Interaction Scenarios Research Articles

Optimization of Interaction with Counterparties: Selection Game Algorithm under Uncertainty

The purpose of this study is to develop a comprehensive algorithm for optimizing the interaction of economic entities with counterparties, taking into account the uncertainty of market conditions and the variety of behavioral strategies of participants. The developed algorithm aims to increase the stability and efficiency of the interactions between the economic entity under study and its counterparties, minimizing risks and optimizing cooperative and competitive strategies within the framework of existing market relations. The methodology uses game theory to devise interaction strategies using mutual influence indices, non-cooperative game principles, and payment matrices. The model analyzes various interaction scenarios with counterparties by using payment matrices and considering both competitive and cooperative conditions. The research methodology is supplemented by the calculation of integral estimates based on a set of financial and economic indicators, enabling the assessment of the impact of various interaction strategies on the overall efficiency of an economic entity. After testing the developed models, a set of data was obtained, which can be used to optimize strategic planning and manage the interaction of economic entities with counterparties. The developed algorithm is an effective tool for improving the operational analysis of enterprises, primarily in industrial sectors.

Plume‐Driven Subduction Termination in 3‐D Mantle Convection Models

AbstractThe effect of mantle plumes is secondary to that of subducting slabs for modern plate tectonics when considering plate driving forces. However, the impact of plumes on tectonics and planetary surface evolution may nonetheless have been significant. We use numerical mantle convection models in a 3‐D spherical chunk geometry with damage rheology to study some of the dynamics of plume‐slab interactions. Substantiating our earlier 2‐D results, we observe a range of interaction scenarios, and that the plume‐driven subduction terminations we had identified earlier persist in more realistic convective flow. We analyze the dynamics of plume affected subduction, including in terms of their geometry, frequency, and the overall effect of plumes on surface dynamics as a function of the fraction of internal to bottom heating. Some versions of such plume‐slab interplay may be relevant for geologic events, for example, for the inferred ∼183 Ma Karoo large igneous province formation and associated slab disruption. More recent examples may include the impingement of the Afar plume underneath Africa leading to disruption of the Hellenic slab, and the current complex structure imaged for the subduction of the Nazca plate under South America. Our results imply that plumes may play a significant role not just in kick‐starting plate tectonics, but also in major modifications of slab‐driven plate motions, including for the present‐day mantle.

А comprehensive approach to managing robot group formation

Subject matter: Research and development of methods for controlling swarms of unmanned aerial vehicles (UAVs) based on the "master – slave" model. This includes examining existing classifications and interactions between unmanned aerial vehicles in various formations such as groups, flocks, associations, and swarms, with the goal of creating an effective management system. Goal To improve the quality of interaction between unmanned aerial vehicles based on the "master – slave" model during flight missions through constant control between objects. Ensuring reliable execution of flight missions by implementing new management methods that account for different modes of interaction between devices. Tasks: Analyze the classification of existing UAVs; analyze the parameters and model of interaction of unmanned aerial vehicles in existing groups, flocks, associations, swarms; create a scenario of interaction between two UAVs based on the "master – slave" model; develop a program for visualizing the flight of unmanned aerial vehicles based on the "master – slave" model; conduct flight testing according to the proposed model on stages with various geospatial objects. Methods: Simulation method for developing a UAV flight visualization subsystem; graphical modeling method for creating an aircraft-type unmanned aerial vehicle model; methods of algorithm theory for developing a scenario of interaction between two UAVs. Utilization of specialized software tools for visualization and simulation of UAV behavior in real-time conditions. Results: Developed a classification of unmanned aerial vehicles; created a graphical model of the Mini-Flight-M aircraft; developed a scheme for the interaction of two UAVs in "teacher" or "mentor" modes; created a program for visualizing the flight of UAVs based on the "master – slave" model; conducted flight testing according to the proposed model on stages with various geospatial objects. The results confirmed the effectiveness of the developed model and demonstrated its applicability in various fields, including environmental monitoring, rescue operations, and other autonomous missions. Conclusions: The proposed approach to controlling a UAV swarm based on the "master – slave" model improves the quality of interaction between the devices and ensures reliable execution of flight missions. Further research should focus on optimizing energy consumption and ensuring reliable communication between swarm agents. It is also important to develop methods for protecting UAV swarms from cyberattacks and other threats to enhance their resilience and reliability during complex missions.

The Future of Speech Therapy for Autism: Bridging Technology and Personalized Care

Researchers have been working on autism since the 1980s [1]. Autism spectrum disorder (AUD) is a complex neurodevelopment condition that affects people's interaction with others, behavior, communication, and social interaction. Although autism may be a lifelong condition, appropriate support, services, and treatments can improve a person's symptoms and daily functioning. Individuals with autism often face challenges with speech and language development are prominent. Speech therapy (ST) plays a role in gaining control over verbal communication. An effective speech therapy can enhance the quality of life by addressing communication difficulties. Traditionally, the treatment of autism has a multidisciplinary approach that aims to address the diverse needs of individuals on the spectrum. Advancements in technology are revolutionizing the field by offering various possibilities for personalized care and improved outcomes. Healthcare professionals diagnose autism by assessing a person's development patterns and behaviors. Currently, speech therapy is delivered through face-to-face interactions with a trained therapist. Because parents of autistic children consistently identify language and social communication skills as a top priority. This approach has limitations, like scheduling conflicts, limited access to geographical constraints, and specialized care [2]. Telepractice platforms and virtual reality systems (VR), offer novel opportunities for accessible, personalized, and engaging therapy experiences. Telepractice is an online therapy service via technology-based platforms that allows long-distance interventions, breaking geographical barriers and expanding access to specialized care. Specifically, telepractice capitalized on communication practices such as video conferencing, and data tracking tools to facilitate effective communications and reduce barriers like distance. It is a very effective and low-cost method for conducting and completing online sessions for individuals with autism spectrum disorder [3]. The use of mobile technology in various countries become a necessity in the lives of people and also makes it a potential medium of intervention for people diagnosed with autism. It also enhances social skills, language development, and communication abilities. Virtual reality is an essential tool for healthcare intervention, offering realistic scenarios for practicing communication strategies and social interaction. Virtual reality interventions can lead to more stable and faster communication skills over time [4]. Advancements in artificial intelligence has enabled therapists to analyze data and identify patterns to meet the unique needs of each individual with autism. Technology is poised to facilitate collaboration and communication among individuals, and promote consistency across various settings. Researchers are involved in creating and training robots to interact with autistic children. We can empower individuals with autism to reach their full communication potential with the help of these latest technologies.

Rhizomic Interdisciplinary Model in the Research into the Phenomenon of “New Sincerity”

The article localizes the problem of interscientific system methodology in the study of a new social practice domain, which manifests itself in the form of the trend towards sincerity and frankness in language interaction. The purpose of the article is to consider the issues that arise within the overlapping scientific approaches in the context of polyparadigmality in linguistics. The article describes vectors and scenarios of discipline interaction, as well as the examples of interdisciplinary transfer practice. The author presents the concept of rhizomic interdisciplinarity as a nonlinear development of scientific research that contains the potential for differentiation and integration. The system methodology application has enabled the author to build the core part of the model for describing linguistic facts. It includes some clusters of scientific knowledge that are undergoing a development phase. The article outlines the problems of “new sincerity” with an emphasis on network communication. For illustration, data from social events with elements of a flash mob, cases of cancel culture and eco-alarmism were used. The patterns that form a social community in the form of thematic fashion, Internet communication algorithms, and mobilizing potential are indicated. The author presents several clusters of research into the phenomenon of “new sincerity” from the perspective of the science of language. Being indicative of the dynamics of interaction amongst currently existing approaches and theories, they can form the core of the research model.

Analysis of visual communication elements in variable font design from the perspective of digital technology

With the maturity of digital technology, the effectiveness of information transmission has received extensive attention. Variable font design is regarded as an extension of graphic design in digital media art, and variable font design is studied from the perspective of information communication design. From the perspective of digital technology, based on the research theory of variable information communication design, combined with the specific methods of font design, the perception, cognitive methods, and aesthetic laws of aesthetic subject vision and psychology in the field of font variable design are discussed. Provide relevant theoretical support for information communication design activities with variable fonts. Based on artificial intelligence technology, a new interactive art expression method is proposed. By analyzing the main expression scenarios of interactive art, namely user information communication scenarios, interactive art push scenarios, interactive art promotion scenarios and personal service scenarios, it provides a scenario application basis for interactive expression, calculate the space complexity, space complexity and resource complexity, according to the complexity calculation results, carry out interaction design from three aspects of visual elements, multimedia elements, and human-computer interaction elements, integrate the topology structure after the interaction is realized, and in the network topology structure. The proposed model consists mainly of visual design, basic design elements, basic visual design, complete design and solution generation. It realizes the expression of interactive art of multimedia elements in display and control. The experimental results show that the interactive element extraction speed of the visual communication expression method based on artificial intelligence technology is increased by 30%, and the flexibility is stronger.

The 33 M⊙ black hole Gaia BH3 is part of the disrupted ED-2 star cluster

Context. The Gaia Collaboration has recently reported the detection of a 33 M⊙ black hole in a wide binary system located in the solar neighbourhood. Aims. Here we explore the relationship between this black hole, known as Gaia BH3, and the nearby ED-2 halo stellar stream. Methods. We studied the orbital characteristics of the Gaia BH3 binary and present measurements of the chemical abundances of ED-2 member stars derived from high-resolution spectra obtained with the VLT. Results. We find that the Galactic orbit of the Gaia BH3 system and its metallicity are entirely consistent with being part of the ED-2 stream. The characteristics of the stream, particularly its negligible spread in metallicity and in other chemical elements, as well as its single stellar population, suggest that it originated from a disrupted star cluster of low mass. Its age is comparable to that of the globular cluster M92 that has been estimated to be as old as the Universe. Conclusions. This is the first black hole unambiguously associated with a disrupted star cluster. We infer the plausible mass range for the cluster to be relatively narrow, between 2 × 103 M⊙ and 5.2 × 104 M⊙. This implies that the black hole could have formed directly from the collapse of a massive very metal-poor star, but that the alternative scenario of binary interactions inside the cluster environment also deserves to be explored.

MANAGEMENT OF THE SDGs ACHIEVEMENT PROCESS IN LNTU SCIENTIFIC ACTIVITIES

The article is devoted to considering green standards for scientific research activities, and a system of priority measures and the achievement of key performance indicators reasoning. A self-assessment of SDGs achievement according to Green standards at LNTU in 2023 has been conducted, which includes environmental, social, and economic responsibility, as well as components of education and research. The hypothesis of the consistency of experts' views during the self-assessment of compliance with green standards of scientific activities has been proven by the Kendall concordance coefficient.The results of the self-assessment of compliance with green standards of scientific activities at LNTU are the basis for forming strategic actions to achieve SDGs. A methodology for forming an archetypal scenario of interaction between LNTU and SDGs has been proposed for use: tolerant, uncommitted, paternalistic, or transformational. The implementation of the transformational archetypal scenario of interaction between LNTU contains priorities for improving policies and plans.

Physical Robots in Education: A Systematic Review Based on the Technological Pedagogical Content Knowledge Framework

Driven by the wave of artificial intelligence, the educational practice and application of robots have become increasingly common. Despite extensive coverage in the literature on various aspects of educational robots, there are still unexplored avenues, particularly regarding robotic support, robotic personality, and challenges in their applications. This study presented a systematic review of high-quality empirical research on the use of physical robots in educational settings. A total of 92 relevant papers from the Web of Science database were analyzed. Employing the technological pedagogical content knowledge (TPCK) framework, we investigated research questions across seven components, including the learning domain, teaching strategy, robot types, learning results, problems with using robots, robotic support, and robotic personality. The findings revealed that robots are most prevalently employed in language learning applications. When opting for teaching strategies, educators tend to favor those that incorporate physical interaction. Concurrently, humanoid robots emerge as the preferred choice among many. These robots, in human–robot interaction scenarios, often exhibit an agreeable personality. In terms of evaluating learning results, cognitive aspects like thinking, creativity, self-regulation, and inquiry ability are especially emphasized. Such results are frequently influenced by the informational and emotional support provided by robots. Nonetheless, challenges encountered by teachers, learners, and robots in this process are not to be overlooked. The findings of this study contributed to future applications of robotics in education.

Mastering the complex time-scale interaction during Stress Corrosion Cracking phenomena through an advanced coupling scheme

Stress corrosion cracking (SCC) failure is a multi-physics phenomena and is usually modelled at the microstructural level, which includes mechanical, chemical, and electrochemical contributions. In aggressive corrosive environments, materials prone to localized corrosion, can suffer heavy pitting corrosion. Subsequently, pit-to-crack transition events might be initiated. Respective mechanical assisted pitting corrosion propagation processes are determined by mechanical, chemical, and electrochemical properties as well as transport properties of ions at grain boundaries. Variations in the electrolyte exposure conditions (including the kinetics at the solid–liquid interface), different mechanical loading scenarios, grain-specific crystal anisotropies, and other local factors combine to produce a highly complex SCC-type interaction scenario at various time and length scales. Since corrosion is a slow process whereas brittle fracture is a rapid failure mechanism, the individual domain discretization-based solvers need to use distinct time steps and appropriate solver settings to become capable to accurately simulate such coupled events. In order to address the issues that arise while accounting for scaling effects in both time and space, and retaining coupled mechanistic interplay and including the aspects specified earlier, a sophisticated modelling method is necessary for the analysis of structural failure by SCC. In this work, a partitioned multi-physics computational approach is presented, using two separate single physics solvers coupled by the open-source coupling library preCICE. In the proposed computational setup, two separate software environments are used, with dedicated solver settings and different time steps, to simulate the mechanical fracture and dissolution-driven pitting corrosion for various loading and corrosion conditions, while also taking into account the effects of microstructural anisotropy. For a 2D polycrystalline model representing face-centered-cubic (fcc) material systems, selected numerical experiments are conducted that predict the evolution of fracture and crack path resulting from SCC. The framework has been further extended to simulate 3D problems as well. The corresponding results are evaluated to show the applicability of the proposed methodology.

Боротьба з контрабандою: заходи та виклики

Ukraine, as a modern state, faces the challenge of effectively combating smuggling, which not only leads to significant budget losses but also poses a threat to national security and economic development. This article discusses the key aspects of this problem, from the causes of smuggling of equipment to the low level of incentives for customs officers and the threats they face. The reasons for smuggling are discussed, such as corruption, excessive customs duties and taxes, and imperfect legislation. The article also considers the need for parliamentary and public control over the actions of customs and border authorities, as well as optimization of taxation to ensure effective protection of the domestic market. Particular emphasis is placed on the importance of international cooperation, technical support, dog training and public education for the successful fight against smuggling. The article also discusses the problem of low salaries and poor incentives for customs officers, which can jeopardize the effectiveness of the fight against smuggling. The article concludes with a section on possible threats to customs officials and ways to address them, including the possibility of threats, bribery and other negative influences that complicate their work. This article also discusses comprehensive measures such as technical support for customs, the development of a dog service, and the importance of public education for the successful fight against smuggling. The low level of salaries among customs officers and their weak incentives to disclose smuggling schemes are seen as a systemic problem that requires a comprehensive approach and solution. The author analyzes the threats that may be directed at customs officials by smugglers and criminal elements. Scenarios of influence, possible bribery, threats and other negative interactions are discussed in order to ensure effective measures to protect customs and border services. All these aspects interact and influence the success of the fight against smuggling in Ukraine. The article highlights the need for a systematic approach and cooperation of all stakeholders – government agencies, the public and international partners – to create an effective system that minimizes the risks and losses from smuggling.

Computational Interpersonal Communication Model for Screening Autistic Toddlers: A Case Study of Response-to-Name.

Interpersonal communication facilitates symptom measures of autistic sociability to enhance clinical decision-making in identifying children with autism spectrum disorder (ASD). Traditional methods are carried out by clinical practitioners with assessment scales, which are subjective to quantify. Recent studies employ engineering technologies to analyze children's behaviors with quantitative indicators, but these methods only generate specific rule-driven indicators that are not adaptable to diverse interaction scenarios. To tackle this issue, we propose a Computational Interpersonal Communication Model (CICM) based on psychological theory to represent dyadic interpersonal communication as a stochastic process, providing a scenario-independent theoretical framework for evaluating autistic sociability. We apply CICM to the response-to-name (RTN) with 48 subjects, including 30 toddlers with ASD and 18 typically developing (TD), and design a joint state transition matrix as quantitative indicators. Paired with machine learning, our proposed CICM-driven indicators achieve consistencies of 98.44% and 83.33% with RTN expert ratings and ASD diagnosis, respectively. Beyond outstanding screening results, we also reveal the interpretability between CICM-driven indicators and expert ratings based on statistical analysis.

Research on Intelligent Speech Interaction System Based on Residual Neural Network and Baidu Speech Platform

To address the dual needs of convenience and security in human-computer interaction under the context of the Internet of Things (IoT) and Artificial Intelligence (AI), a system has been designed based on Raspberry Pi4B, which integrates voice recognition, speech synthesis, and speaker verification functions. Voice recognition and speech synthesis capabilities leverage Baidu's speech platform technology, while speaker verification employs a Residual Neural Network (ResNet34) model based on the PyTorch framework. With a focus on enhancing the user experience, the system incorporates the snowboy offline voice wake-up engine for voice interaction and utilizes Python's Tkinter library to implement a customized graphical user interface (GUI). After strict testing and verification, this system not only efficiently and friendly meets various voice interaction scenarios in the field of Internet of Things technology, but also utilizes voiceprint recognition technology to ensure the application security of the system. It also provides research value for the innovation of open-source hardware platforms in the field of artificial intelligence.

We are all ordinary: the shared visual narratives of daily life promote the patients’ positive attitudes toward doctors

BackgroundCurrent research on the doctor-patient relationship primarily focuses on the responsibilities of doctors, with relatively less emphasis on examining the contributions patients can make. As a result, there is an urgent demand for exploring innovative approaches that highlight the active role patients play in cultivating a robust doctor-patient relationship. The purpose of this study was to devise an intervention strategy centered around patients to enhance the doctor-patient relationship. Comics were developed to depict shared narratives encompassing challenging daily life experiences between doctors and ordinary individuals. The study aimed to assess the efficacy of this approach in cultivating positive attitudes toward doctors.MethodA 3-group design trial was conducted in Shanghai, China. A total of 152 participants were randomly assigned to one of three conditions: the parallel presenting group (n = 51), where narratives about a doctor and an ordinary employee were presented side by side in comics; the single presenting group (n = 50), where only narratives about a doctor were presented; and the control group (n = 51). The outcomes assessed in this study encompassed changes in identification with the doctor portrayed in the comics, perceived intimacy between doctors and patients in reality, and appraisal of the doctor in a prepared doctor-patient interaction situation.ResultsThe parallel presenting group exhibited significantly larger increases in identification with the doctor portrayed in the comics, perceived intimacy between doctors and patients in reality, and appraisal of the doctor in a prepared doctor-patient interaction scenario compared to the single presenting group. The observed enhancements in the appraisal of the doctor in a prepared doctor-patient interaction scenario can be attributed to the changes in identification with the doctor portrayed in the comics experienced by the participants.ConclusionOur study responds to the doctor-centric focus in existing research by exploring patients’ contributions to the doctor-patient relationship. Using comics to depict shared narratives, the parallel presenting group demonstrated significantly increased identification with the depicted doctor, perceived intimacy, and positive appraisal in prepared scenarios compared to the single presenting group. This underscores the effectiveness of patient-centered interventions in shaping positive attitudes toward doctors, highlighting the pivotal role patients play in fostering a resilient doctor-patient relationship.Trial registrationChinese Clinical Trail Registry: ChiCTR2400080999 (registered 20 February 2024; retrospectively registered).

GL-STGCNN: Enhancing Multi-Ship Trajectory Prediction with MPC Correction

In addressing the challenges of trajectory prediction in multi-ship interaction scenarios and aiming to improve the accuracy of multi-ship trajectory prediction, this paper proposes a multi-ship trajectory prediction model, GL-STGCNN. The GL-STGCNN model employs a ship interaction adjacency matrix extraction module to obtain a more reasonable ship interaction adjacency matrix. Additionally, after obtaining the distribution of predicted trajectories using the model, a model predictive control trajectory correction method is introduced to enhance the accuracy and reasonability of the predicted trajectories. Through quantitative analysis of different datasets, it was observed that GL-STGCNN outperforms previous prediction models with a 31.8% improvement in the average displacement error metric and a 16.8% improvement in the final displacement error metric. Furthermore, trajectory correction through model predictive control shows a performance boost of 44.5% based on the initial predicted trajectory distribution. While GL-STGCNN excels in multi-ship interaction trajectory prediction by reasonably modeling ship interaction adjacency matrices and employing trajectory correction, its performance may vary in different datasets and ship motion patterns. Future work could focus on adapting the model’s ship interaction adjacency matrix modeling to diverse environmental scenarios for enhanced performance.

Tools and methods to study and replicate experiments addressing human social cognition in interactive scenarios

In the last decade, scientists investigating human social cognition have started bringing traditional laboratory paradigms more “into the wild” to examine how socio-cognitive mechanisms of the human brain work in real-life settings. As this implies transferring 2D observational paradigms to 3D interactive environments, there is a risk of compromising experimental control. In this context, we propose a methodological approach which uses humanoid robots as proxies of social interaction partners and embeds them in experimental protocols that adapt classical paradigms of cognitive psychology to interactive scenarios. This allows for a relatively high degree of “naturalness” of interaction and excellent experimental control at the same time. Here, we present two case studies where our methods and tools were applied and replicated across two different laboratories, namely the Italian Institute of Technology in Genova (Italy) and the Agency for Science, Technology and Research in Singapore. In the first case study, we present a replication of an interactive version of a gaze-cueing paradigm reported in Kompatsiari et al. (J Exp Psychol Gen 151(1):121–136, 2022). The second case study presents a replication of a “shared experience” paradigm reported in Marchesi et al. (Technol Mind Behav 3(3):11, 2022). As both studies replicate results across labs and different cultures, we argue that our methods allow for reliable and replicable setups, even though the protocols are complex and involve social interaction. We conclude that our approach can be of benefit to the research field of social cognition and grant higher replicability, for example, in cross-cultural comparisons of social cognition mechanisms.

Speech emotion recognition in real static and dynamic human-robot interaction scenarios

The use of speech-based solutions is an appealing alternative to communicate in human-robot interaction (HRI). An important challenge in this area is processing distant speech which is often noisy, and affected by reverberation and time-varying acoustic channels. It is important to investigate effective speech solutions, especially in dynamic environments where the robots and the users move, changing the distance and orientation between a speaker and the microphone. This paper addresses this problem in the context of speech emotion recognition (SER), which is an important task to understand the intention of the message and the underlying mental state of the user. We propose a novel setup with a PR2 robot that moves as target speech and ambient noise are simultaneously recorded. Our study not only analyzes the detrimental effect of distance speech in this dynamic robot-user setting for speech emotion recognition but also provides solutions to attenuate its effect. We evaluate the use of two beamforming schemes to spatially filter the speech signal using either delay-and-sum (D&S) or minimum variance distortionless response (MVDR). We consider the original training speech recorded in controlled situations, and simulated conditions where the training utterances are processed to simulate the target acoustic environment. We consider the case where the robot is moving (dynamic case) and not moving (static case). For speech emotion recognition, we explore two state-of-the-art classifiers using hand-crafted features implemented with the ladder network strategy and learned features implemented with the wav2vec 2.0 feature representation. MVDR led to a signal-to-noise ratio higher than the basic D&S method. However, both approaches provided very similar average concordance correlation coefficient (CCC) improvements equal to 116 % with the HRI subsets using the ladder network trained with the original MSP-Podcast training utterances. For the wav2vec 2.0-based model, only D&S led to improvements. Surprisingly, the static and dynamic HRI testing subsets resulted in a similar average concordance correlation coefficient. Finally, simulating the acoustic environment in the training dataset provided the highest average concordance correlation coefficient scores with the HRI subsets that are just 29 % and 22 % lower than those obtained with the original training/testing utterances, with ladder network and wav2vec 2.0, respectively.

Enhanced LSTM‐DQN algorithm for a two‐player zero‐sum game in three‐dimensional space

AbstractTo tackle the challenges presented by the two‐player zero sum game (TZSG) in three‐dimensional space, this study introduces an enhanced deep Q‐learning (DQN) algorithm that utilizes long short term memory (LSTM) network. The primary objective of this algorithm is to enhance the temporal correlation of the TZSG in three‐dimensional space. Additionally, it incorporates the hindsight experience replay (HER) mechanism to improve the learning efficiency of the network and mitigate the issue of the “sparse reward” that arises from prolonged training of intelligence in solving the TZSG in the three‐dimensional. Furthermore, this method enhances the convergence and stability of the overall solution.An intelligent training environment centred around an airborne agent and its mutual pursuit interaction scenario was designed to proposed approach's effectiveness. The algorithm training and comparison results show that the LSTM‐DQN‐HER algorithm outperforms similar algorithm in solving the TZSG in three‐dimensional space. In conclusion, this paper presents an improved DQN algorithm based on LSTM and incorporates the HER mechanism to address the challenges posed by the TZSG in three‐dimensional space. The proposed algorithm enhances the solution's temporal correlation, learning efficiency, convergence, and stability. The simulation results confirm its superior performance in solving the TZSG in three‐dimensional space.

Virus removal by microfiltration: Effects of electrostatic and hydrophobic interactions

Virus removal by membrane filtration is challenging due to the small size of these microorganisms. For microfiltration (MF) membranes, which have pore sizes above 100 nm (i.e., larger than most viruses), surface interactions are of critical importance in determining virus removal. The present study aims to evaluate the impact of surface interactions on virus removal by MF membranes wherein predictions by extended DLVO (XDLVO) modeling are compared with experimental data on virus clearance. The study employed four viruses (MS2, Qβ, phiX174, phi6), two MF cartridge membranes (nylon and PTFE), and several solution chemistry conditions to cover a range of virus-membrane surface interaction scenarios. For the hydrophilic nylon membrane, the highest log removal values (LRVs) were observed at the pH when the filter carried a slightly positive charge. For the hydrophobic PTFE membrane, higher LRVs were attained for high ionic strength solutions, wherein the electric double layer was compressed, even at pH values where the filter was negatively charged. We conclude that the electrostatic interaction determines whether viruses can approach the membrane and hydrophobic interactions are a critical factor in retaining viruses near the membrane surface, preventing viral leakage into the filtrate. The surface interactions have to be considered in virus membrane filtration.

A comprehensive investigation of clustering algorithms for User and Entity Behavior Analytics.

Government agencies are now encouraging industries to enhance their security systems to detect and respond proactively to cybersecurity incidents. Consequently, equipping with a security operation center that combines the analytical capabilities of human experts with systems based on Machine Learning (ML) plays a critical role. In this setting, Security Information and Event Management (SIEM) platforms can effectively handle network-related events to trigger cybersecurity alerts. Furthermore, a SIEM may include a User and Entity Behavior Analytics (UEBA) engine that examines the behavior of both users and devices, or entities, within a corporate network. In recent literature, several contributions have employed ML algorithms for UEBA, especially those based on the unsupervised learning paradigm, because anomalous behaviors are usually not known in advance. However, to shorten the gap between research advances and practice, it is necessary to comprehensively analyze the effectiveness of these methodologies. This paper proposes a thorough investigation of traditional and emerging clustering algorithms for UEBA, considering multiple application contexts, i.e., different user-entity interaction scenarios. Our study involves three datasets sourced from the existing literature and fifteen clustering algorithms. Among the compared techniques, HDBSCAN and DenMune showed promising performance on the state-of-the-art CERT behavior-related dataset, producing groups with a density very close to the number of users.