation with BM25 varies across methods, with some exhibiting stronger alignment and others performing similarly or worse than the pointwise method. Our approach reduces computational complexity by introducing comparisons only against a selected subset of reference items.