Skip Content
You are currently on the new version of our website. Access the old version .

Applied Sciences

Applied Sciences is an international, peer-reviewed, open access journal on all aspects of applied natural sciences published semimonthly online by MDPI.

Quartile Ranking JCR - Q2 (Engineering, Multidisciplinary)

All Articles (85,094)

Emotion recognition in conversations (ERC) is a significant task in natural language processing, aimed at identifying the emotion of each utterance within a conversation. Current research predominantly relies on pre-trained language models, often incorporating sophisticated network architectures to capture complex contextual semantics in conversations. However, existing approaches have not successfully combined effective task-specific adaptation with adequate modeling of conversational context complexity. To address this, we propose a model named TAMC-ERC (Task-Adaptive and Multi-level Contextual Understanding for Emotion Recognition in Conversations). The model adopts a progressive recognition framework that sequentially builds on foundational utterance representations, integrates conversation-level contexts, and leads to a task-adaptive classification decision. First, the Task-Adaptive Representation Learning module produces highly discriminative utterance representations. It achieves this by integrating emotion space information into prompts and employing contrastive learning. Subsequently, the Multi-Level Contextual Understanding module performs in-depth modeling of the conversational context. It synergistically integrates both macroscopic narratives and microscopic interactions to construct a comprehensive emotional context. Finally, the classifier is directly parameterized by the emotion concept vectors from the task-adaptive stage. This creates a coherent task adaptation process, maintaining task-specific awareness from representation learning through to the final decision. Experiments on three benchmark datasets demonstrate that TAMC-ERC achieves highly competitive performance: it attains weighted average F1 scores of 71.04% on IEMOCAP, 66.95% on MELD, and 40.99% on EmoryNLP. These results set a new state of the art and demonstrate that the model outperforms most existing baselines. This work validates that integrating task adaptation with multi-level contextual modeling is key to addressing conversational complexity and improving recognition accuracy.

9 February 2026

The overall architecture of the TAMC-ERC model.

The issue of microplastics in the aquatic environment has become one of the key topics in contemporary environmental engineering, chemical engineering and materials technology. Plastic microparticles are found not only in natural waters, but also in industrial and municipal piping systems, process installations and even in drinking water, posing a growing threat to public health, ecosystem stability and the reliability of technical equipment. Due to its chemical resistance, hydrophobicity and variety of sizes and shapes, microplastics are difficult to remove using traditional separation methods, and their harmful impact is part of a broader analysis of the life cycle of plastics, from their production and use to the waste phase and their impact on the environment. In response to the scale of the phenomenon, a number of liquid–solid separation methods have been developed, including approaches based on physical, chemical and biological principles. These methods vary in their scope of application, operational requirements and the way they interact with the particles present in the flow. The scientific literature describes mechanical techniques, chemical reactions and the interaction of biological organisms in a controlled environment as the main groups of separation. Each group has specific limitations resulting from the properties of microplastics, flow conditions and medium characteristics, which means that the choice of separation technology must take into account the specific nature of the system in question. The development of advanced measurement methods, monitoring systems and control techniques enables more accurate observation and analysis of particle movement, as well as the study of the relationship between device operating parameters and the behaviour of contaminants in the flow. The increasingly widespread use of measurement data, predictive algorithms and pattern recognition techniques makes it possible to describe the phenomena accompanying microplastic separation in greater detail and to formulate new concepts for devices and flow systems based on analytical methods, computational tools and adaptive control systems is in line with current trends in process engineering and automation, as well as with the concept of Industry 4.0. Taking the above information into account, the aim of this work is to analyse selected liquid–solid separation methods in order to identify the most optimal in terms of the effectiveness of removing plastic microparticles, with the assumption of the greatest possible number of features indicating the possible future automation of a given process.

9 February 2026

Articulated Tug-Barge systems connect a tugboat and a barge via an articulated link, improving manoeuvrability and flow, and offering opportunities for greater efficiency. Due to their size, these systems are vital to waterborne cargo distribution, managing the transport of several types of oil, chemicals, and bulk goods, as well as container barges. The interest in these systems is driven by the rising demand for energy efficiency and environmentally friendly maritime transport. Analysing reliability, costs, environmental and operational conditions, and crew experience helps manage each design option more effectively. The dual-mode Articulated Tug-Barge (ATB) system can disconnect the tug from the barge when seaway loads reach design limits. Effective load management and real-time monitoring are essential in these situations. This research introduces a method for evaluating barge efficiency using a structural reliability index and associated costs, accounting for environmental conditions, operational scenarios, and crew experience. The reliability index assesses the barge’s hull integrity, accounting for environmental pollution from oil spills and air emissions from construction and operation, as well as crew proficiency. The chosen design, operational status, crew experience, hull failure progression, and their effects on structural integrity, along with impacts on the ship, cargo, and environment from construction, voyages, and cleaning, are all incorporated into the cost analysis. Mitigating risk measures focus on improving the crew experience, directly reducing costs and enhancing reliability without requiring additional structural materials to increase strength.

9 February 2026

Underground saturated jointed rock is prone to engineering geohazards under the combined effects of in situ stress and dynamic loading. A modified split Hopkinson pressure bar (SHPB) system was used to conduct dynamic loading tests on artificially fabricated saturated jointed rocks. The effects of joint matching coefficient (JMC) and confining pressure on the dynamic strength, deformation characteristics, energy evolution, and stress wave propagation of the specimens were investigated. The test results show that the dynamic compressive strength and stiffness of saturated jointed rocks increase with the increase in JMC, but the compressive strength is still lower than the typical dynamic strength range. Rock damage mainly occurs at the joint location, and the damage mode is dominated by tensile fracture. In terms of energy, the energy dissipation rate of the rock decreases with decreasing JMC and increasing confining pressure. The propagation of stress waves is mainly affected by the coupling of JMC and three-dimensional static stress, which is manifested as a transition from a rapidly changing phase to an unstable changing phase, a process accompanied by an energy distribution mechanism. These insights fill a gap in the mechanical response of saturated jointed rocks under complex loading conditions underground and help predict the risk of dynamic instability in underground engineering and mining operations.

9 February 2026

News & Conferences

Issues

Open for Submission

Editor's Choice

Reprints of Collections

Feature Paper Collection in the Section ‘Energy Science and Technology’
Reprint

Feature Paper Collection in the Section ‘Energy Science and Technology’

Editors: Demis Pandelidis, Katrzyna Wartalska, Martyna Grzegorzek
Cosmetics Ingredients Research
Reprint

Cosmetics Ingredients Research

Editors: Anna Waszkielewicz

Get Alerted

Add your email address to receive forthcoming issues of this journal.

XFacebookLinkedIn
Appl. Sci. - ISSN 2076-3417