Driftage: a multi-agent system framework for concept drift detection.
Ontology highlight
ABSTRACT: Background
The amount of data and behavior changes in society happens at a swift pace in this interconnected world. Consequently, machine learning algorithms lose accuracy because they do not know these new patterns. This change in the data pattern is known as concept drift. There exist many approaches for dealing with these drifts. Usually, these methods are costly to implement because they require (i) knowledge of drift detection algorithms, (ii) software engineering strategies, and (iii) continuous maintenance concerning new drifts.Results
This article proposes to create Driftage: a new framework using multi-agent systems to simplify the implementation of concept drift detectors considerably and divide concept drift detection responsibilities between agents, enhancing explainability of each part of drift detection. As a case study, we illustrate our strategy using a muscle activity monitor of electromyography. We show a reduction in the number of false-positive drifts detected, improving detection interpretability, and enabling concept drift detectors' interactivity with other knowledge bases.Conclusion
We conclude that using Driftage, arises a new paradigm to implement concept drift algorithms with multi-agent architecture that contributes to split drift detection responsability, algorithms interpretability and more dynamic algorithms adaptation.
SUBMITTER: Vieira DM
PROVIDER: S-EPMC8168350 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Wireless sensor networks (WSNs) have been widely investigated in recent years. One of the fundamental issues in WSNs is packet routing, because in many application domains, packets have to be routed from source nodes to destination nodes as soon and as energy efficiently as possible. To address this issue, a large number of routing approaches have been proposed. Although every existing routing approach has advantages, they also have some disadvantages. In this paper, a multi-agent framework is proposed that can assist existing routing approaches to improve their routing performance. This framework enables each sensor node to build a cooperative neighbour set based on past routing experience. Such cooperative neighbours, in turn, can help the sensor to effectively relay packets in the future. This framework is independent of existing routing approaches and can be used to assist many existing routing approaches. Simulation results demonstrate the good performance of this framework in terms of four metrics: average delivery latency, successful delivery ratio, number of live nodes and total sensing coverage.
| S-EPMC4481995 | biostudies-other
Project description:A two-stage decomposition approach based on a novel multi-agent system (MAS) is proposed for the distributed resource constrained multi-project scheduling problem (DRCMPSP). In stage one, from the point of view of each local project manager, a forward-backward hybrid genetic algorithm (FBHGA) is developed to generate an initial local schedule with the objective of minimizing individual project makespan. In stage two, from the global perspective of project management office, a sequential game-based negotiation mechanism is employed to eliminate global resource conflicts with the objective of minimizing total tardiness cost (TTC). The proposed approach is tested on 140 benchmark problem instances. According to the computational results, high-quality local project schedules can be obtained by FBHGA in stage one. Furthermore, it is observed that our method is capable of dealing with various complex multi-project instances under different degrees of resource conflicts in reasonable CPU running time. Compared to the existing decentralized methods for DRCMPSP, the proposed approach with sequential game-based negotiation mechanism shows the superiority in producing multi-project schedules with lower TTC, especially for large-size and strong conflicting instances.
| S-EPMC6177185 | biostudies-literature
Project description:MotivationDue to the complexity and heterogeneity of multicellular biological systems, mathematical models that take into account cell signalling, cell population behaviour and the extracellular environment are particularly helpful. We present PhysiBoSS, an open source software which combines intracellular signalling using Boolean modelling (MaBoSS) and multicellular behaviour using agent-based modelling (PhysiCell).ResultsPhysiBoSS provides a flexible and computationally efficient framework to explore the effect of environmental and genetic alterations of individual cells at the population level, bridging the critical gap from single-cell genotype to single-cell phenotype and emergent multicellular behaviour. PhysiBoSS thus becomes very useful when studying heterogeneous population response to treatment, mutation effects, different modes of invasion or isomorphic morphogenesis events. To concretely illustrate a potential use of PhysiBoSS, we studied heterogeneous cell fate decisions in response to TNF treatment. We explored the effect of different treatments and the behaviour of several resistant mutants. We highlighted the importance of spatial information on the population dynamics by considering the effect of competition for resources like oxygen.Availability and implementationPhysiBoSS is freely available on GitHub (https://github.com/sysbio-curie/PhysiBoSS), with a Docker image (https://hub.docker.com/r/gletort/physiboss/). It is distributed as open source under the BSD 3-clause license.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC6449758 | biostudies-literature
Project description:Proteins from thermophiles are generally more thermostable than their mesophilic homologs, but little is known about the evolutionary process driving these differences. Here we attempt to understand how the diverse thermostabilities of bacterial ribonuclease H1 (RNH) proteins evolved. RNH proteins from Thermus thermophilus (ttRNH) and Escherichia coli (ecRNH) share similar structures but differ in melting temperature (T(m)) by 20 °C. ttRNH's greater stability is caused in part by the presence of residual structure in the unfolded state, which results in a low heat capacity of unfolding (?Cp) relative to ecRNH. We first characterized RNH proteins from a variety of extant bacteria and found that Tm correlates with the species' growth temperatures, consistent with environmental selection for stability. We then used ancestral sequence reconstruction to statistically infer evolutionary intermediates along lineages leading to ecRNH and ttRNH from their common ancestor, which existed approximately 3 billion years ago. Finally, we synthesized and experimentally characterized these intermediates. The shared ancestor has a melting temperature between those of ttRNH and ecRNH; the T(m)s of intermediate ancestors along the ttRNH lineage increased gradually over time, while the ecRNH lineage exhibited an abrupt drop in Tm followed by relatively little change. To determine whether the underlying mechanisms for thermostability correlate with the changes in T(m), we measured the thermodynamic basis for stabilization--?Cp and other thermodynamic parameters--for each of the ancestors. We observed that, while the T(m) changes smoothly, the mechanistic basis for stability fluctuates over evolutionary time. Thus, even while overall stability appears to be strongly driven by selection, the proteins explored a wide variety of mechanisms of stabilization, a phenomenon we call "thermodynamic system drift." This suggests that even on lineages with strong selection to increase stability, proteins have wide latitude to explore sequence space, generating biophysical diversity and potentially opening new evolutionary pathways.
| S-EPMC4227636 | biostudies-literature
Project description:In recent years, maintenance work on public transport routes has drastically decreased in many countries due to difficult economic situations. The various studies that have been conducted by groups of drivers and groups related to road safety concluded that accidents are increasing due to the poor conditions of road surfaces, even affecting the condition of vehicles through costly breakdowns. Currently, the processes of detecting any type of damage to a road are carried out manually or are based on the use of a road vehicle, which incurs a high labor cost. To solve this problem, many research centers are investigating image processing techniques to identify poor-condition road areas using deep learning algorithms. The main objective of this work is to design of a distributed platform that allows the detection of damage to transport routes using drones and to provide the results of the most important classifiers. A case study is presented using a multi-agent system based on PANGEA that coordinates the different parts of the architecture using techniques based on ubiquitous computing. The results obtained by means of the customization of the You Only Look Once (YOLO) v4 classifier are promising, reaching an accuracy of more than 95%. The images used have been published in a dataset for use by the scientific community.
| S-EPMC7663208 | biostudies-literature
Project description:BACKGROUND: Concept recognition is an essential task in biomedical information extraction, presenting several complex and unsolved challenges. The development of such solutions is typically performed in an ad-hoc manner or using general information extraction frameworks, which are not optimized for the biomedical domain and normally require the integration of complex external libraries and/or the development of custom tools. RESULTS: This article presents Neji, an open source framework optimized for biomedical concept recognition built around four key characteristics: modularity, scalability, speed, and usability. It integrates modules for biomedical natural language processing, such as sentence splitting, tokenization, lemmatization, part-of-speech tagging, chunking and dependency parsing. Concept recognition is provided through dictionary matching and machine learning with normalization methods. Neji also integrates an innovative concept tree implementation, supporting overlapped concept names and respective disambiguation techniques. The most popular input and output formats, namely Pubmed XML, IeXML, CoNLL and A1, are also supported. On top of the built-in functionalities, developers and researchers can implement new processing modules or pipelines, or use the provided command-line interface tool to build their own solutions, applying the most appropriate techniques to identify heterogeneous biomedical concepts. Neji was evaluated against three gold standard corpora with heterogeneous biomedical concepts (CRAFT, AnEM and NCBI disease corpus), achieving high performance results on named entity recognition (F1-measure for overlap matching: species 95%, cell 92%, cellular components 83%, gene and proteins 76%, chemicals 65%, biological processes and molecular functions 63%, disorders 85%, and anatomical entities 82%) and on entity normalization (F1-measure for overlap name matching and correct identifier included in the returned list of identifiers: species 88%, cell 71%, cellular components 72%, gene and proteins 64%, chemicals 53%, and biological processes and molecular functions 40%). Neji provides fast and multi-threaded data processing, annotating up to 1200 sentences/second when using dictionary-based concept identification. CONCLUSIONS: Considering the provided features and underlying characteristics, we believe that Neji is an important contribution to the biomedical community, streamlining the development of complex concept recognition solutions. Neji is freely available at http://bioinformatics.ua.pt/neji.
| S-EPMC3849280 | biostudies-literature
Project description:Diagnosis and management of bone and joint infections (BJI) is a challenging task. The high intra and inter patient's variability in terms of clinical presentation makes it impossible to rely on a systematic description or classical statistical analysis for its diagnosis. Advances can be achieved through a better understanding of the system behavior that results from the interactions between the components at a micro-scale level, which is difficult to mastered using traditional methods. Multiple studies from the literature report factors and interactions that affect the dynamics of the BJI system. The objectives of this study were (i) to perform a systematic review to identify relevant interactions between agents (cells, pathogens) and parameters values that characterize agents and interactions, and (ii) to develop a two dimensional computational model of the BJI system based on the results of the systematic review. The model would simulate the behavior resulting from the interactions on the cellular and molecular levels to explore the BJI dynamics, using an agent-based modeling approach. The BJI system's response to different microbial inoculum levels was simulated. The model succeeded in mimicking the dynamics of bacteria, the innate immune cells, and the bone mass during the first stage of infection and for different inoculum levels in a consistent manner. The simulation displayed the destruction in bone tissue as a result of the alteration in bone remodeling process during the infection. The model was used to generate different patterns of system behaviors that could be analyzed in further steps. Simulations results suggested evidence for the existence of latent infections. Finally, we presented a way to analyze and synthesize massive simulated data in a concise and comprehensive manner based on the semi-supervised identification of ordinary differential equations (ODE) systems. It allows to use the known framework for temporal and structural ODE analyses and therefore summarize the whole simulated system dynamical behavior. This first model is intended to be validated by in vivo or in vitro data and expected to generate hypotheses to be challenged by real data. Step by step, it can be modified and complexified based on the test/validation iteration cycles.
| S-EPMC7080862 | biostudies-literature
Project description:The treatment of large data streams in the presence of concept drifts is one of the main challenges in the field of data mining, particularly when the algorithms have to deal with concepts that disappear and then reappear. This paper presents a new algorithm, called Fast Adapting Ensemble (FAE), which adapts very quickly to both abrupt and gradual concept drifts, and has been specifically designed to deal with recurring concepts. FAE processes the learning examples in blocks of the same size, but it does not have to wait for the batch to be complete in order to adapt its base classification mechanism. FAE incorporates a drift detector to improve the handling of abrupt concept drifts and stores a set of inactive classifiers that represent old concepts, which are activated very quickly when these concepts reappear. We compare our new algorithm with various well-known learning algorithms, taking into account, common benchmark datasets. The experiments show promising results from the proposed algorithm (regarding accuracy and runtime), handling different types of concept drifts.
| S-EPMC4386643 | biostudies-other
Project description:The drift-diffusion model (DDM) is an important decision-making model in cognitive neuroscience. However, innovations in model form have been limited by methodological challenges. Here, we introduce the generalized drift-diffusion model (GDDM) framework for building and fitting DDM extensions, and provide a software package which implements the framework. The GDDM framework augments traditional DDM parameters through arbitrary user-defined functions. Models are solved numerically by directly solving the Fokker-Planck equation using efficient numerical methods, yielding a 100-fold or greater speedup over standard methodology. This speed allows GDDMs to be fit to data using maximum likelihood on the full response time (RT) distribution. We demonstrate fitting of GDDMs within our framework to both animal and human datasets from perceptual decision-making tasks, with better accuracy and fewer parameters than several DDMs implemented using the latest methodology, to test hypothesized decision-making mechanisms. Overall, our framework will allow for decision-making model innovation and novel experimental designs.
| S-EPMC7462609 | biostudies-literature
Project description:The Simon effect is observed in spatial conflict tasks where the response time of subjects is increased if stimuli are presented in a lateralized manner so that they are incongruous with the response information that they represent symbolically. Previous studies have used fMRI to investigate this phenomenon, and while some have been driven by considerations of an underlying model, none have attempted to directly tie model and BOLD response together. It is likely that this is due to Simon models having been predominantly descriptive of the phenomenon rather than capturing the full spectrum of behavior at the level of individual subjects. Sequential sampling models (SSM) which capture full response distributions for correct and incorrect responses have recently been extended to capture conflict tasks. In this study we use our freely available framework for fitting and comparing non-standard SSMs to fit the Simon effect SSM (SE-SSM) to behavioral data. This model extension includes specific estimates of automatic response bias and a conflict counteraction parameter to individual subject behavioral data. We apply this approach in order to investigate whether our task specific model parameters have a correlate in BOLD response. Under the assumption that the SE-SSM reflects aspects of neural processing in this task, we go on to examine the BOLD correlates with the within trial expected decision-variable. We find that the SE-SSM captures the behavioral data and that our two conflict specific model parameters have clear across subject BOLD correlates, while other model parameters, as well as more standard behavioral measures do not. We also find that examining BOLD in terms of the expected decision-variable leads to a specific pattern of activation that would not be otherwise possible to extract.
| S-EPMC7054266 | biostudies-literature