Adaptive Agents Research Articles

Multiagent Intratumoral Immunotherapy Can Be Effective in A20 Lymphoma Clearance and Generation of Systemic T Cell Immunity

The use of immunotherapies has shown promise against selective human cancers. Identifying novel combinations of innate and adaptive immune cell-activating agents that can work synergistically to suppress tumor growth and provide additional protection against resistance or recurrence is critical. The A20 murine lymphoma model was used to evaluate the effect of various combination immunotherapies administered intratumorally. We show that single-modality treatment with Poly(I:C) or GM-CSF-secreting allogeneic cells only modestly controls tumor growth, whereas when given together there is an improved benefit, with 50% of animals clearing tumors and surviving long-term. Neither heat nor irradiation of GM-CSF-secreting cells enhanced the response over use of live cells. The use of a TIM-3 inhibitory antibody and an OX40 agonist in combination with Poly(I:C) allowed for improved tumor control, with 90% of animals clearing tumors with or without a combination of GM-CSF-secreting cells. Across all treatment groups, mice rejecting their primary A20 tumors were immune to subsequent challenge with A20, and this longstanding immunity was T-cell dependent. The results herein support the use of combinations of innate and adaptive immune activating agents for immunotherapy against lymphoma and should be investigated in other cancer types.

A complex adaptive agent modeling to predict the stock market prices

Understanding the behaviors of financial markets and their participants remains a challenging problem to resolve. Adaptive agents, which switch from fundamentalist to chartist behavior, are examined in some recent work. In this paper, we propose an adaptive agent-based model that combines three forecasting behaviors of financial agents: fundamentalist, chartist, and mimetic. The weighting of each type of behavior in the final forecasting changes according to the market cycle. Our model adapts to the different cycles of the market.We assess the ability of the proposed model to predict and explain the dynamics of stock market price formation. First, on the microscopic level, we consider four agent-based models: fundamentalist, chartist, mimetic and adaptive. We compare the prices generated by the different prediction models to the real prices generated by the US market (S&P 500 index) over the period (1990–2021). Second, at a macroscopic level, we set up a multi-agent system to simulate an artificial stock market composed of the four types of agents with different market fractions. We compare the prices generated by the artificial market with the real data generated by the US market.The series of statistical analyses that we have carried out allows us to conclude that: the proposed adaptive agent exists in the stock market, he offers a better accuracy of price predictions compared to fundamentalist, chartist and mimetic models and that he can explain the dynamics of the stock market prices formation when he dominates.

Harnessing our greatest asset: Solving margin issues by investing in frontline leaders

The rate of change in combination with the scope and magnitude and the need for increased efficacy in healthcare operations are on the rise, especially with the advent of a plethora of patient needs in the post-COVID-19 world. Senior leaders in the field are faced with various operational and financial challenges on account of the new and rapidly rising patient requirements in the healthcare sector, and, instead of optimising existing resources to meet current challenges, they are often persuaded to just add on new programmes, leaving the existing programmes to languish. Thus, to circumvent some of the major issues in healthcare operations, a more effective strategy has to be pursued than the usual one of simply buying and implementing a new productivity system with updated targets or performance benchmarks. The solution is to assess the efficacy and profitability of existing improvement programmes and resources in the advent of a new set of requirements: deploying burst versus incremental improvement; engaging middle managers to enable their solutions; and achieving organisation speed, spread and scalability across the organisation [Caldwell, C., Cook, K., (2020), ‘Achieving speed, spread, scalability, and sustainability in health systems’, American College of Healthcare Executives-Cluster Session, Clearwater, FL, 17–20th January]. This paper describes how Dignity Health East Valley was able to optimise the use of existing performance improvement resources and deploy an accelerated improvement structure to achieve rapid gains, followed by incremental improvement to both sustain and further the gains made. The approach included mentoring middle managers to become adaptive change agents and achieve 5 per cent improvement in margins in six months. The burst method described in this paper is based on the findings from the research undertaken by top-performing hospitals that identified five essential characteristics that healthcare’s frontline leaders are expected to possess and which are a clear mark of their leadership skills and competence [Caldwell, C., Cook, K., (2020), ‘Achieving speed, spread, scalability, and sustainability in health systems’, American College of Healthcare Executives-Cluster Session, Clearwater, FL, 17–20th January]. The paper presents the background to this research as well as the structure that builds these top-performer capabilities in the front-line team in order for them to lead change and drive its implementation. The positive results that emerged from the leadership training provided to frontline leaders are substantial, including improved margin, higher patient experience and higher employee engagement.

Learning-Empowered Resource Allocation for Air Slicing in UAV-Assisted Cellular V2X Communications

In this article, we propose a resource allocation scheme for air slicing in unmanned aerial vehicle (UAV)-assisted cellular vehicle-to-everything (V2X) communications. We consider a scenario, where multiple flexible UAVs are deployed as the aerial base station (BS) to assist terrestrial BS for providing service to vehicular users with the objective of maximizing the bandwidth efficiency while concurrently guaranteeing the transmission rate and the latency by adopting network slicing. Due to the uncertainty of the stochastic environment in the scenario, we formulate the optimization problem to be a stochastic game, which is an extension of game theory to Markov decision process-like environments for the case of multiple adaptive agents are involved to compete goals simultaneously. Nevertheless, the dynamic nature of both UAVs and vehicles pose the difficulty of perceiving and interacting with the unknown environment, the long short-term memory algorithm is used for extracting the features of the observation and making forecast on the mobility of UAVs and vehicles. Simulation results adduce the validity of the proposed scheme as compared with two benchmark schemes: Deep Q-network and deep deterministic policy gradient.

Plant adaptive agents: Promising therapeutic molecules in the treatment of post-viral fatigue

In recent years, the spread of the coronavirus disease 2019 (COVID-19) in China has been effectively controlled by implementing national prevention and control measures. However, a large number of recovered patients are plagued by fatigue, whether acute or chronic, and other fatigue-related syndromes that severely affect their quality of life. Post-viral fatigue syndrome (PVFS) is a widespread chronic neurological disease with no definite etiological factor(s), definitive diagnostic test, or approved pharmacological treatment, therapy, or cure. In this study, we performed a bibliometric analysis and the results suggested that neuroinflammation plays a role in the development of PVFS. Therefore, we briefly analyzed the mechanisms underlying the development of neuroinflammation in patients with COVID-19. To identify effective drugs to alleviate PVSF, we summarized four traditional herbal phytoadaptations and discussed their molecular mechanisms in improving neurological fatigue. Our study showed that ginseng, Acanthopanax, Rhodiola, and Schisandra played beneficial roles in alleviating PVSF.

The vanishing trial: a dynamic model with adaptive agents

The vanishing trial: a dynamic model with adaptive agents

Heterogeneity-adjusted management of pension funds using adaptive representative agents

Heterogeneity-adjusted management of pension funds using adaptive representative agents

Multi-objective deep reinforcement learning for optimal design of wind turbine blade

The design of a wind turbine blade is a typical complex multi-objective optimization problem, mostly solved by evolutionary algorithms. However, these methods are not effective due to limitations such as inaccurate solutions on Pareto fronts for high-dimensional problems, numerous iterations and low adaptability to problems with similar conditions. To address these issues, two multi-objective deep reinforcement learning models are introduced in this paper from an entirely different perspective. The first model, namely the multi-objective deep deterministic policy gradient (MO-DDPG), extends the existing popular reinforcement learning algorithm DDPG to multi-objective optimization problems by integrating various techniques including modeling of constraints on high-dimensional spaces and generation of Pareto solutions. The second model, namely the multi-objective deep stochastic policy gradient (MO-DSPG), further improves the MO-DDPG by incorporating a random neural network called restricted Boltzmann machine (RBM). An adaptive random agent is trained to transform multiple deterministic policies into an optimal stochastic policy. In addition, neighborhood-based parameter transfer strategy is applied to MO-DSPG in the model training phase to reduce the computation time. Experiments showed that the aerodynamic performance of the blades is improved by both the MO-DDPG and the MO-DSPG models with the hypervolume increasing an average of 6.67% and 9.25% respectively, compared with the state-of-art models. The computational efficiency of MO-DSPG is improved by using the parameter transfer strategy, with its runtime reduced to 72.52% compared with state-of-art models.

Towards Robustness Analysis for Adaptive Artificial Intelligence in Multi-Autonomous agent systems

Individual autonomous agents can employ adaptive Artificial intelligence. The individual agent can respond fast, near real-time, to the environment and avoid hurdles and collisions while keeping a certain distance. Although the systems learn to handle the environment with new conditions and situations, it does not, per see, guarantee that the system is robust meaning the system performs predictably while its variables and assumptions are altered. Nor does it mean that adaptive individual autonomous agents in multi-agent systems perform well in dynamic, distributed and partially observable environments where unexpected things happen.This paper presents an approach to applying robustness analysis on adaptive Artificial intelligence in multi-autonomous agent systems. Adaptiveness modifies the agents’ learning by generating appropriate responses to new situations to achieve resilience to perturbations. The robustness analysis explores the quality of these responses so the agent can continuously operate despite abnormalities in input and consequently safely tolerate perturbations. A multi-agent prototype simulating the integration of adaptive agents with robustness analysis shows that it is possible to apply robustness analysis to the responses of adaptive Artificial intelligence. In the system, each autonomous agent collects data about the surrounding environment and applies adaptation to provide options, i.e., possible actions and decisions. The robustness analysis examines the options in order to validate and adjust them as needed. With these updated options, the agents retrain to resist malfunctioning and achieve resilience and robustness for given situations.

USE OF INFORMATION AND COMMUNICATION TECHNOLOGIES FOR POLITICAL SCIENCE RESEARCH

The article shows a perspective using information and communication technologies for the amplification of the political processes research methodology. It considered the evolving of research with computational techniques using, complications and a variety of possible approaches. It gives information about using simulation modeling, especially the autonomous adaptive agent method for the research related to the course of political events prognostication. It shows the possibilities of computer modeling for the analysis of complex dynamic systems in which decision-making at the micro level changes the system as a whole. In the article are noted the advantages and disadvantages of simulation modeling for political science research. It is stressed that the internet and social network development is important for modern scientists and gives examples of using social networks as a field and tool for political science analysis. It is noted that the use of such an approach can be an important addition to classical methods. It describes in short the possibilities of «Big Data analysis» for political science and stressed the advantages of the method for research conducting. The text provides information about the «text as data» method for automatically mining and analytical processing of large-scale textual information. It gives an example of the “text as data” used and is noted that the proposed method is useful for comparative analysis. It shows the possibilities of using the method of automatic text analysis not only for processing modern information in digital form but also for the information contained in printed sources using computer optical text recognition. At the same time describes in short, the limitations and disadvantages of this method. Conclusions are drawn that information and communication technologies expands the methodology of political science research, improves efficiency and reliability of conclusions.

Climate Services and Transformational Adaptation

The Working Group II contribution to the IPCC’s Sixth Assessment Report states that effective adaptation to the changing climate will require transformational changes in how people live. This article explores the potential for climate services to catalyze and foster transformational adaptation. I argue that weather and climate information are not, in and of themselves, tools for transformation. When designed and delivered without careful identification of the intended users of the service and the needs that service addresses, they can fail to catalyze change amongst the users of that information. At worst, they can reinforce the status quo and drive maladaptive outcomes. For climate services to serve as agents of transformational adaptation, the climate services community will have to change how it understands the users of these services and their needs. Building climate services around contemporary understandings of how people make decisions about their lives and livelihoods offers designers and implementers of climate services opportunities to create services that catalyze transformational adaptation. These opportunities provide examples for the wider field of adaptation to consider in its efforts to contribute to climate resilient development.

Brittleness Evolution Model of the Supply Chain Network Based on Adaptive Agent Graph Theory under the COVID-19 Pandemic

The triggering of supply chain brittleness has a significant impact on enterprise benefits under attack from the COVID-19 pandemic. The complexity of the supply chain system, the uncertainty of the COVID-19 pandemic, and demand uncertainty have made the triggering and propagation of supply chain brittleness complicated. In this study, a brittleness evolution model based on adaptive agent graph theory has been constructed. The parameters of brittleness evolution, including brittleness entropy and the vertex state value, have been quantitatively designed, and the brittleness evolution model in which the adaptability of nodes is considered and is not considered is constructed. A simulation algorithm based on the integrated scheduling model of the supply chain has been established. Finally, the practicability of the proposed model and algorithm is demonstrated via a case study of an electronic supply chain network. The results indicate that the proposed model and algorithm can effectively analyze the brittleness evolution law of the supply chain under the impact of the COVID-19 pandemic, including the evolution law of the vertex state, the brittleness entropy of the vertex, the global entropy of brittleness, the seasonal evolution law of the supply chain brittleness, and the evolution law of the brittleness behavior.

Strategy Game Using Adaptive Agents and Reinforcement Learning

This paper presents the functional specifications of a training platform for use in the training of cadets and serving officers. The game aims to teach trainees that their decisions need to be based both on strategic goals as well as on constraints imposed by international law concerning rules of engagement, ethical codes of conduct or environmental issues. Existing techniques bearing similarities to the required solution are presented. The importance of the problem is hence demonstrated and the possibilities for enhancing the quality of the learning experience for both students and instructors are explored. The rules of a computer game suitable for the cadets training are presented. The game is shown to be sufficient for use in the teaching of strategy ethics. The study leads to high level specifications for the design of the proposed training game. The functional design of the proposed game is then explained and its rules are listed. The design of adaptive software agents that are capable of assuming the role of non-player characters is presented. Further research work necessary for the development of optimization algorithms necessary for the design is described.

Adapt and overcome: Perceptions of adaptive autonomous agents for human-AI teaming

Rapid advances in AI technologies have caused teams to explore the use of AI agents as full, active members of the team. The complex environments that teams occupy require human team members to constantly adapt their behaviors, and thus the ability of AI teammates to similarly adapt to changing situations significantly enhances the team’s chances to succeed. In order to design such agents, it is important that we understand not only how to identify the amount of autonomous control AI agents have over their decisions, but also how changes to this control cognitively affects the rest of the team. Professional organizations often break their work cycles into phases that set limits on the team members’ actions, and we propose that a similar process could be used to define the autonomy levels of AI teammates. Cyber incident response is an ideal context for this proposal, as we were able to use incident response phases to explore how a team’s work cycle could guide an AI agent’s changing level of autonomy. Using a mixed methods approach, we recruited 103 participants to complete a factorial survey containing ten contextual vignettes focused on an AI teammate’s level of autonomy in incident response contexts, and from these participants we conducted twenty-two follow-on qualitative interviews that further explored how the participants felt an AI agent’s adaptive capabilities would affect team performance and cohesiveness. Our results showed that work cycles can be used to assign autonomy levels to adaptive AI agents based upon the degree of formal processes and predictability of the team’s tasks during the cycle, and that dynamic, human-like adaptation methods are vital to effective human-AI teams. This research provides significant contributions to the HCI community by proposing design recommendations for the development of adaptive autonomous teammates that both enhance Human-AI teams’ productivity and promote positive team dynamics.

Thermodynamic machine learning through maximum work production

Adaptive systems—such as a biological organism gaining survival advantage, an autonomous robot executing a functional task, or a motor protein transporting intracellular nutrients—must somehow embody relevant regularities and stochasticity in their environments to take full advantage of thermodynamic resources. Analogously, but in a purely computational realm, machine learning algorithms estimate models to capture predictable structure and identify irrelevant noise in training data. This happens through optimization of performance metrics, such as model likelihood. If such learning is physically implemented, is there a sense in which computational models estimated through machine learning are physically preferred? We introduce the thermodynamic principle that work production is the most relevant performance measure for an adaptive physical agent and compare the results to the maximum-likelihood principle that guides machine learning. Within the class of physical agents that most efficiently harvest energy from their environment, we demonstrate that an efficient agent’s model explicitly determines its architecture and how much useful work it harvests from the environment. We then show that selecting the maximum-work agent for given environmental data corresponds to finding the maximum-likelihood model. This establishes an equivalence between nonequilibrium thermodynamics and dynamic learning. In this way, work maximization emerges as an organizing principle that underlies learning in adaptive thermodynamic systems.

An Adaptive Dempster-Shafer Theory of Evidence Based Trust Model in Multiagent Systems

Multiagent systems (MASs) have a wide range of industrial applications due to agents’ advantages. However, because of the agents’ dynamic behaviors, it is a challenge to ensure the quality of service they present. In this paper, to address this problem, we propose an adaptive agent trust estimation model where agents may decide to go from genuine to malicious or the other way around. In the proposed trust model, both direct trust and indirect reputation are used. However, the indirect reputation derived from the direct experience of third-party agents must have reasonable confidence to be useful. The proposed model introduces a near-perfect measure that utilizes consistency, credibility, and certainty to capture confidence. Moreover, agents are incentivized to contribute correct information (to be honest) through a credit mechanism in the proposed model. Simulation experiments are conducted to evaluate the proposed model’s performance against some of the previous trust models reported in the literature.

Hierarchical Multi-agent System for Sleep Stages Classification

Sleep is a fundamental restorative process for human mental and physical health. Considering the risks that sleep disorders can present, sleep analysis is considered as a primordial task to identify the different abnormalities. Sleep scoring is the gold standard for human sleep analysis. The manual sleep scoring task is considered exhausting, subjective, time-consuming and error prone. Moreover, sleep scoring is based on fixed epoch lengths usually of 30 seconds, which leads to an information loss problem. In this paper, we propose an automatic unsupervised sleep scoring model. The aim of our work is to consider different epoch’s durations to classify sleep stages. Therefore, we developed a model based on Hierarchical Multi-Agent Systems (HMASs) that presents different layers where each layer contains a number of adaptive agents working with a specific time epoch. The effectiveness of our approach was investigated using real electroencephalography (EEG) data. Good results were reached according to a comparative study realized with the often used machine learning techniques for sleep stages classification problems.

Assessement of Enterprise Interoperability Maturity Level through Generative and Recognition Mo

In a globalized and networked society, enterprise interoperability is a key factor of success for enterprises in their effort to maximize their own added values and to exploit the market opportunities. The sustainable enterprise interoperability is a continuous challenge of the networked collaborative environment. By making business decisions, managers have to take into account the maturity level of their own enterprise and of others’ with whom they get involved into businesses. Maturity level of enterprise interoperability has been defined by the Framework for Enterprise Interoperability (FEI), standardized by CEN EN ISO 11354. In this paper, we propose a novel approach to assess maturity levels of enterprise interoperability (MLEI) through latent factor analysis (LFA) and generative and recognition models applied to the categories and features defined by FEI. Given an enterprise interoperability maturity matrix we have trained a stochastic neural network, namely Restricted Bolzmann Machine (RBM) to learn the MLEI. Our research seeks to answer the following questions: whether the maturity level assessed by evaluators correlate with the maturity levels recognized by RBM trained in a supervised learning representation, and how to model recognition matrix of MLEI by using maturity level correlations between observed performances (inputs) and latent or hidden factors that influence the correct assessment. We considered a maturity level correlation matrix representing the enterprise features as defined in FEI in addition to a set of latent factors, representing the type of maturity level of each individual enterprise. Our proposal is based on a generative and a recognition model using deterministic non-linear functions in a Bayesian setting. The model has been tested on artificial data by training a RBM. Experiments on artificial data sets of enterprises proved that our proposal is a reliable approach that can be further developed into a methodology and extended for the design of adaptive learning agents. In the perspective of the Future Internet, such agents may successfully assist human evaluators in the tedious and time consuming process of the assessment of MLEI in real settings.

Characterization of Indicators for Adaptive Human-Swarm Teaming.

Swarm systems consist of large numbers of agents that collaborate autonomously. With an appropriate level of human control, swarm systems could be applied in a variety of contexts ranging from urban search and rescue situations to cyber defence. However, the successful deployment of the swarm in such applications is conditioned by the effective coupling between human and swarm. While adaptive autonomy promises to provide enhanced performance in human-machine interaction, distinct factors must be considered for its implementation within human-swarm interaction. This paper reviews the multidisciplinary literature on different aspects contributing to the facilitation of adaptive autonomy in human-swarm interaction. Specifically, five aspects that are necessary for an adaptive agent to operate properly are considered and discussed, including mission objectives, interaction, mission complexity, automation levels, and human states. We distill the corresponding indicators in each of the five aspects, and propose a framework, named MICAH (i.e., Mission-Interaction-Complexity-Automation-Human), which maps the primitive state indicators needed for adaptive human-swarm teaming.

IANP-EC: Identifying Anticancer Natural Products Using Ensemble Learning Incorporated with Evolutionary Computation.

Cancer is one of the most deadly diseases that annually kills millions of people worldwide. The investigation on anticancer medicines has never ceased to seek better and more adaptive agents with fewer side effects. Besides chemically synthetic anticancer compounds, natural products are scientifically proved as a highly potential alternative source for anticancer drug discovery. Along with experimental approaches being used to find anticancer drug candidates, computational approaches have been developed to virtually screen for potential anticancer compounds. In this study, we construct an ensemble computational framework, called iANP-EC, using machine learning approaches incorporated with evolutionary computation. Four learning algorithms (k-NN, SVM, RF, and XGB) and four molecular representation schemes are used to build a set of classifiers, among which the top-four best-performing classifiers are selected to form an ensemble classifier. Particle swarm optimization (PSO) is used to optimise the weights used to combined the four top classifiers. The models are developed by a set of curated 997 compounds which are collected from the NPACT and CancerHSP databases. The results show that iANP-EC is a stable, robust, and effective framework that achieves an AUC-ROC value of 0.9193 and an AUC-PR value of 0.8366. The comparative analysis of molecular substructures between natural anticarcinogens and nonanticarcinogens partially unveils several key substructures that drive anticancerous activities. We also deploy the proposed ensemble model as an online web server with a user-friendly interface to support the research community in identifying natural products with anticancer activities.