Smart Internet of Vehicles (IoVs) combined with Artificial Intelligence (AI) will contribute to vehicle decision-making in the Intelligent Transportation System (ITS). Multi-Vehicle Pursuit games (MVP), a multi-vehicle cooperative ability to capture mobile targets, is becoming a hot research topic gradually. Although there are some achievements in the field of MVP in the open space environment, the urban area brings complicated road structures and restricted moving spaces as challenges to the resolution of MVP games. We define an Observation-constrained MVP (OMVP) problem in this paper and propose a Transformer-based Time and Team Reinforcement Learning scheme (T3OMVP) to address the problem. First, a new multi-vehicle pursuit model is constructed based on decentralized partially observed Markov decision processes (Dec-POMDP) to instantiate this problem. Second, by introducing and modifying the transformer-based observation sequence, QMIX is redefined to adapt to the complicated road structure, restricted moving spaces and constrained observations, so as to control vehicles to pursue the target combining the vehicle’s observations. Third, a multi-intersection urban environment is built to verify the proposed scheme. Extensive experimental results demonstrate that the proposed T3OMVP scheme achieves significant improvements relative to state-of-the-art QMIX approaches by 9.66%~106.25%. Code is available at https://github.com/pipihaiziguai/T3OMVP.

Fast convergence routing is an important issue for LEO constellation network, due to its dynamical topology changing and time varying transmission requests. Most of existing research focus on the OSPF routing algorithm, which cannot handle the frequently links state changing of network. In this paper, we propose a Fast-Convergence Reinforcement Learning Satellite Routing Algorithm (FRL-SR) for LEO satellite networks, in which the satellite gets the network links status fast and adjusts its routing strategy. In FRL-SR, each satellite node is regarded as an agent. The agent selects the port for packet forwarding according to its own routing policy. When the satellite network state changes, agent would send ’hello’ packets to the neighbor node to update the neighbor node’s routing policy. Compared with traditional reinforcement learning, FRL-SR can perceive network information faster, and then converge faster. Also, FRL-SR can mask the dynamics of satellite network topology and adaptively adjust the forwarding strategy according to the link state. Various simulation is constructed, the results show that the proposed FRL-SR algorithm out performance the Dijkstra algorithm in performance of average delay, packet arriving ratio, network load balance.

Ever-increasing need for improving the livability of a city and improve outcomes for its residents, over the last decade, the adoption of technology to develop urbanised societies around the world has given rise to the need for developing smart cities. The speed at which the world population is growing, the use of Internet of Things in smart cities have really advanced the quality of life. One significant area of concern within the smart city framework is waste management. If the waste within a city is not adequately managed, then it leads to issues in the health of the citizens. Additionally, the waste management has such a high impact on the environmental footprint, hence the need to have a smart way of managing waste is of critical importance. Through our research, we analyse the challenges of waste management within a city to understand the impact of the problem on to the citizens and overall city operations. We then investigate ways in which we can solve these problems using the emerging technologies, such as the Internet of Things, to collect valuable data of large volumes arriving at an astronomical rate, then apply multi-agent deep reinforcement learning algorithms to harness the power of big data to extract meaningful information and actionable insights. We ingest data generated by our Internet of Things into our algorithm for three main purposes including providing the notifications to an external system, for example, a map navigation engine out of the scope for this project but a future extension for route optimisation and waste vehicle tracking; extracting and reporting the actionable insights from the underlying data; and consuming the extracted data for predictive forecasting to draw out the unknown patterns of waste fill levels within various geographical locations and again send out triggers and notification to external systems for example a waste collection authority who can efficiently schedule the waste collection vehicles and optimise the route. To achieve the above mentioned outcomes, we propose a framework that is agnostic of the hardware that it connects to and can effectively interface with a wide variety of hardware keeping a level of abstraction in the architecture.

In recent years, the viability of employing multi-agent reinforcement learning technology for adaptive traffic signal control has been extensively validated. However, owing to restricted communication among agents and the partial observability of the traffic environment, the process of mapping road network states to actions encounters numerous challenges. To address this problem, this paper proposes a multi-agent deep reinforcement learning model with an emphasis on communication content (CMARL). The model decouples the complex relationships between multi-signal agents through centralized training and decentralized execution. Specifically, we first pass the traffic state through an improved deep neural network to achieve the extraction of high-dimensional semantic information and the learning of the communication matrix. Then the agents selectively interact with each other based on the learned communication matrix and generate the final state features. Finally, the features are inputted to the QMIX network to achieve the final action selection. We compare the CMARL model with 6 other baseline algorithms in real traffic networks. The results show that CMARL can significantly reduce vehicle congestion, and run stably in various scenarios.

The adoption of algorithms based on Artificial Intelligence (AI) has been rapidly increasing during the last years. However, some aspects of AI techniques are under heavy scrutiny. For instance, in many use cases, it is not clear whether the decisions of an algorithm are well-informed and conforming to human understanding. Having ways to address these concerns is crucial in many domains, especially whenever humans and intelligent (physical or virtual) agents must cooperate in a shared environment. In this paper, we introduce an application of an explainability method based on the creation of a Policy Graph (PG) based on discrete predicates that represent and explain a trained agent’s behaviour in a multi-agent cooperative environment. We show that from these policy graphs, policies for surrogate interpretable agents can be automatically generated. These policies can be used to measure the reliability of the explanations enabled by the PGs, through a fair behavioural comparison between the original opaque agent and the surrogate one. The contributions of this paper represent the first application of policy graphs in the context of explaining agent behaviour in collaborative multi-agent scenarios and presents experimental results that sets this kind of scenario apart from previous application in single-agent scenarios: when requiring collaborative behaviour, predicates that allow representing observations about the other agents are crucial to replicate the opaque agent’s behaviour and increase the reliability of explanations.

Continuous greenhouse gas emissions are causing global warming and impacting the habitats of many animals. Researchers in the field of electric power are making efforts to mitigate this situation. Operating and maintaining the power grid in an economic, low-carbon, and stable is challenging. To address the issue, we propose a grid dispatching technique that combines prediction technology, reinforcement learning, and optimization technology. Prediction technology can forecast future power demand and solar power generation, while reinforcement learning and optimization technology can make charging and discharging decisions for energy storage devices based on current and future grid conditions. In the power system, the aggregation of distributed energy resources increases uncertainty, particularly due to the fluctuating generation of renewable energy. This requires the use of advanced predictive control techniques to ensure long-term economic and decarbonization goals. In this paper, we present a real-time dispatching framework that integrates deep learning-based prediction, reinforcement learning-based decision-making, and stochastic optimization techniques. The framework can rapidly adapt to target uncertainty caused by various factors in real-time data distribution and control processes. The proposed framework achieved global Champion in the NeurIPS Challenge 2022 competition and demonstrated its effectiveness in practical scenarios of intelligent building energy management.

In this work, we propose a self-supervised multi-agent system that meets the online learning of clustering tasks for video behavior recognition spatio-temporal tasks. Encoding visual behavioral actions as discrete temporal sequence(DTS). Real-time clustering recognition task in a multi-agent system for continuous model building, training, and correction. Finally, we implemented a fully decentralized multi-agent system and completed its feasibility verification in a surveillance video application scenario on vehicle path clustering.

In response to the issue of vehicle escape guidance, this manuscript proposes a unified intelligent control strategy synthesizing optimal guidance and Meta Deep Reinforcement Learning (DRL). Optimal control with minor energy consumption is introduced to meet terminal latitude, longitude and altitude. Maneuvering escape is realized by adding longitudinal and lateral direction maneuver overloads. Maneuver command decision model is calculated based on Soft-Actor-Critic (SAC) networks. Meta learning is introduced to enhance autonomous escape capability, which improves generalization performance to time-varying scenarios not encountered in the training process. In order to obtain training samples at a faster speed, this manuscript uses the prediction method to solve reward values, which avoiding a large number of numerical integration. The simulation results manifest that the proposed intelligent strategy can achieve high precise guidance and effective escape.

Wireless Sensor Networks (WSN) is designed to collect information across a large number of limited battery sensor nodes. Therefore, it is important to minimize the energy consumption of each node, which leads to the extension of the network life. Our goal is to design an intelligent WSN that collects as much information as possible to process it intelligently. To achieve this goal, an agent has been migrated to each node in order to process the information and to cooperate with these neighboring nodes while Mobile Agents (MA) can be used to reduce information between nodes and send those to the base station (Sink). This work proposes to use communication architecture for wireless sensor networks based on the Multi Agent System (MAS) to ensure optimal information collection. The collaboration of these agents generates a simple message that summarizes the important information in order to transmit it by a mobile agent. To reduce the size of the MA, the nodes of the network have been grouped into sector. As for each MA, we have established an optimal itinerary, consuming a minimum amount of energy with the data aggregation efficiency in a minimum time. Successive simulations in large scale wireless sensor networks through the SINALGO simulator show the performance of our proposal, in terms of energy consumption and package delivery rate.

In this paper, we unite concepts from Husserlian phenomenology, the active inference framework in theoretical biology, and category theory in mathematics to develop a comprehensive framework for understanding social action premised on shared goals. We begin with an overview of Husserlian phenomenology, focusing on aspects of inner time consciousness, namely, retention, primal impression, and protention. We then review active inference as a formal approach to modeling agent behavior, based on variational (approximate Bayesian) inference. Expanding upon Husserl’s model of time consciousness, we consider collective goal-directed behavior, emphasizing shared protentions among agents and their connection to the shared generative models of active inference. This integrated framework aims to formalize shared goals in terms of shared protentions, and to thereby shed light on the emergence of group intentionality. Building on this foundation, we incorporate mathematical tools from category theory; particularly, sheaf and topos theory, to furnish a mathematical image of individual and group interactions within a stochastic environment. Specifically, we employ morphisms between polynomial representations of individual agent models, allowing predictions not only of their own behaviors but also those of other agents and environmental responses. Sheaf and topos theory facilitate the construction of coherent agent worldviews and provides a way of representing consensus or shared understanding. We explore the emergence of shared protentions, bridging the phenomenology of temporal structure, multi-agent active inference systems, and category theory. Shared protentions are highlighted as pivotal for coordination and achieving common objectives. We conclude by acknowledging the intricacies stemming from stochastic systems and uncertainties in realizing shared goals.

Large-scale crowd phenomena are complex to model because the behaviour of pedestrians needs to be described at both strategic, tactical, and operational levels and is impacted by the density of the crowd. Microscopic models manage to mimic the dynamics at low densities, whereas mesoscopic models achieve better performances in dense situations. This paper proposes and evaluates a novel agent-based architecture to enable agents to dynamically change their operational model based on local density. The ability to combine microscopic and mesoscopic models for multi-scale simulation is studied through a use case of pedestrians at the Festival of Lights, Lyon, France. Pedestrian outflow data is extracted from video recordings of exiting crowds at the festival. The hybrid model is calibrated and validated using a genetic algorithm that optimizes the match between simulated and observed outflow data. Additionally, a local sensitivity analysis is then conducted to identify the most sensitive parameters in the model. Finally, the performance of the hybrid model is compared to different models in terms of density map and computation time. The results demonstrate that the hybrid model has the capacity to effectively simulate pedestrians across varied density scenarios while optimizing computational performance compared to other models.

Many complex behaviours in biological systems emerge from large populations of interacting molecules or cells, generating functions that go beyond the capabilities of the individual parts. Such collective phenomena are of great interest to bioengineers due to their robustness and scalability. However, engineering emergent collective functions is difficult because they arise as a consequence of complex multi-level feedback, which often spans multiple length-scales. Here, we present a perspective on how some of these challenges could be overcome by using multi-agent modelling as a design framework within synthetic biology. Using case studies covering the construction of synthetic ecologies to biological computation and synthetic cellularity, we show how multi-agent modelling can capture the core features of complex multi-scale systems and provide novel insights into the underlying mechanisms which guide emergent functionalities across scales. The ability to unravel design rules underpinning these behaviours offers a means to take synthetic biology beyond single molecules or cells and towards the creation of systems with functions that can only emerge from collectives at multiple scales.

This paper addresses the critical issue of trust in Artificial Intelligence systems, especially when users might find it challenging to comprehend the internal decision-making processes of such systems. A relevant topic of research in this respect is Theory of Mind, which involves attempting to understand these systems as if they possessed beliefs, desires, and intentions. We focus on the latter: intentions, and we examine how producing explanations based on them can improve \emph{understandability} while allowing for a better interpretation of how they align with human values. We also review some existing methods for identifying intentions in AI systems and we conclude with a discussion on possible future directions in this line of research.

Machine learning offers advanced tools for efficient management of radio resources in modern wireless networks. In this study, we leverage a multi-agent deep reinforcement learning (DRL) approach, specifically the Parameterized Deep Q-Network (DQN), to address the challenging problem of power allocation and user association in massive multiple-input multiple-output (M-MIMO) communication networks. Our approach tackles a multi-objective optimization problem aiming to maximize network utility while meeting stringent quality of service requirements in M-MIMO networks. To address the non-convex and nonlinear nature of this problem, we introduce a novel multi-agent DQN framework. This framework defines a large action space, state space, and reward functions, enabling us to learn a near-optimal policy. Simulation results demonstrate the superiority of our Parameterized Deep DQN (PD-DQN) approach when compared to traditional DQN and RL methods. Specifically, we show that our approach outperforms traditional DQN methods in terms of convergence speed and final performance. Additionally, our approach shows 72.2 % and 108.5 % improvement over DQN methods and RL method respectively in handling large-scale multi-agent problems in M-MIMO networks.

This investigation explores a novel path-planning and optimization strategy for multiple cooperative robotic agents, applied in a fully observable and dynamically changing obstacle field. Current dynamic path planning strategies employ static algorithms operating over incremental time-steps. We propose a cooperative multi-agent (CMA) based algorithm, based on natural flocking of animals, using vector operations. It is preferred over more common graph search algorithms like A* as it can be easily applied for dynamic environments. CMA algorithm executes obstacle avoidance using static potential fields around obstacles, that scale based on relative motion. Optimization strategies including interpolation and Bezier curves are applied to the algorithm. To validate effectiveness, CMA algorithm is compared with A* using static obstacles due to lack of equivalent algorithms for dynamic environments. CMA performed comparably to A* with difference ranging from -0.2% to 1.3%. CMA algorithm is applied experimentally to achieve comparable performance, with an error range of -0.5% to 5.2%. These errors are attributed to the limitations of the Kinect V1 sensor used for obstacle detection. The algorithm was finally implemented in a 3D simulated space, indicating that it is possible to apply with drones. This algorithm shows promise for application in warehouse and inventory automation, especially when the workspace is observable.

The glucose-insulin regulatory system and its glucose oscillations is a recurring theme in the literature because of its impact on human lives, mostly the ones affected by diabetes mellitus. Several approaches were proposed, from mathematical to data-based models, with the aim of modeling the glucose oscillation curve. Having such a curve, it is possible to predict, when injecting insulin in type 1 diabetes (T1D) individuals. However, the literature presents prediction horizons no longer than 6 hours, which could be a problem considering their sleeping time. This work presents Tesseratus, a model that adopts a multi-agent approach to combine machine learning and mathematical modeling to predict the glucose oscillation up to 8 hours. Tesseratus uses the pharmacokinetics of insulins and data collected from T1D individuals. Its outcome can support endocrinologists while prescripting daily treatment for T1D individuals, and provide personalized recommendations for such individuals, to keep their glucose concentration in the ideal range. Tesseratus brings pioneering results for prediction horizons of 8 hours for nighttime, in an experiment with seven real T1D individuals. It is our claim that Tesseratus will be a reference for classification of glucose prediction model, supporting the mitigation of short- and long-term complications in the T1D individuals.

This paper extends the concept of weighted graphs to matrix weighted graphs. The consensus algorithms dictate that all agents reach consensus when the weighted graph is connected. However, it is not always the case for matrix weighted graphs. The conditions leading to different types of consensus have been extensively analysed based on the properties of matrix-weighted Laplacians and graph theoretic methods. However, in practice, there is concern on how to pick matrix-weights to achieve some desired consensus, or how the change of elements in matrix weights affects the consensus algorithm. By selecting the elements in the matrix weights, different clusters may be possible. In this paper, we map the roles of the elements of the matrix weights in the systems consensus algorithm. We explore the choice of matrix weights to achieve different types of consensus and clustering. Our results are demonstrated on a network of three agents where each agent has three states.

There exist numerous high-dimensional problems in the real world which cannot be solved through the common traditional methods. The metaheuristic algorithms have been developed as successful techniques for solving a variety of complex and difficult optimization problems. Notwithstanding their advantages, these algorithms may turn out to have weak points such as lower population diversity and lower convergence rate when facing complex high-dimensional problems. An appropriate approach to solve such problems is to apply multi-agent systems along with the metaheuristic algorithms. The present paper proposes a new approach based on the multi-agent systems and the concept of agent, which is named Multi-Agent Metaheuristic (MAMH) method. In the proposed approach, several basic and powerful metaheuristic algorithms, including Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Artificial Bee Colony (ABC), Firefly Algorithm (FA), Bat Algorithm (BA), Flower Pollination Algorithm (FPA), Gray Wolf Optimizer (GWO), Whale Optimization Algorithm (WOA), Crow Search Algorithm (CSA), Farmland Fertility Algorithm (FFA), are considered as separate agents each of which sought to achieve its own goals while competing and cooperating with others to achieve the common goals. In overall, the proposed method was tested on 32 complex benchmark functions, the results of which indicated effectiveness and powerfulness of the proposed method for solving the high-dimensional optimization problems. In addition, in this paper, the binary version of the proposed approach, called Binary MAMH (BMAMH), was executed on the spam email dataset. According to the results, the proposed method exhibited a higher precision in detection of the spam emails compared to other metaheuristic algorithms and methods.

In this study, we examine the relationship of bank level lending and borrowing decisions and the risk preferences on the dynamics of the interbank lending We develop an agent-based model that incorporates individual bank decisions using the temporal difference reinforcement learning algorithm with empirical data of 6600 S. banks. The model can successfully replicate the key characteristics of interbank lending and borrowing relationships documented in the recent literatur A key finding of this study is that risk preferences at individual bank level can lead to unique interbank market structures which are suggestive of the capacity that the market responds to surprising

The anti-money laundering (AML) process has failed both in identifying suspicious cases in due time as in assisting the AML analysts in decision making. Starting from a new generic anti-fraud approach, this article presents the main aspects related to the development of a multi-agent system that goes beyond the capture of suspicious transactions, seeking to assist the human expert in the analysis of suspicious behaviour. First, a transactional behavioural profile of clients is obtained in a data mining process. A set of rules, obtained through data mining over a real database, in conjunction with specific rules based on legal aspects and in the expertise of the AML analysts make up the agents' knowledge base. The cases for which the system was unable to suggest a decision are flagged as requiring more detailed analysis. The system analysed 6 months of real transactions and indicated several suspicious profiles, a set of these suspects was investigated by the AML analysts who proved the suspicion of several cases, including some that had not been identified by the systems in execution.

For the task planning problem of the command and control architecture, the existing algorithms have problems such as low efficiency and poor re-planning quality under abnormal conditions. Based on the requirements of the current accusation architecture, this paper constructs a distributed command and control architecture model based on multi-agents, which makes use of the superiority of multi-agents in dealing with complex tasks. The concept of MultiAgents-HTN is proposed under the framework. The original hierarchical task network planning algorithm is optimized, the multi-agent collaboration framework is redefined, and the coordination mechanism of local conflict is designed. Taking the classical resource scheduling problem as the experimental background, the comparison between the proposed algorithm and the classical HTN algorithm is carried out. The experimental results show that the proposed algorithm has higher quality and higher efficiency than the existing algorithm, and the space anomaly is heavy during processing. The planning is more efficient, and the time is more complicated and superior in dealing with the same problem, with good convergence and adaptability. The conclusion proves that the distributed command and control architecture proposed in this paper has high practicability in related fields and can solve the problem of distributed command and control architecture in multi-agent environment.

We present information theoretic search strategies for single and multi-robot teams to localize the source of biochemical contaminants in turbulent flows. The robots synthesize the information provided by sporadic and intermittent sensor readings to optimize their exploration strategy. By leveraging the spatio-temporal sensing capabilities of a mobile sensing network, our strategies result in control actions that maximize the information gained by the team while optimizing the time spent localizing the position of the biochemical source. By leveraging the team's ability to obtain simultaneous measurements at different locations, we show how a multi-robot team is able to speed up the search process resulting in a collaborative information theoretic search strategy. We validate our proposed strategies in both simulations and experiments.

In this paper, a distributed algorithm is proposed to solve a consensus convex optimization problem. It is a Jacobi-proximal alternating direction method of multipliers with a damping parameter $\gamma$ in the iteration of multiplier. Compared with existing algorithms, it has the following nice properties: (1) The restriction on proximal matrix is relaxed substantively, thus alleviating the weight of the proximal term. Therefore, the algorithm has a faster convergence speed. (2) The convergence analysis of the algorithm is established for any damping parameter $\gamma\in(0,2]$, which is larger ones in the literature. In addition, some numerical experiments and an application to a logistic regression problem are provided to validate the effectiveness and the characteristics of the proposed algorithm.

Blade Health Monitoring (BHM) is often necessary in power plants and in aviation to prevent excessive blade vibration and cracks. This article proposes a network of blade tip timing sensors operated in a distributed BHM system. A number of cooperating agents is implemented in smart conditioning units which can autonomously operate in an adverse environment and communicate with other nodes via a serial interface. The project uses special versions of reduced instruction set chips that are able to operate near the hot section of the engine. Due to the limited number of types of microprocessors available in the extended temperature range grading, it was necessary to fully utilize the limited hardware resources and implement preemptive multitasking. For this purpose, a custom operating system and communication protocol were designed. The protocol hosts the middle layer which hides the implementation of the distributed system. The presented architecture ensures the sufficient computational capacity in individual nodes of the network operated in adverse conditions. It is scalable and resistant to transmission errors.

This study assesses the impact of incorporating an adaptive learning mechanism into an agent-based model (ABMS) simulating behavior on a university campus during the course of a pandemic outbreak, with a particular case on the COVID-19 pandemic. The aim is to reduce overcrowding and infections on campus through the use of Reinforcement Learning (RL). Our findings indicate that RL is a viable approach for effectively representing agents’ behavior within this context. The results reveal specific temporal patterns of overcrowding violations. While our study successfully mitigated campus crowding, it had limited influence on altering the course of the epidemic. This highlights the necessity for comprehensive epidemic control strategies that consider the role of individual decision-making influenced by adaptive learning, along with the implementation of targeted interventions. This research significantly contributes to our understanding of adaptive learning within complex systems and offers valuable insights for shaping future public health policies in similar community settings. Future research directions encompass exploring various parameter settings and updating representations of the disease’s natural history.

In this paper, we propose, implement, and test two novel downlink LTE scheduling algorithms. The implementation and testing of these algorithms were in Matlab, and they are based on the use of Reinforcement Learning, more specifically, the Qlearning technique for scheduling two types of users. The first algorithm is called a Collaborative scheduling algorithm, and the second algorithm is called a Competitive scheduling algorithm. The first type of the scheduled users is the Primary Users, and they are the licensed subscribers that pay for their service. The second type of the scheduled users is the Secondary Users, and they could be unlicensed subscribers that dont pay for their service, device to device communications, or sensors. Each user whether it is a primary or secondary is considered as an agent. In the Collaborative scheduling algorithm, the primary user agents will collaborate in order to make a joint scheduling decision about allocating the resource blocks to each one of them, then the secondary user agents will compete among themselves to use the remaining resource blocks. In the Competitive scheduling algorithm, the primary user agents will compete among themselves over the available resources, then the secondary user agents will compete among themselves over the remaining resources. Experimental results show that both scheduling algorithms converged to almost ninety percent utilization of the spectrum, and provided fair shares of the spectrum among users.

The paper proposed a modification of the GeoSER(D) model previously developed by us by detailing the age structure of the population, personal schedule on weekdays and working days, and individual health characteristics of the agents, this made it possible to build a more realistic model of the functioning of the city and its residents. The developed model made it possible to simulate the spread of 3 types of the strain of the COVID-19 virus, and to analyze the adequacy of this model in the case of unhindered spread of the virus among city residents. The paper showed that SARS COV 2 spreads mainly from contacts in workplaces and transport, and schoolchildren and preschool children are the consequence, not the initiator of the epidemic. Fluctuations in the dynamics of various indicators of the spread of SARS COV 2 associated with the difference in the daily schedule on weekdays and weekends. It has been shown that people's daily schedules strongly influence the spread of SARS COV 2. For the more contagious "rapid" strains of SARS COV 2 (omicron), immunocompetent people become a significant source of infection. For the less contagious "slow strains" (alpha) of SARS COV 2, the most active source of infection is immunocompromised individuals (pregnant women). The more contagious – "fast" strain of the SARS COV 2 virus (omicron) spreads faster in public transport. For less contagious – "slow" strains of the virus (alpha), the greatest infection occurs due to work and educational contacts.

This paper presents control algorithms enabling autonomous heterogeneous trucks to drive in platoons. Heterogeneous trucks imply that the hardware information (e.g., truck length, break, accelerator, or engine) of a truck may be distinct from that of another truck. We define a platoon as a collection of trucks where a manually driven truck (leader truck) is followed by several automatically controlled following trucks. The proposed approach is to make every autonomous truck keep following the leader's trajectory while maintaining a designated distance from its predecessor truck. As far as we know, this paper is unique in developing both lateral maneuver and speed control considering a platoon of heterogeneous trucks. The efficiency of the proposed approach is verified using simulations.

In this work, we show that a late fusion approach to multi-modality in sign language recognition improves the overall ability of the model in comparison to the singular approaches of Computer Vision (88.14%) and Leap Motion data classification (72.73%). With a large synchronous dataset of 18 BSL gestures collected from multiple subjects, two deep neural networks are benchmarked and compared to derive a best topology for each. The Vision model is implemented by a CNN and optimised MLP and the Leap Motion model is implemented by an evolutionary optimised deep MLP topology search. Next, the two best networks are fused for synchronised processing which results in a better overall result (94.44%) since complementary features are learnt in addition to the original task. The hypothesis is further supported by application of the three models to a set of completely unseen data where a multi-modality approach achieves the best results relative to the single sensor method. When transfer learning with the weights trained via BSL, all three models outperform standard random weight distribution when classifying ASL, and the best model overall for ASL classification was the transfer learning multi-modality approach which scored 82.55% accuracy.

Graph neural networks (GNNs) build on the success of deep learning models by extending them for use in graph spaces. Transfer learning has proven extremely successful for traditional deep learning problems: resulting in faster training and improved performance. Despite the increasing interest in GNNs and their use cases, there is little research on their transferability. This research demonstrates that transfer learning is effective with GNNs, and describes how source tasks and the choice of GNN impact the ability to learn generalisable knowledge. We perform experiments using real-world and synthetic data within the contexts of node classification and graph classification. To this end, we also provide a general methodology for transfer learning experimentation and present a novel algorithm for generating synthetic graph classification tasks. We compare the performance of GCN, GraphSAGE and GIN across both the synthetic and real-world datasets. Our results demonstrate empirically that GNNs with inductive operations yield statistically significantly improved transfer. Further we show that similarity in community structure between source and target tasks support statistically significant improvements in transfer over and above the use of only the node attributes.

Users on the social networking platform have the freedom to express themselves freely. Towards the same time, this has created a forum for disagreement and hate directed at someone, society, racism, sexual orientation, and so on. Identifying hate online is a challenging task. Researchers from all around the world have contributed major methods for detecting hate speech, but owing to the issue's complexity, there are still many unresolved issues. In this research, we offer a multi-model learning strategy for detecting hate speech on Twitter. We utilised the Kaggle TwitterHate dataset, which had 31962 tweets categorised as binary hate or non-hate, to evaluate our technique. The suggested method is tested using commonly used machine learning classifiers with multi-model technique. Using TF-IDF features, we acquired detection results of 96.29 %, precision of 96%, recall of 96%, and f1-score of 96%.

In this paper, modelling, simulation and verification of multi-agent manufacturing system with application of bio-inspired techniques are addressed. To this end, the new solution of abstract architecture for control and coordination decentralized systems - CODESA is suggested. Centralized architecture suffers from various problems, such as rigidity, scalability, low fault-tolerance or very limited flexibility, agility, energy efficiency and productivity. Prime is concrete application of CODESA in manufacturing domain. The undesirable characteristics of emergent behaviour are the problem to achieve optimization and impossibility to predict future states of the system. CODESA-Prime has been tested by simulations for automatic guided vehicle (AGV) systems guided by magnetic tape in Ella Software Platform.

Mucilage from Coccinia grandis was extracted, isolated by maceration technique and precipitated, accordingly. The mucilage was evaluated for its physicochemical, binding, and disintegrant properties in tablets using paracetamol as a model drug. The crucial physicochemical properties such as flow properties, solubility, swelling index, loss on drying, viscosity, pH, microbial load, cytotoxicity were evaluated and the compatibility was analysed using sophisticated instrumental methods (TGA, DTA, DSC, and FTIR). The binding properties of the mucilage were used at three different concentrations and compared with starch and PVP as standard binders. The disintegrant properties of mucilage were used at two different concentrations and compared with standard disintegrants MCCP, SSG, and CCS. The wet granulation technique was used for the preparation of granules and was evaluated for the flow properties. The tablets were punched and evaluated for their hardness, friability, assay, disintegration time, in vitro dissolution profiles. In vitro cytotoxicity study of the mucilage was performed in human embryonic kidney (HEK) cell line using cytotoxic assay by MTT method. The outcome of the study indicated that the mucilage had good performance when compared with starch and PVP. Further, the mucilage acts as a good disintegrant than MCCP, SSG and CCS to paracetamol tablets. Moreover, the in vitro cytotoxicity evaluation results demonstrated that the mucilage is non-cytotoxic to human cells and is safe.

The prediction of drug-target interactions plays a fundamental role in facilitating drug discovery, where the goal is to find prospective drug candidates. With the increase in the number of drug-protein interactions, machine learning techniques, especially deep learning methods, have become applicable for drug-target interaction discovery because they significantly reduce the required experimental workload. In this paper, we present a spontaneous formulation of the drug-target interaction prediction problem as an instance of multi-instance learning. We address the problem in three stages, first organizing given drug and target sequences into instances via a private-public mechanism, then identifying the predicted scores of all instances in the same bag, and finally combining all the predicted scores as the output prediction. A comprehensive evaluation demonstrates that the proposed method outperforms other state-of-the-art methods on three benchmark datasets.

As Artificial Intelligence (AI) technology, particularly Machine Learning algorithms, becomes increasingly ubiquitous, our abilities to understand and interpret AI and machine learning algorithms are becoming increasingly desirable. Visualization has been used as a common tool to view and understand complex machine learning processes. In this paper, we will focus on developing a general framework for the visualization of machine learning models as a scalar valued multi-dimensional function to help users understand how the models behave over different viewing spaces. We first give a formal definition of the visualization problem. Interpolation-based morphing and subspace sampling techniques are applied to generate various renderings through projections and cross-sections of the model space as 3D surfaces or heatmap images. This method will be applied to two real-world datasets and applications: the diagnosis of Alzheimer's Disease (AD) using a human brain networks dataset and a real-world benchmark dataset for predicting home credit default risks. The visualizations show that different machine learning algorithms can behave quite differently under different conditions.

In this paper, we tackle air quality forecasting by using machine learning approaches to predict the hourly concentration of air pollutants (e.g., Ozone, PM_2.5 and Sulfur Dioxide). Machine learning, as one of the most popular techniques, is able to efficiently train a model on big data by using large-scale optimization algorithms. Although there exists some works applying machine learning to air quality prediction, most of the prior studies are restricted to small scale data and simply train standard regression models (linear or non-linear) to predict the hourly air pollution concentration. In this work, we propose refined models to predict the hourly air pollution concentration based on meteorological data of previous days by formulating the prediction of 24 hours as a multi-task learning problem. It enables us to select a good model with different regularization techniques. We propose a useful regularization by enforcing the prediction models of consecutive hours to be close to each other, and compare with several typical regularizations for multi-task learning including standard Frobenius norm regularization, nuclear norm regularization, ℓ_2,1 norm regularization. Our experiments show the proposed formulations and regularization achieve better performance than existing standard regression models and existing regularizations.

In training a deep learning system to perform audio transcription, two practical problems may arise. Firstly, most datasets are weakly labelled, having only a list of events present in each recording without any temporal information for training. Secondly, deep neural networks need a very large amount of labelled training data to achieve good quality performance, yet in practice it is difficult to collect enough samples for most classes of interest. In this paper, we propose factorising the final task of audio transcription into multiple intermediate tasks in order to improve the training performance when dealing with this kind of low-resource datasets. We evaluate three data-efficient approaches of training a stacked convolutional and recurrent neural network for the intermediate tasks. Our results show that different methods of training have different advantages and disadvantages.

As a new distributed machine learning (ML) approach, federated learning (FL) shows the great potential to preserve data privacy by enabling distributed data owners to collaboratively build a global model without sharing their raw data. However, the heterogeneity in terms of data distribution and hardware configurations make it hard to select participants from the thousands of nodes. In this paper, we propose a multi-objective node selection approach to improve time-to-accuracy performance while resisting malicious nodes. We firstly design a deep reinforcement learning assisted FL framework. Then the problem of multi-objective node selection under this framework is formulated as a Markov decision process (MDP), which aims to reduce the training time and improve model accuracy simultaneously. Finally, a deep Q-netwok (DQN) based algorithm is proposed to efficiently solve the optimal set of participants for each iteration. Simulation results show that the proposed method not only significantly improves the accuracy and training speed of FL, but has stronger robustness to resist malicious nodes.

Like traditional single label learning, multi-label learning is also faced with the problem of dimensional disaster.Feature selection is an effective technique for dimensionality reduction and learning efficiency improvement of high-dimensional data. In this paper, Logistic regression, manifold learning and sparse regularization were combined to construct a joint framework for multi-label feature selection (LMFS). Firstly, the sparsity of the eigenweight matrix is constrained by the $L_{2,1}$-norm. Secondly, the feature manifold and label manifold can constrain the feature weight matrix to make it fit the data information and label information better. An iterative updating algorithm is designed and the convergence of the algorithm is proved.Finally, the LMFS algorithm is compared with DRMFS, SCLS and other algorithms on eight classical multi-label data sets. The experimental results show the effectiveness of LMFS algorithm.

The PLM concept implies the use of heterogeneous information resources at different stages of the product life cycle, the joint work of which allows you to effectively solve the problems of product quality and various costs. According to the principle of isomorphism of regularities of complex systems, an effective PLM system must have these regularities. Unfortunately, this principle is not often fundamental when designing PLM systems. The purpose of the work is to show, using a simple example, the principles of development, operation and use of an educational multi-agent PLM system, the main purpose of which is to study and research these regularities in the life cycle of a special threaded connection. The multi-agent approach to the development of a PLM system provides the necessary prerequisites for the emergence of system-wide regularities in it. The parallel work of agents is implemented using the actor model and the Ray Python-package. Agents for the logical inference of knowledge base facts, CAD/FEA/CAM/SCADA agents, agents for optimization by various methods, and other agents have been developed. Open source software was used to develop the system. Each agent has relatively simple behavior, implemented by its rule function, and can interact with other agents. The system can work in interactive mode with the user or in automatic mode according to a simple algorithm: the rule functions of all agents are executed until at least one of them returns a value other than None. Examples of the operation of the system are given and such system-wide regularities as emergence, historicity and self-organization are demonstrated in it.

The option of decarbonizing urban freight transport using Battery Electric Vehicle (BEV) seems promising.However, there is currently a strong debate whether Fuel Cell Electric Vehicle (FCEV) might be the bettersolution. The question arises as to how a fleet of FCEV influences the operating cost, the Greenhouse Gas(GHG) emissions and primary energy demand in comparison to BEVs and to Internal Combustion EngineVehicle (ICEV). To investigate this, we simulate the urban food retailing as a representative share of urbanfreight transport using a multi-agent transport simulation software. Synthetic routes as well as fleet size andcomposition are determined by solving a Vehicle Routing Problem (VRP). We compute the operating costsusing a total cost of ownership (Total Cost of Ownership (TCO)) analysis and the use phase emissions as wellas primary energy demand using the Well To Wheel (WTW) approach. While a change to BEV results in 17 -23% higher costs compared to ICEV, using FCEVs leads to 22 - 57% higher costs. Assuming today’s electricitymix, we show a GHG emission reduction of 25% compared to the ICEV base case when using BEV. Currenthydrogen production leads to a GHG reduction of 33% when using FCEV which however cannot be scaled tolarger fleets. Using current electricity in electrolysis will increase GHG emission by 60% compared to the basecase. Assuming 100% renewable electricity for charging and hydrogen production, the reduction from FCEVsrises to 73% and from BEV to 92%. The primary energy requirement for BEV is in all cases lower and forhigher compared to the base case. We conclude that while FCEV have a slightly higher GHG savings potentialwith current hydrogen, BEV are the favored technology for urban freight transport from an economic andecological point of view, considering the increasing shares of renewable energies in the grid mix.

We describe a new approach for integrating multiple views of data into a common latent space using non-negative tensor factorization (NTF). This approach, which we refer to as the "Integrated Sources Model" (ISM), consists of two main steps: embedding and analysis. In the embedding step, each view is transformed into a matrix with common non-negative components. In the analysis step, the transformed views are combined into a tensor and decomposed using NTF. Noteworthy, ISM can be extended to process multi-view data sets with missing views. We illustrate the new approach using two examples: the UCI digit dataset and a public cell type gene signatures dataset, to show that multi-view clustering of digits or marker genes by their respective cell type is better achieved with ISM than with other latent space approaches. We also show how the non-negativity and sparsity of the ISM model components enable straightforward interpretations, in contrast to latent factors of mixed signs. Finally, we present potential applications to single-cell multi-omics and spatial mapping, including spatial imaging and spatial transcriptomics, and computational biology, which are currently under evaluation. ISM relies on state-of-the-art algorithms invoked via a simple workflow implemented in a Jupyter Python notebook.

Existing Reynolds Averaged Navier-Stokes based transition models do not accurately predict separation induced transition for low pressure turbines. Therefore, in this study, a novel framework based on computational fluids dynamics driven machine learning coupled with multi-expression and multi-objective optimization is explored to develop models which can improve the transition prediction for the T106A low pressure turbine at an isentropic exit Reynolds number of Re2is=100,000. Model formulations are proposed for the transfer and laminar eddy viscosity terms of the laminar kinetic energy transition model using seven non-dimensional pi groups. The multi-objective optimization approach makes use of cost functions based on the suction-side wall-shear stress and the pressure coefficient. A family of solutions is thus developed, whose performance is assessed using Pareto analysis and in terms of physical characteristics of separated-flow transition. Two models are found which bring the wall-shear stress profile in the separated region at least two times closer to the reference high-fidelity data than the baseline transition model. As these models are able to accurately predict the flow coming off the blade trailing edge, they are also able to significantly enhance the wake-mixing prediction over the baseline model.

An electrocardiograph (ECG) reflects the health of the human heart and is used to help diagnose arrhythmia and myocardial infarction(MI) in clinical practice. Early diagnosis of arrhythmia helps implement preventive measures and plays a crucial role in saving a patient's life. With the increasing demand of clinicians for ECG analysis technology, intelligent detection and diagnosis of ECG signals has become a more efficient means to assist physicians in diagnosing cardiovascular diseases. This paper introduces an ECG diagnosis approach based on an ensemble deep learning combination of CNN(convolutional neural network) and SLAP(stacked-long short term memory architecture for prediction) architecture. ECG data is denoised and further divided into single heartbeats to achieve data standardization and sample diversity. Adam optimizer and BCEwithlogitsloss multi-classification loss function were used to enhance the model effect, and the system achieved the classification effect of 99.3% average accuracy, 99.0% F1-value, and 99.2% sensitivity in MIT-BIH standard database classification. It also shows good generalization ability on the Tianchi data set.

Fine-tuning is an important technique in transfer learning that has achieved significant success in tasks that lack training data. However, as it is difficult to extract effective features for single-source domain fine-tuning when the data distribution difference between the source and the target domain is large, we propose a transfer learning framework based on multi-source domain called adaptive multi-source domain collaborative fine-tuning to address this issue. This approach utilizes multiple source domain models for collaborative fine-tuning, thereby improving the model's feature extraction capability in the target task. Specifically, this approach employs an adaptive multi-source domain layer selection strategy to customize appropriate layer fine-tuning schemes for the target task among multiple source domain models. The objective is to extract more efficient features. Furthermore, a novel multi-source domain collaborative loss function is designed to facilitate the precise extraction of target data features by each source domain model. Simultaneously, it works towards minimizing the output difference among various source domain models, thereby enhancing the adaptability of the source domain model to the target data. In order to validate the effectiveness of the proposed the adaptive multi-source domain collaborative fine-tuning framework, it is analyzed and compared with the most widely used fine-tuning methods by applying them to seven publicly available visual categorization datasets commonly employed in transfer learning. Experimental results demonstrate that, in comparison with the existing fine-tuning approaches, our method not only enhances the accuracy of feature extraction in the model but also provides precise layer fine-tuning schemes for the target task, resulting in state-of-the-art performance.

A heterogeneous disease like cancer is activated through multiple pathways and different perturbations. Depending upon the activated pathway(s), patients’ survival vary significantly and show different efficacy to various drugs. Therefore, cancer subtype detection using genomics level data is a significant research problem. Subtype detection is often a complex problem, and in most cases, needs multi-omics data fusion to achieve accurate subtyping. Different data fusion and subtyping approaches have been proposed, such as kernel-based fusion, matrix factorization, and deep learning autoencoders. In this paper, we compared the performance of different deep learning autoencoders for cancer subtype detection. We performed cancer subtype detection on four different cancer types from The Cancer Genome Atlas (TCGA) datasets using four autoencoder implementations. We also predicted the optimal number of subtypes in a cancer type using the silhouette score. We observed that the detected subtypes exhibit significant differences in survival profiles. Furthermore, we also compared the effect of feature selection and similarity measures for subtype detection. To evaluate the results obtained, we selected the Glioblastoma multiforme (GBM) dataset and identified the differentially expressed genes in each of the subtypes identified by the autoencoders; the obtained results coincide well with other genomic studies and can be corroborated with the involved pathways and biological functions. Thus, it shows that the results from the autoencoders, obtained through the interaction of different datatypes of cancer, can be used for the prediction and characterization of patient subgroups and survival profiles.

In recent years, intelligent identification and prediction of ore deposits based on deep learning algorithm and image processing technology has gradually become one of the research frontiers in the field of geological and metallogenic prediction. However, this method also has many problems that need to be solved. For example, (1) very few trainable image samples containing mineral point labels; (2) The geological image features are small and irregular, and the image similarity is high; (3) It is difficult to calculate the influence of different geological prospecting factors on ore mineralization. Based on this, this paper constructs a deep learning network model Multiscale Feature Attention Framework (MFAF) based on geo-image data. The results show that MFCA-Net module in MFAF model can solve the problem of scarce mine label images to a certain extent. In addition, the channel attention mechanism SE-Net module can quantify the difference of influence of different source factors on mineralization. The prediction map is obtained by applying the MFAF model in the study of deposit identification and prediction in the research area of the southern section of Qin-hang metallogenic Belt. In the forecast map, many regions have high metallogenic potential. Through observation, it is found that the above predicted area covers 100% of the known ore deposits at present, which has a good prediction effect. Later, we can find out the specific reasons through field verification. The multi-scale feature fusion and attention mechanism MFA Framework in this paper can provide a new way of thinking for geologists in mineral exploration. The research of this paper also provides resource guarantee and technical support for the sustainable exploitation of mineral resources and the sustainable growth of society and economy.

Respiratory infections are usually characterized by mucus hypersecretion. This condition may worsen and prolong symptoms and signs. Mucoactive agents include different molecules with different mechanisms of action. Sobrerol is a monoterpene able to fluidify mucus, increase mucociliary clearance, and exert antioxidant activity. Sobrerol is available in various formulations (granules, syrup, nebulized, and suppository). Sobrerol has been on the market for over 50 years. Several studies investigated its efficacy and safety in acute and chronic respiratory diseases characterized by mucus hyperproduction. Seven pediatric studies have been conducted with favorable outcomes. Recently, regulatory agencies reduced the treatment duration to three days. Therefore, a future study will test the hypothesis that a combination of oral and topical sobrerol could benefit children and adults with frequent respiratory infections. The rationale considers that mucus accumulation could be a risk factor for increased susceptibility to have infections.

(R)-(+)-3,5-Dinitro-N-(1-phenylethyl)benzothioamide 1 is a potential chiral solvating agent (CSA) for the spectral resolution of enantiomers by 1H NMR spectroscopy. The single enantiomer of 1 was synthesized from commercially (R)-(+)-a-methylbenzylamine 2 in two-steps with 85% yield.

The devastating COVID-19 pandemic forced academia to go virtual. Educational institutions around the world have stressed online learning programs in the aftermath of the pandemic. However, because of insufficient access to ICT, a substantial number of students failed to harness the opportunity of online learning. This study explores the latent digital divide exhibited during the COVID-19 pandemic while online learning activities are emphasized among Bangladeshi students. It also investigates the digital divide exposure and the significant underlying drivers of the divide. A cross-sectional survey was employed to collect quantitative data mixed with open-ended questions to collect qualitative information from the student community. The findings revealed that despite the majority of students have physical access to ICT but only 32.5% of students could attend online classes seamlessly, 34.1% of the students reported the data prices as the critical barrier, and 39.8% of students identified the poor network infrastructure is the significant barrier for them to participate in online learning activities. Although most students possess physical access to the device and the Internet, they face the first-level digital divide due to the quality of access and maintaining subscriptions. Consequently, they fail to take advantage of physical access, resulting in the third-level digital divide (Utility Gap) and submerging them into a digital divide cycle. This paper aimed to explore the underlying issues of the digital divide among Bangladeshi students to assist relevant stakeholders (e.g., the Bangladesh government, Educational Institutions, Researchers) in providing the necessary insights and theoretical understanding to arrange adequate support for students to undertake conducive online learning activities.

Human pose estimation is a complex detection task in which the network needs to capture the rich information contained in the images. In this paper, we propose MSTPose (Multi-Scale Transformer for human Pose estimation). Specifically, MSTPose leverages a high-resolution Convolution neural network (CNN) to extract texture information from images. For the feature maps from three different scales produced by the backbone network, each branch performs the coordinate attention operations. The feature maps are then spatially and channel-wise flattened, combined with keypoint tokens generated through random initialization, and fed into a parallel Transformer structure to learn spatial dependencies between features. As the Transformer outputs one-dimensional sequential features, the mainstream two-dimensional heatmap method is abandoned in favor of one-dimensional coordinate vector regression. The experiments show that MSTPose outperforms other CNN-based pose estimation models and demonstrates clear advantages over CNN + Transformer networks of similar types.

A method for classification is introduced in this article, and it is tested on ADNI database to diagnose alzheimer’s disease (AD). It is obvious that tunning the performance of a classification to get better results is a complicated problem, and when we want model’s accuracy or other peformance measurments higher than 90%, the problem will be more complicated. In this study, we tried and succeeded to discover a method to solve this problem. The final feature set can be used clustering too, because outgrowth feature set of the proposed method is invigorated. In the recent years, a lot of activities is done to develop computer aided systems (CAD) for alzheimer’s disease diagnosis. Most of these recently developed systems concenterated on extracting and combining features from MRI, PET, CSF, and …; in this article, we made attempt to do so and utilized one more technique to increase classification performance. Finding and producing the best features to solve three binary classification problems of AD vs. Normal Control (NC), Mild Cognitive Impairment (MCI) vs. NC, and MCI vs. AD are the purposes of this article. Experiments indicate performance and effectiveness rates of the proposed method, which are accuracies of 98.81%, 81.61%, and 81.40% for AD vs. NC, MCI vs. NC, and AD vs. MCI classification problems, respectively. As can be seen, using this method increased the performance of the three binary problems incredibly.

In this study, we present a federated learning approach that combines a multi-branch network and the Oort client selection algorithm to improve the performance of federated learning systems. This method successfully addresses the significant issue of non-iid data, a challenge not adequately tackled by the commonly used MFedAvg method. Additionally, one of the key innovations of this research is the introduction of uniformity, a metric that quantifies the disparity in training time amongst participants in a federated learning setup. This novel concept not only aids in identifying stragglers but also provides valuable insights into assessing the fairness and efficiency of the system. Experimental results underscore the merits of the integrated multi-branch network with the Oort client selection algorithm and highlight the crucial role of uniformity in designing and evaluating federated learning systems.

Alkenyl Succinic Anhydride (ASA) is a sizing agent used in papermaking to increase the water repellency of paper. Almost 60 years after the introduction of the chemical in papermaking, scientists still have differing views on how ASA interacts with cellulose. Several experiments were conducted to bring more clarity to the ASA sizing mechanism, especially on the contentious question of ASA-cellulose covalent bonding or the esterification reaction between ASA and cellulose during papermaking. Herein, research papers and patents, including experiments and results, from the1960’s to 2020 were reviewed. Our investigation revealed that the ester bond formation between ASA and cellulose is insignificant and is not a prerequisite for sizing effectiveness; the main ASA related material found in sized paper is hydrolyzed ASA or both hydrolyzed ASA and ASA salt. In addition, ASA emulsion stability and ASA emulsion retention are important for sizing efficiency improvement.

In recent years, demand has been increasing for target detection and tracking from aerial imagery via drones using onboard powered sensors and devices. We propose a very effective method for this application based on a deep learning framework. A state-of-art embedded hardware system empowers small flying robots to carry out the real-time onboard computation necessary for object tracking. Two types of embedded modules were developed: one is designed using a Jetson TX or AGX Xavier, and the other is based on an Intel Neural Compute Stick. These are suitable for real-time onboard computing power on small flying drones with limited space. A comparative analysis of current state-of-art deep-learning-based multi-object detection algorithms was carried out utilizing the designated GPU-based embedded computing modules to obtain detailed metric data about frame rates as well as the computation power. We also introduce an effective target tracking approach for moving objects. The algorithm for tracking moving objects is based on the extension of simple online and real-time tracking. It was developed by integrating a deep-learning-based association metric approach (Deep SORT), which uses a hypothesis tracking methodology with Kalman filtering and a deep-learning-based association metric. In addition, a guidance system that tracks the target position using a GPU-based algorithm is introduced. Finally, we demonstrate the effectiveness of the proposed algorithms by real-time experiments with a small multi-rotor drone.

Fabry-Pérto (FP) cavity is the essential component of ultra-stable laser (USL) for gravitational wave detection, which couples multi-physic (Optical/Thermal/Mechanics) fields and requires ultra-high precision. To satisfy the requirements of precise and efficient design, a multi-physic coupling optimization method for fixing cubic FP cavity based on data learning is proposed. A multi-physic model for the cubic FP cavity is established and the performance is obtained by finite element analysis. The key performance indices (V, wF, wF) and key design variables (d, l, F) are determined considering the features of the FP cavity. The 49 sets of data by orthogonal experiment are acquired for the establishment and comparison of different data learning models (NN, RSF, KRG). The result turns out that the neural network has the best performance. Based on NSGA-II, the Pareto optimal front is obtained and the optimal combination of design variables is finally determined as {5,32,250}. The performance after optimization has proven to be a great improvement, of which the displacement under the fixing force and vibration test are decreased by more than 60%. The optimization strategy can not only help the design of the FP cavity but also enlighten other optimization fields.

The classical approach to non-linear regression in physics, is to take a mathematical model describing the functional dependence of the dependent variable from a set of independent variables, and then, using non-linear fitting algorithms, extract the parameters used in the modeling. Particularly challenging are real systems, characterised by several additional influencing factors related to specific components, like electronics or optical parts. In such cases, to make the model reproduce the data, empirically determined terms are built-in the models to compensate for the impossibility of modeling things that are, by construction, impossible to model. A new approach to solve this issue is to use neural networks, particularly feed-forward architectures with a sufficient number of hidden layers and an appropriate number of output neurons, each responsible for predicting the desired variables. Unfortunately, feed-forward neural networks (FFNNs) usually perform less efficiently when applied to multi-dimensional regression problems, that is when they are required to predict simultaneously multiple variables that depend from the input dataset in fundamentally different ways. To address this problem, we propose multi-task learning (MTL) architectures. These are characterized by multiple branches of task-specific layers, which have as input the output of a common set of layers. To demonstrate the power of this approach for multi-dimensional regression, the method is applied to luminescence sensing. Here the MTL architecture allows predicting multiple parameters, the oxygen concentration and the temperature, from a single set of measurements.

A significant number and range of challenges besetting sustainability can be traced to the actions and interactions of multiple autonomous agents (people mostly) and the entities they create (e.g., institutions, policies, social network) in the corresponding social-environmental systems (SES). To address these challenges, we need to understand decisions made and actions taken by agents, the outcomes of their actions, including the feedbacks on the corresponding agents and environment. The science of Agent-based Complex Systems—ACS science—has a significant potential to handle such challenges. The advantages of ACS science for sustainability are addressed by way of identifying the key elements and challenges in sustainability science, the generic features of ACS, and the key advances and challenges in modeling ACS. Artificial intelligence and data science promise to improve understanding of agents’ behaviors, detect SES structures, and formulate SES mechanisms.

Aim: To determine whether an AI model and single sensor measuring acceleration and ECG could model cognitive and physical fatigue for a self-paced trail run. Methods: A field-based protocol of continuous fatigue repeated hourly induced physical (~45 minutes) and cognitive (~10 minutes) fatigue on one healthy participant. Physical load was a 3.8 km, 200 m vertical gain, trail run with acceleration and electrocardiogram (ECG) data collected using a single sensor. Cognitive load was a Multi Attribute Test Battery (MATB) and separate assessment battery including the Finger Tap Test (FTT), Stroop, Trail Making A and B, Spatial Memory, Paced Visual Serial Addition Test (PVSAT), and a vertical jump. A fatigue prediction model was implemented using a Convolutional Neural Network (CNN). Results: When the fatigue test battery results were compared for sensitivity to the protocol load, FTT right hand (R2 0.71) and Jump Height (R2 0.78) were the most sensitive while the other tests were less sensitive (R2 values Stroop 0.49, Trail Making A 0.29, Trail Making B 0.05, PVSAT 0.03, spatial memory 0.003). Best prediction results were achieved with a rolling average of 200 predictions (102.4 s), during set activity types, mean absolute error for ‘walk up’ (MAE200 12.5%) and range of absolute error for ‘run down‘ (RAE200 16.7%). Conclusion: We were able to measure cognitive and physical fatigue using a single wearable sensor during a practical field protocol including contextual factors in conjunction with a neural network model. This research has practical application to fatigue research in the field.

Bedbug (Cimex spp.) are a nuisance public-health pest that is on the rise globally, particularly in crowded cities such as Hong Kong. To investigate the health impacts of bedbug infestations among bedbug victims, online surveys were distributed in Hong Kong between June 2019 to July 2020. Data on sociodemographics, self-rated health, average hours of sleep per day, and details of bedbug infestation were collected. Bivariate and multivariable analysis were performed using logistic regression. The survey identified 422 bedbug victims; among them, 223 (52.9%) experienced ≥5 bites in the past month, most bites occurred on the arms (n=202, 47.8%) and legs (n=215, 51%), and the most common reaction to bites were itchiness (n=322, 76.3%), redness, and swelling of the skin (n=246, 58.1%), and difficulties sleeping or restlessness (n=125, 29.6%). Bites usually occurred during sleep (n=230, 54.5%). For impact on daily life in the past month, most bedbug victims reported moderate to severe impact on mental and emotional health (n=223, 52.8%) and sleeping quality (n=239, 56.6%). Lower self-rated health (aOR<1) was independently associated with impact to physical appearance (p=0.008), spending money on medication or doctor consultation (p=0.04), number of bites in the past month (p=0.023), and irregular time of bites (p=0.003). Lower average hours of sleep per day (aOR<1) was independently associated with impact on mental and emotional health (p=0.016). This study brings attention to the neglected issue of bedbug infestation by considering bedbugs as an infectious agent instead of a vector and providing empirical evidence describing its health impacts.

Manufacturing systems need to meet I4.0 guidelines to deal with uncertainty in scenarios of turbulent demand for products. The engineering concepts to define the service’s resources to manufacture the products will be more flexible, ensuring the possibility of re-planning in operation. These can follow the engineering paradigm based on capabilities. The virtualization of industry components and assets achieves the RAMI 4.0 guidelines and (I4.0C), which describes the Asset Administration Shell (AAS). However, AAS are passive components that provide information about I4.0 assets. The proposal of specific paradigms is exposed for managing these components, as is the case of multi-agent systems (MAS) that attribute intelligence to objects. The implementation of resource coalitions with evolutionary architectures (EAS) applies cooperation and capabilities’ association. Therefore, this work focuses on designing a method for modeling the asset administration shell (AAS) as virtual elements orchestrating intelligent agents (MAS) that attribute cooperation and negotiation through contracts to coalitions based on the engineering capabilities concept. The systematic method suggested in this work is partitioned for the composition of objects, AAS elements, and activities that guarantee the relationship between entities. Finally, Production Flow Schema (PFS) refinements are applied to generate the final Petri net models (PN) and validate them with Snoopy simulations. The results achieved demonstrate the validation of the procedure, eliminating interlocking and enabling liveliness to integrate elements behavior.

The potential of quantum computing for scientific and industrial breakthroughs is immense, however, we are still in the Noisy Intermediate-Scale Quantum (NISQ) era, where the currently available quantum devices contain small numbers of qubits, are very sensitive to environmental conditions and prone to quantum decoherence. Even so, existing NISQ computers have already been shown to outperform conventional computers on specific problems and the key question is how to make use of today’s NISQ devices to achieve quantum advantage in the field of computational science and engineering (CSE). In this direction, this work proposes a hybrid computing formulation by combining quantum computing with machine learning for accelerating the solution of parameterized linear systems in NISQ devices. In particular, it focuses on the Variational Quantum Linear Solver (VQLS), which is a hybrid quantum- classical algorithm for solving linear systems of equations. VQLS employs a short-depth quantum circuit to efficiently evaluate a cost function related to the system solution. The algorithm’s circuit consists of a quantum gate sequence (unitary operators) that involves a set of tunable parameters. Then, well-established classical optimizers are utilized to tune the parameters of the sequence in order to minimize the cost function, which is equivalent to finding the system solution at an acceptable level of accuracy. In this work, it is demonstrated that machine learning tools such as feed-forward neural networks and nearest-neighbor interpolation techniques can be successfully employed to accelerate the convergence of the VQLS algorithm towards the optimal values for the circuit parameters when applied to parameterized linear systems that need to be solved for multiple parameter instances.

A new method for multi-shot reconstruction of high-energy photon distributions in the context of studying the interaction between a beam and a plasma in plasma wakefield acceleration (PWFA) experiments is presented. The study investigates the effects of beam perturbations on betatron radiation and analyzes how these perturbations can lead to hosing, a transverse instability that can degrade the quality of the beam. The potential of betatron radiation spectroscopy as a non-invasive diagnostic technique for PWFA experiments is also emphasized.

Deep learning has been applied in many areas that have had a significant impact on applications that improves real-life challenges. The success of deep learning in a wide range of areas is due in part to the use of activation functions, which are particularly effective at solving non-linear problems. Activation functions are a key focus for researchers in artificial intelligence who aim to improve the performance of neural networks. This article provides a comprehensive explanation and comparison of different activation functions, with a focus on the arc tangent and its variations specifically. The paper presents experimental results that show that variations of the arc tangent using irrational numbers such as pi, the golden ratio, and Euler’s number, as well as a self-arctan function, produce promising results. Since we experimented with promising activation functions on two different problems, and datasets, we reached a result that different irrationals work well for different problems. In other words, arctan ϕ gives the best results mostly for multiclass classification and arctan e gives the best results for time series prediction problems. The paper focuses on a multi-class classification problem applied to the Reuters Newswire dataset and a time-series prediction problem on Türkiye energy trade value to show the impacts of activation functions.

The central goal of few-shot scene classification is to learn a model that can generalize well to a novel scene category (UNSEEN) from only one or a few labeled examples. Recent works in the remote sensing (RS) community tackle this challenge by developing algorithms in a meta-learning manner. However, most prior approaches have either focused on rapidly optimizing a meta-learner or aimed at finding good similarity metrics while overlooking the embedding power. Here we propose a novel Task-Adaptive Embedding Learning (TAEL) framework that complements the existing methods by giving full play to feature embedding’s dual roles in few-shot scene classification - representing images and constructing classifiers in the embedding space. First, we design a lightweight network that enriches the diversity and expressive capacity of embeddings by dynamically fusing information from multiple kernels. Second, we present a task-adaptive strategy that helps to generate more discriminative representations by transforming the universal embeddings into task-specific embeddings via a self-attention mechanism. We evaluate our model in the standard few-shot learning setting on two challenging datasets: NWPU-RESISC4 and RSD46-WHU. Experimental results demonstrate that, on all tasks, our method achieves state-of-the-art performance by a significant margin.

Effective detection of isopropyl methylfluorophosphonate (GB, sarin), a type of organophosphine poisoning agent, is an urgent issue to be addressed in maintaining public safety. In this research, a gas-sensitive film material defined as poly (4-hydroxy-4,4-bis trifluoromethyl) - butyl-1-enyl) - si-loxane (SXFA) with the structure of hexafluoroisopropyl (HFIP) functional group was synthesized by using methyl vinylpropyl dichlorosilane and hexafluoroacetone trihydrate as initial materials. Synthesis process products were characterized by FTIR. SXFA was prepared on a 200 MHz shear surface wave delay line with spin coating method for GB detected. Detection limit of ＜ 0.1 mg/m3 was obtained through conditional experiments. Meanwhile, we also obtained the maximum re-sponse of 2.168 mV at 0.1 mg/m3 concentration, which indicting a much lower detection limit of SAW-SXFA sensor. Additionally, the maximum response standard deviation of 0.11 mV with a co-efficient of variation of 0.01, as well as the maximum recovery standard deviation of 0.22 mV with a coefficient of variation of 0.02 were also obtained through 5 repeated experiments. Results showed that the SAW-SXFA sensor has strong selectivity and reproducibility, good selectivity, positive detection ability, high sensitivity, and fast alarm performance for sarin detection.

Gadolinium-based contrast agents (GBCA) are complexes, highly stable in vivo, used in Magnetic Resonance Imaging (MRI), administered in patients and then eliminated via renal, passing through wastewater treatment plants (WWTP) before being discarded in the receiving medium, without apparent removal. In this study, it was studied if different exposure periods to several environmental parameters (solar radiation, different salinities, temperatures and pH) will influence the stability of these complexes, namely, the Gd-DOTA. Gd-DOTA solutions were processed in a seaFAST-pico saline matrix pre-concentration and elimination system and Gd concentrations were determined by ICP-MS. Results showed that the complex remained stable in fresh, brackish and saline water environments, even when exposed to extreme temperatures (40ºC) or slightly acidic to basic conditions (6-10), for an exposure period of 96h. A small increase in the free Gd concentration was observed after 18 days when exposed to pH<4, in all tested salinities (0, 18 and 36 PSU), with a degradation increase of up to 29%, after 5 weeks of exposure in freshwater. When exposed to direct solar radiation a low Gd-DOTA degradation (4%) was observed after 24h at salinity 18 PSU and remained constant until the end of the exposure period (96h), while the remaining salinities showed negligible values.

The purpose of this study was to analyze the influence of Chitosan 0.2% in various final cleaning methods on the bond strength of fiberglass post (FP) to intrarradicular dentin. Ninety bovine incisors were sectioned to obtain root remnants measuring 18 mm in length. The roots were divided: G1: EDTA 17%; G2: EDTA 17% + PUI; G3: EDTA 17% + EA; G4: EDTA 17% + XPF; G5: Chitosan 2%; G6: Chitosan 2% + PUI; G7: Chitosan 2% + EA; G8: Chitosan 2% +XPF. After carrying out the cleaning methods, the posts were installed, and the root cleaved to to generate two disks from each root third. Bond strength values (MPa) obtained from the micro push-out test data were assessed by Kruskal-Wallis and Dwass-Steel-Critchlow-Fligner tests for multiple comparisons (α = 5%). Differences were observed in the cervical third between G1 and G8 (p=0.038), G4 and G8 (p=0.003), G6 and G8 (p=0.049), and Control and G8 (p=0.019). The final cleaning method influenced the adhesion strength of cemented FP to intrarradicular dentin. Chitosan 0.2% + XPF positively influenced adhesion strength, with the highest values in the cervical third.

Background. We created agent-based model for short- and longterm forecasting of COVID-19 and for evaluation how the actions of the regulator affected the human and material resources of the healthcare system. Methods. The model was implemented in the AnyLogic software. It includes two state charts – social network and disease transmission. The COVID-19 Essential Supplies Forecasting Tool (COVID-ESFT, version 2.0) was used to determine healthcare resources needed. Results. Satisfactory results were obtained with long-term (up to 50 days) forecasting in the case of a monotonous change in total cases curve. However, if periods of relative stability are accompanied by sudden outbreaks, relatively satisfactory results were obtained with short-term forecasting, up to 10 days. Simulation of various scenarios showed that the most important place for the spread of infection are families. Wherein the maximum number of cases of COVID-19 is observed in the age group of 26-59 years. Due to a set of measures taken by government agencies, the number of cases in Karaganda city was 3.2 times less than was predicted in “no intervention” scenario. Economic effect is estimated at 40 %. Conclusion. Performed model is an attempt to consider as much as possible the peculiarities of the socio-demographic situation in the country. In the future, we will be prepared to some extent for challenges like those we have experienced in the past three years.

Jade waste is a normal byproduct that makes up much more than the amount of jade extracted. Therefore, recycling jade waste is worth investigating from the point of view of energy conservation. Moreover, it is an environment-friendly material, which is desirable for use in building materials. In this study, Xiuyan jade waste was repurposed as antibacterial additives for building coatings. The powder waste was activated by milling and subsequent annealing. The antibacterial properties of the treated waste were mostly related to the annealing temperatures. Based on the investigations of the phase change and the release of metal ions of a series of samples and their antibacterial activities, the antibacterial mechanism of the treated samples was explored experimentally. The most applicable sample for coatings was finally chosen by considering its pH values and its antibacterial abilities. Antibacterial testing showed that the addition of treated jade waste could enhance the bacterial inhibition rate of building coatings from 60% to 99.9%.

Agent-based models (ABMs) are computational models for simulating the actions and interactions of autonomous agents in time and space. These models allow users to simulate the complex interactions between individual agents and the landscapes they inhabit and are increasingly used in epidemiology to understand complex phenomena and make predictions. However, as the complexity of the simulated systems increases, notably when disease control interventions are considered, model flexibility and processing speed can become limiting. Here we introduce SamPy, an open-source Python library for stochastic agent-based modeling of epidemics. SamPy is a modular toolkit for model development, providing adaptable modules that capture host movement, disease dynamics, and disease control interventions. Memory optimization and design provide high computational efficiency allowing modelling of large, spatially-explicit populations of agents over extensive geographical areas. In this article, we demonstrate the high flexibility and processing speed of this new library. The version of SamPy considered in this paper is available at https://github.com/sampy-project/sampy-paper .

2-(Morpholin-4-yl)-4,5-bis(2’’,2’’,2’’-trinitroethoxy)-1,3,5-triazine having QSAR-predicted anti-tumor activity was tested for the cytotoxicity using MTT and LDH cell viability tests. The experiments were conducted using human fibroblasts, peripheral blood mononuclear cells and breast cancer cells and allowed to identify effective cytotoxic concentration ant therapeutic range of this compound. The data obtained suggest the feasibility of the further studies of the test compound as a potential anti-cancer agent.

In this study, a natural-based gelling agent comprised of blended flax seed gum (FSG), konjac glucomannan (KG), and agar gel (AG) was developed for application to control the textural properties of foods. The compound gels, including FSG, KG, and AG, were investigated to determine their physicochemical properties, including minimum gelling concentration, water binding capacity, water soluble index, and swelling power. In addition, we analyzed the rheological properties of the compound gel through texture analysis, frequency sweep, and creep and recovery. The microstructure of the compound gel was identified and compared with the viscoelastic properties of the gel. Overall, these results showed that the F4K6 (4:6:2 of FSG:KG:AG) could serve as an excellent gelling agent, which endowed food gel with the promoted elastic properties, water capacity, and rigid surface morphology. This work suggests that novel gelling agents, including FSG, KGM, and AG, successfully prepared food gels with improved physicochemical properties.

Excessive CO₂ emissions and alternative energy fuels are two major difficult issues. The utilization of CO₂ into fine chemicals is an optimal route. Diethyl carbonate (DEC) is an extremely versatile chemical intermediate. DEC is used in gasoline, pharmaceutical, chemical and other fields. DEC synthesis from CO₂ and ethanol is a typical green synthetic route. Ni-Cu@Na₃PW₁₂O₄₀ catalysts were synthesized by two novel methods of supported and mixed. The catalyst prepared by mixed method showed nice catalytic performance. It was confirmed that water removal was the key to improving conversion efficiency. In the presence of dehydrating agent of ethylene, ethanol conversion increased from ca. 3% to ca. 40%. Propylene oxide (PO) was participated in the reaction and ethanol conversion continued to reach to ca.90% while DEC selectivity dropped by half. Under optimal conditions, our Ni-Cu@Na₃PW₁₂O₄₀ catalyst effectively solved the two major issues above.

Bitumen aging is the major factor which contributes to the deterioration of the road pavement. Oxidation and volatilization are generally considered as the most important phenomena affecting aging in asphalt paving mixtures. The present study was carried to investigate whether various antioxidants provided by natural resources such as phospholipids, ascorbic acid as well as lignin from rice husk, could be used to reduce age hardening in asphalt binders. A selected bituminous material was modified by adding 2 % w/w of the anti-aging natural additives and subjected to accelerated oxidative aging regimes according to the Rolling Thin Film Oven Test (RTFOT) method. The effects of aging were evaluated based on changes in sol-gel transition temperature of modified bitumens measured through Dynamic Shear Rheology (DSR). Moreover, changes of Electron Paramagnetic Resonance (EPR) spectra were monitored on the bituminous fractions asphaltene and maltene separated by solvent extraction upon oxidative aging. The phospholipids-treated binder exhibited the highest resistance to oxidation and the lowest age-hardening effect compared to the other tested anti-oxidants. The combination of EPR and DSR techniques represents a promising method for elucidating the changes in associated complex properties of bitumen fractions promoted by addition of free radical scavengers borrowed by green resources.

Object recognition is an essential element of machine intelligence tasks. However, one model cannot practically be trained to identify all the possible objects it encounters. An ensemble of models may be needed to cater to a broader range of objects. Building a mathematical understanding of the relationship between various objects that share comparable outlined features is envisaged as an effective method of improving the model ensemble through a pre-processing stage, where these objects' features are grouped under a broader classification umbrella. This paper proposes a mechanism to train an ensemble of recognition models coupled with a model selection scheme to scale-up object recognition in a multi-model system. An algorithmic relationship between the learnt parameters of a trained classification model and the features of input images is presented in the paper for the system to learn the model selection scheme. The multiple models are built with a CNN structure, whereas the image features are extracted using a CNN/VGG16 architecture. Based on the models' excitation weights, a neural network model selection algorithm, which links a new object with the models and decides how close the features of the object are to the trained models for selecting a particular model for object recognition is developed and tested on a five-model neural network platform. The experiment results show the proposed model selection scheme is highly effective and accurate in selecting an appropriate model for a network of multiple models.

Electric moped scooter sharing services have recently experienced strong growth rates, particularly in Europe. Due to their compactness, environmental-friendliness and convenience, shared e-mopeds are suitable modes of transport in urban mobility to help reduce the environmental impact. However, its traffic-related, economic and environmental effects are merely represented in academic research. We used passenger car traffic data in Berlin generated by the multi-agent transport simulation framework MATSim to develop a python-based simulation, resembling an e-moped sharing system. Based on the results, a total cost of ownership and a life cycle assessment for fleet sizes of 2,500, 10,000 and 50,000 vehicles were conducted. The results indicate that a substantial part of all passenger car trips in Berlin can be substituted. The larger the fleet, the more and longer trips are replaced. Simultaneously, the efficiency in terms of fleet utilization decreases. The scenario with 10,000 e-mopeds offers the lowest total distance-based costs for sharing operators, whereas a fleet consisting of 2,500 vehicles exhibits the lowest environmental emissions per kilometer driven over the expected lifespan of a shared e-moped. Based on the renewable energy potential for 2050 forecasted by the German Federal Environment Agency, a significant overall decline in environmental impacts can be achieved.

The combination of new-generation information technology and manufacturing technology has resulted in major and profound impact on future development paradigm of manufacturing. It is challenging for existing methods to conduct a multidimensional trend exploration related to machine tool domain, which is the basis of virtually everything in manufacturing. In this paper, we proposed an integrating approach framework combined topic models, bibliometric, trend analysis and patent analysis to mine insightful information about future development from multi-source data related to machine tool, such as papers, grants, patents and news. Specifically, papers and grants provided two different perspectives to explore the current focuses and future trends in machine tool research. Furthermore, the future technology development of machine tool was investigated through patents analysis. Finally, news related to machine tool industry in recent years was analyzed to analyze future machine tool business mode. The integration of the above various analytical methods and the multi-dimensional mining of literatures enabled the analysis of the future development of machine tool domain systematically from multi-perspectives which include research, technology development and industry. The conclusions obtained in this paper is beneficial to different communities of machine tool in terms of determining the research directions for researchers, identifying industry opportunities for corporations and developing reasonable industry policy for policy makers.

In daily travel and activities, pathfinding is a significant process. They are often used in transportation routes calculation. They have now evolved to be able to solve most situations of the pathfinding and its related problems. This review describes previous and recent studies on the pathfinding algorithms. It reviews the development of pathfinding algorithms in a classification base on their usage. The aim is to summarize the application of the pathfinding algorithms for the readers interested in the subject that can be used as a supplement.

Generative models have recently gained popularity in Remote Sensing, offering substantial benefits for interpreting and utilizing satellite imagery across diverse applications such as climate monitoring, urban planning, and wildfire detection. These models are particularly adept at addressing the challenges posed by satellite images, which often exhibit domain variability due to seasonal changes, sensor characteristics, and especially variations in spectral bands. Such variability can significantly impact model performance across various tasks. In response to these challenges, our work introduces a novel approach that harnesses the capabilities of Generative Adversarial Networks (GANs), augmented with Contrastive Learning, to generate target domain images that account for multi-spectral band variations effectively. By maximizing mutual information between corresponding patches and leveraging the power of GANs, our model aims to generate realistic-looking images across different multi-spectral domains. We present a comparative analysis of our model against other well-established generative models, demonstrating its efficacy in generating high-quality satellite images while effectively managing domain variations inherent to multi-spectral diversity.

Research within the field of hydrology often focuses on comparing stochastic to machine learning (ML) forecasting methods. The comparisons performed are all based on case studies, while an extensive study aiming to provide generalized results on the subject is missing. Herein, we compare 11 stochastic and 9 ML methods regarding their multi-step ahead forecasting properties by conducting 12 large-scale computational experiments based on simulations. Each of these experiments uses 2 000 time series generated by linear stationary stochastic processes. We conduct each simulation experiment twice; the first time using time series of 100 values and the second time using time series of 300 values. Additionally, we conduct a real-world experiment using 405 mean annual river discharge time series of 100 values. We quantify the performance of the methods using 18 metrics. The results indicate that stochastic and ML methods perform equally well.

Multi-Faith Spaces (MFS) are a relatively recent invention that quickly gained in significance. On the one hand, they offer a convenient solution for satisfying needs of people with diverse beliefs in the institutional context of hospitals, schools, airports, etc. On the other hand, as Andrew Crompton pointed out, they are politically significant because the multi-faith paradigm “is replacing Christianity as the face of public religion in Europe” (2012, p. 493). Due to their ideological entanglement, MFS are often used as the means to promote either a more privatised version of religion, or a certain denominational preference. Two distinct designs are used to achieve these means: negative in the case of the former, and positive in the latter. Neither is without problems, and neither adequately fulfils its primary purpose of serving diverse groups of believers. Both, however, seem to follow the biases and main problems of secularism. In this paper, I analyse recent developments of MFS to detail their main problems and answer the question, whether the MFS, and the underlying Multi-Faith Paradigm, can be classified as a continuation of secularism.

Electricity load forecasting is a crucial undertaking within all the deregulated markets globally. In contemporary times, the transition from conventional electricity grids to Smart Grids constitutes an area where extensive research is conducted on a global scale. Among the research challenges, the investigation of Deep Transfer Learning (DTL) in the field of electricity load forecasting represents a fundamental effort that imparts generality to Artificial Intelligence applications, due to new capabilities, such as knowledge transfer and computational power reduction. In this paper a comprehensive study is conducted for day-ahead electricity load forecasting. For this purpose, three Sequence-to-Sequence (Seq2seq) Deep Learning (DL) models are used, namely the Multilayer Perceptron (MLP), the Convolutional Neural Network (CNN) and the Ensemble Learning Model (ELM), which is consisted of the weighted combination of the outputs of MLP and CNN models. Also, the study focuses on the development of different forecasting strategies based on DTL and emphasizing the way the datasets are trained and fine-tuning for higher forecasting accuracy. In order to implement the forecasting strategies using Deep Learning models, load datasets from three Greek islands, Rhodes, Lesvos, and Chios, are used. The main purpose is to apply DTL for day-ahead predictions (1-24 hours) for each month of the year for Chios dataset after training and fine-tuning the models using the datasets of the three islands in various combinations. After several trials, four DTL strategies are illustrated. In the first strategy (DTL Case 1), each of the three DL models is trained using only Lesvos dataset, while fine-tuning is performed on the dataset of Chios island, in order to create day-ahead predictions for Chios load. In the second strategy (DTL Case 2), data from both Lesvos and Rhodes concurrently are used for the DL model training period, and fine-tuning is performed on the data from Chios. The third DTL strategy (DTL Case 3) contains the training of the DL models using Lesvos dataset, and the testing period performed directly on the Chios dataset without fine-tuning. The fourth strategy is a Multi-task Deep Learning (MTDL) approach, which has been extensively studied in recent years. In MTDL, the three DL models are trained simultaneously on all three datasets and the final predictions are made on the unknown part of the dataset of Chios. In this paper, we explore the performance of DTL and compare the results with those produced with MTDL. The results demonstrated that DTL can be applied with high efficiency for day-ahead load forecasting. Specifically, the two cases with fine-tuning (DTL Case 1 and 2) outperformed MTDL in terms of load prediction accuracy. Regarding the DL models, all three exhibit very high prediction accuracy, especially in the two cases with fine-tuning. The ELM excels compared to the single models. More specifically, for conducting day-ahead predictions, it has been concluded that the MLP model presents best monthly forecasts with a MAPE of 6.24% and 6.01% for the first two cases, the CNN model presents best monthly forecasts with a MAPE of 5.57% and 5.60% respectively and the ELM model achieves best monthly forecasts with a MAPE of 5.29% and 5.31%, respectively, indicating the very high accuracy it can achieve.

This paper investigates nonverbal communication in human interactions, with a specific focus on facial expressions. Employing a Long Short-Term Memory (LSTM) architecture and a custom-ized facial expression framework, our approach aims to improve virtual agent interactions by incorporating subtle nonverbal cues. The paper contributes to the emerging field of facial expres-sion generation, addressing gaps in current research and presenting a novel framework within Unreal Engine 5. The model's architecture, trained on the CANDOR corpus, captures temporal dynamics, and refines hyperparameters for optimal performance. During testing, the trained model showed a cosine similarity of -0.95. This enables the algorithm to accurately respond to non-verbal cues and interact with humans in a way that is comparable to human-human interac-tion. Unlike other approaches in the field of facial expression generation, the presented method is more comprehensive and enables the integration of a multi-modal approach for generating facial expressions. Future work involves integrating blendshape generation, real-world testing, and the inclusion of additional modalities to create a comprehensive framework for seamless hu-man-agent interactions beyond facial expressions.

Numerous innovative advancements in dressing technology for wound healing have emerged. Among the various types of wound dressings available, hydrogel dressings, structured with a three-dimensional network and composed of predominantly hydrophilic components, are widely used for wound care due to their remarkable capacity to absorb abundant wound exudate, maintain a moisture environment, provide soothing and cooling effects, and mimic the extracellular matrix. Composite hydrogel dressings, one of the evolved dressings, address the limitations of traditional hydrogel dressings by incorporating additional components, including particles, fibers, fabrics, or foams, within the hydrogels, effectively promoting wound treatment and healing. The added elements enhance the features or add specific functionalities of the dressings, such as sensitivity to external factors, adhesiveness, mechanical strength, control over the release of therapeutic agents, antioxidant and antimicrobial properties, and tissue regeneration behavior. They can be categorized as natural or synthetic based on the origin of the main components of the hydrogel network. This review focuses on recent research on developing natural polysaccharide-based composite hydrogel wound dressings. Their preparation and composition, the reinforcement materials integrated into hydrogels, and therapeutic agents are also explored. Furthermore, their features and the specific types of wounds where applied are discussed as well.

Objectives: Non-adhesive gel-like embolic materials (NAGLEMs) are becoming increasingly dominant in the endovascular treatment of hypervascularised formations in the head and neck due to a combination of their key properties. The main advantages include their lack of adhesion, effective distribution and penetration through pathological vessels, and crucially, their controlla-bility during the process. Our assigned duty was to scrutinise the literature and assess the efficacy and outcomes of administering NAGLEMs, in comparison to other embolizing substances (name-ly, coils, glue, and particles), among patients treated at our clinic. The procedures involved ana-lyzing the technical aspects, efficiency, and safety of endovascular therapy applied to two catego-ries of hypervascular pathological anomalies, surgically managed from 2015 to 2023. Arteriove-nous malformations (AVMs) located in the head, neck, and paragangliomas with jugular/carotid body localization are combined by intense shunting blood flow and shared requirements for em-bolizates used in endovascular treatment (such as penetration, distribution, delayed polymeriza-tion and controllability). An analysis of the literature was also conducted. Results showed 18 pa-tients diagnosed with neck paragangliomas of the carotid body and jugular type. Five patients with arteriovenous malformation (AVM) of the face and neck were included, consisting of 16 fe-males and 7 males with an average age of 55 ± 13 years. Endovascular procedures were conduct-ed using NAGLEMs (ONYX (Medtronic), SQUID (Balt), and PHIL (Microvention)) and dimethyl sulfoxide (DMSO)-compatible balloon catheters. All patients achieved complete or partial embo-lization of hypervascularized formations using one or more stages of endovascular treatment. Additionally, three AVMs of the face and two paragangliomas of the neck were surgically ex-cised following embolization. In other instances, formations were not deemed necessary to be re-moved. The patients' condition upon discharge was assessed by the modified Rankin Scale (mRs) and rated between 0 and 2. Conclusion: Currently, NAGLEMs are predominantly used to treat hypervascularized formations in the neck and head due to their fundamental properties. These properties include a lack of adhesion and a delay in predictable polymerization (after 30-40 minutes). NAGLEMs also exhibit excellent distribution and penetration throughout the vascular bed of the formation. Adequate controllability of the process is largely achieved through the pres-ence of embolism forms of different viscosity, as well as excellent X-ray visualization.

We aim to evaluate efficiency of two American surveillance systems for monitoring the spread of antimicrobial-resistant (AMR) gonorrhea among men who have sex with men (MSM) using the novel continuous-time agent-based model of gonorrhea transmission. The model was developed using the simulation modelling tool AnyLogic and accounts for susceptible and resistant strains of N. gonorrhoeae, symptomatic and asymptomatic infection and various routes of transmission between different anatomical sites. The model was calibrated using a Bayesian calibration approach. The surveillance systems are the Gonococcal Isolate Surveillance Project (GISP) and the enhanced Gonococcal Isolate Surveillance Project (eGISP). We calculated accuracy, sensitivity, specificity and estimation error for each surveillance system based on the number of isolates submitted in 2018. We also varied that number to see its effect on the outcomes. Our results show that the accuracy of eGISP was between 66% and 92%, while GISP demonstrates low accuracy between 44% and 48%. We also determined that increasing the number of isolates results in improved performance for eGISP, while GISP is not particularly sensitive to it.

The aim of current study is adjusted and synthesized liposomal compound of N. sativa and evaluation its antifungal properties against C. parapsilosis isolates. Fifteen clinical isolates of C. parapsilosis complex isolates were obtained from hospitalized patients affected by candidemia in Mashhad city, Iran, along with a reference strain of C. parapsilosis (ATCC 22019) were assessed by flight mass spectrometry (MALDI-TOF) method, as described previously. N. sativa is encapsulated in liposomal Nanocariers by using thin film hydration technique. At the beginning liposomal nanoparticles was characterized and confirmed with the dynamic light scattering technique (DLS) and Transmission electron microscopy. Then minimum inhibitory concentration of liposomal N. sativa oil was conducted with the CLSI M27 A3 protocol and finally Cytotoxicity function of N. sativa oil liposomal nanocarriers on PBMCs was investigated and confirmed with MTT assay by the results of this research N. sativa oil-Lip-NP didn’t show any toxic effect on PBMCs and The minimum inhibitory concentration (MIC) range of free N. sativa oil and liposomal formulation with inhibitory effects on candida isolates was between 128 - 8, 250 - 31.25 µg ml also MIC50 and MIC90 were 125,187 and 32,96, µg ml respectively. Due to the hydrophobicity and hydrophilicity, biocompatibility, particle size, non-toxic effect, and higher cell viability of N. sativa oil -Lip-NP, it could be considered a more effective approach to treating fungal infections.

Chemical warfare agents (CWAs) are one of the most toxic compounds. Degradation of CWAs using decontamination agents is one of the few ways to protect human health against the harmful effects of CWAs. A ferrate Fe(VI) based potential chemical warfare agent decontaminant was studied for degradation of persistent nitrogen mustard (tris(2-chloroethyl)amine, HN3). By optimizing the reaction conditions, the complete degradation of HN3 was achieved in 4 minutes. The degradation products contained mostly reduced Fe species which confirmed the environmental friendliness of the proposed decontamination solution.

ASEAN SME has a role as the regional socioeconomic stabilizer. This particular role is inseparable from endogenous multi-sector collaboration. Although, Indonesian SMEs were struggled in adopting Industry 4.0 correspond to digital infrastructure and digital literacy problems. This study evaluates Indonesian SME collaboration dynamics with government and technology startup (TS). The integration of agent-based model and causal loop simulation were employed to assess the TS collaboration impact on SME Industry 4.0 adoption and SME competition with larger competitors. The simulation results imply the SME collaboration with TS can lead to early adoption of Industry 4.0 which balances the business competition environment. The model also shows rising the government aid exponentially can help the SME to late adoption of Industry 4.0 which unable to sustain the SME in business competition. Thus, the developed integrative simulation model is a state-action planning model with each state result bounded to the previous state result that determined by initial input parameters. Conclusively, the model can be used as a resiliency planner for SME Industry 4.0 adoption.

Substantial research is required to ensure that micro-mobility ride sharing provides a better fulfillment of user needs. This study proposes a novel crowdsourcing model for the ride-sharing system where light vehicles such as scooters and bikes are crowdsourced. The proposed model consists of three entities: suppliers, customers, and a management party responsible for receiving, renting, booking, and demand matching with offered resources. It can allow suppliers to define the location of their private e-scooters/e-bikes and the period of time they are available for rent. Using a dataset of over 9 million e-scooter trips in Austin, Texas, we ran an agent-based simulation six times using three maximum battery ranges (i.e., 35, 45, and 60 km) and different numbers of e-scooters (e.g., 50 and 100) at each origin. Computational results show that the proposed model is promising and might be advantageous to shift the charging and maintenance efforts to a crowd of suppliers.

Modern agent-based models (ABM) and other simulation models require evaluation and testing of many different parameters. Managing that testing for large scale parameter sweeps (grid searches) as well as storing simulation data requires multiple, potentially customizable steps that may vary across simulations. Furthermore, parameter testing, processing, and analysis are slowed if simulation and processing jobs cannot be shared across teammates or computational resources. While high-performance computing (HPC) has become increasingly available, models can often be tested faster through the use of multiple computers and HPC resources. To address these issues, we created the Distributed Automated Parameter Testing (DAPT) Python package. By hosting parameters in an online (and often free) "database", multiple individuals can run parameter sets simultaneously in a distributed fashion, enabling ad hoc crowdsourcing of computational power. Combining this with a flexible, scriptable tool set, teams can evaluate models and assess their underlying hypotheses quickly. Here we describe DAPT and provide an example demonstrating its use.

This study was conducted to improve the white index (WI) by preparing thermally expandable microspheres (TEMs) for wallpaper. The thermal properties, foam expansion ratio and WI were studied depending on the particle size of colloidal silica in the preparation of TEMs. As a result, the TEMs with small particles of colloidal silica showed the best results for whiteness and yellowing. Additionally, TGA results indicated that it was highly possible that colloidal silica with small particle sizes was physically or chemically attached to the surface of the TEMs that led to an improvement in whiteness at high temperatures.

In Ultra-wideband (UWB)-based wireless ranging or distance measurement, differentiation between line-of-sight~(LOS), non-line-of-sight~(NLOS), and multi-path (MP) conditions are important for precise indoor localization. This is because the accuracy of the reported measured distance in UWB ranging systems is directly affected by the measurement conditions (LOS, NLOS or MP). However, the major contributions in literature only address the binary classification between LOS and NLOS in UWB ranging systems. The MP condition is usually ignored. In fact, the MP condition also has a significant impact on the ranging errors of the UWB compared to the direct LOS measurement results. Though, the magnitudes of the error contained in MP conditions are generally lower than completely blocked NLOS scenarios. This paper addresses machine learning techniques for identification of the mentioned three classes (LOS, NLOS, and MP) in the UWB indoor localization system using an experimental data-set. The data-set was collected in different conditions at different scenarios in indoor environments. Using the collected real measurement data, we compare three machine learning (ML) classifiers, i.e., support vector machine (SVM), random forest (RF) based on an ensemble learning method, and multilayer perceptron (MLP) based on a deep artificial neural network, in terms of their performance. The results show that applying ML methods in UWB ranging systems are effective in identification of the above-mentioned three classes. In specific, the overall accuracy reaches up to 91.9% in the best-case scenario and 72.9% in the worst-case scenario. Regarding the F1-score, it is 0.92 in the best-case and 0.69 in the worst-case scenario. For reproducible results and further exploration, we (will) provide the publicly accessible experimental research data discussed in this paper at PUB - Publications at Bielefeld University. The evaluations of the three classifiers are conducted using the open-source python machine learning library scikit-learn.

Tracking and early identification of suspected cases are essential to control and prevent potential COVID-19 outbreaks. One of the most popular techniques used to track this disease is the use of Infrared cameras to identify individuals with elevated body temperatures. However, they are limited by their inability to be implemented in open public settings such as public parks or even outdoor recreational centers. This limits their ability to effectively track possible COVID-19 patients as open public recreational places such as parks, concert venues and other public venues are hotspots for the spreading of the virus. Other technological solutions such as thermal scanners require an individual to perform the actual testing as they are not individual standalone technologies. This method of testing can potentially cause the transmission of the virus between the tester and the individual getting tested. As can be seen, an alternative solution is essential to solving this issue. In this study, we aim to present the system, design and potential scope of a non-invasive system that can diagnose and identify potential COVID-19 patients using thermal and optical images of the individual using drone technology. The proposed system (COVIDRONE) combines multi-modal machine intelligence, computer vision and real-time monitoring to enable scalable monitoring. The system will also involve the use of machine learning algorithms for better and more accurate diagnosis. We envisage that development of such technologies may help in developing technological solutions to combat infectious disease threats in the future pandemics.

Multi-channel and multi-parameter near-infrared spectrometers (NIRS) have gradually become a new research direction and hot spot due to their ability to provide real-time, continuous, comprehensive indicators of multiple parameters. However, multi-channel and multi-parameter detection may lead to crosstalk between signals. There is still a lack of benchmarks on the evaluation of reliability, sensitivity, stability and response consistency of the NIRS instrument. In this study, a set of test methods (the ink drop test, multi-channel crosstalk test and multi-parameter crosstalk test) for analysis crosstalk and verifying the reliability of NIRS were conducted to test experimental verification on a multi-channel (8-channel), multi-parameter (4-parameter) NIRS instrument independently developed by our team. Results show that these tests can be used to analyze the signal crosstalk and verify the reliability, sensitivity, stability and response consistency in the NIRS instrument. This study contributes to the establishment of benchmarks for the NIRS instrument crosstalk and reliability testing. These novel tests have the potential to become the benchmark for the NIRS instrument reliability testing.

The progressive impairment analysis in gait from neurological diseases patients such as Hereditary Ataxias (HA) has been carried out using gait data collected with movement sensors. This research is focused on finding the minimum amount required of gait features to recognize efficiently and less intrusive way, HA patients based on data collected with iPhone movement sensors placed on the ankles from 14 HA patients and 14 healthy people. A twofold proposal is made , first a local minimum prominent peak criterion to find out the starting point of each stride, to get 10-stride window about which 56 spatial-temporal features are derived; second a search strategy based on Hill Climbing algorithm to reduce the number of gait features and sensors. The main results were the findings that with two gait patterns a 96% of classification accuracy was achieved by using K-Nearest Neighbors (KNN) and Multi-Layer Perceptron (MLP) algorithms, but in addition, MLP only right ankle sensor patterns were required which also allows to reduce the intrusion.

Deep neural networks (DNNs) have gained prominence in addressing regression problems, offering versatile architectural designs that cater to various applications. In the field of earthquake engineering, seismic response prediction is a critical area of study. Simplified models such as single-degree-of-freedom (SDOF) and multi-degree-of-freedom (MDOF) systems have traditionally provided valuable insights into structural behavior, known for their computational efficiency facilitating faster simulations. However, these models have notable limitations in capturing the nuanced nonlinear behavior of structures and the spatial variability of ground motions. This study focuses on leveraging ambient vibration (AV) measurements of buildings, combined with earthquake (EQ) time-history data, to create a predictive model using a neural network (NN) in image format. The primary objective is to predict a specific building's earthquake response accurately. The training dataset consists of 1,197 MDOF 2D shear models, generating a total of 32,319 training samples. To evaluate the performance of the proposed model, termed MLPER (Machine Learning based Prediction of building structures' Earthquake Response), several metrics are employed. These include mean absolute percentage error (MAPE) and mean deviation angle (MDA) for comparisons in the time domain. Additionally, we assess magnitude-squared coherence values and phase differences (Δφ) for comparisons in the frequency domain. This study underscores the potential of MLPER as a reliable tool for predicting building earthquake response, addressing the limitations of simplified models. By integrating AV measurements and EQ time-history data into a neural network framework, MLPER offers a promising avenue for enhancing our understanding of structural behavior during seismic events, ultimately contributing to improved earthquake resilience in building design and engineering.

Multi-criteria decision analysis (MCDA), one of the prevalent branches of operations research, aims to design mathematical and computational tools for selecting the best alternative among several choices with respect to specific criteria. In the cloud, MCDA based online brokers uses customer specified criteria to rank different service providers. However, subjected to limited domain knowledge, the customer may exclude relevant or include irrelevant criterion, which could result in suboptimal ranking of service providers. To deal with such misspecification, this research proposes a model, which uses notion of factor analysis from the domain of unsupervised machine learning. The model is evaluated using two quality-of-service (QoS) based datasets. The first dataset i.e., feedback from customers, was compiled using leading review websites such as Cloud Hosting Reviews, Best Cloud Computing Providers, and Cloud Storage Reviews and Ratings. The second dataset i.e., feedback from servers, was generated from cloud brokerage architecture that was emulated using high performance computing (HPC) cluster at University of Luxembourg (HPC @ Uni.lu). The simulation runs in a stable cloud environment i.e. when uncertainty is low, shows that online broker (equipped with the proposed model) produces optimized ranking of service providers as compared to other brokers. This is due the fact that proposed model assigns priorities to criteria objectively (using machine learning) rather than using priorities based on subjective judgments of the customer. This research will benefit potential cloud customers that view insufficient domain knowledge as a limiting factor for acquisition of web services in the cloud.

In modern security situations, tracking multiple human objects in real-time within challenging urban environments is a critical capability for enhancing situational awareness, minimizing response time, and increasing overall operational effectiveness. Tracking multiple entities enables informed decision-making, risk mitigation, and the safeguarding of civil-military operations to ensure safety and mission success. This paper presents a multi-modal electro-optical/infrared (EO/IR) and radio frequency (RF) fused sensing (MEIRFS) platform for real-time human object detection, recognition, classification, and tracking in challenging environments. By utilizing different sensors in a complementary manner, the robustness of the sensing system is enhanced, enabling reliable detection and recognition results across various situations. Specifically designed Radar tag and thermal tag can be used to discriminate friendly and non-friendly objects. The system incorporates deep learning-based image fusion and human object recognition and tracking (HORT) algorithms to ensure accurate situation assessment. After integrating into an all-terrain robot, multiple ground tests were conducted to verify the consistent HORT in various environments. The MEIRFS sensor system has been designed to meet the Size, Weight, Power, and Cost (SWaP-C) requirements for installation on autonomous ground and aerial vehicles.