Two-stage Task Research Articles

Selective Attention and Decision-Making Have Separable Neural Bases in Space and Time.

Attention and decision-making processes are fundamental to cognition. However, they are usually experimentally confounded, making it difficult to link neural observations to specific processes. Here we separated the effects of selective attention from the effects of decision-making on brain activity obtained from human participants (both sexes), using a two-stage task where the attended stimulus and decision were orthogonal and separated in time. Multivariate pattern analyses of multimodal neuroimaging data revealed the dynamics of perceptual and decision-related information coding through time with magnetoencephalography (MEG), through space with functional magnetic resonance imaging (fMRI), and their combination (MEG-fMRI fusion). Our MEG results showed an effect of attention before decision-making could begin, and fMRI results showed an attention effect in early visual and frontoparietal regions. Model-based MEG-fMRI fusion suggested that attention boosted stimulus information in the frontoparietal and early visual regions before decision-making was possible. Together, our results suggest that attention affects neural stimulus representations in the frontoparietal regions independent of decision-making.

Two-stage task allocation for multiple construction robots using an improved genetic algorithm

The construction industry is facing serious challenges, such as labor shortage and safety hazards. Construction robots can perform dangerous and repetitive tasks instead of workers. However, complex construction tasks require multi-robot collaboration, which needs efficient task allocation. This paper describes a two-stage task allocation method using an improved Genetic Algorithm (GA) for multiple construction robots. First, a construction task decomposition and grouping method under construction constraints is established, using a steel structure as example. Second, a Multi-Robot Construction Task Allocation (MRCTA) model is developed by modeling construction robots and tasks. Third, the MRCTA problem is divided into two stages, i.e., determining the optimal construction robot group for each task and the best task sequence for each robot group. Finally, a simulated experiment was designed and conducted. The results show that the method can efficiently find optimal solutions and the improved GA can enhance the diversity to achieve well-adapted solutions.

Improved two-stage task allocation of distributed UAV swarms based on an improved auction mechanism

Improved two-stage task allocation of distributed UAV swarms based on an improved auction mechanism

Neural correlates of model-based behavior ininternet gaming disorder and alcohol usedisorder.

An imbalance between model-based and model-free decision-making systems is a commonfeature in addictive disorders. However, little is known about whether similar decision-making deficits appear in internet gaming disorder (IGD). This study compared neurocognitive featuresassociated with model-based and model-free systems in IGD and alcohol use disorder (AUD). Participants diagnosed with IGD (n = 22) and AUD (n = 22), and healthy controls (n = 30) performed the two-stage task inside the functional magnetic resonance imaging (fMRI) scanner. We used computational modeling and hierarchical Bayesian analysis to provide a mechanistic account of their choice behavior. Then, we performed a model-based fMRI analysis and functional connectivity analysis to identify neural correlates of the decision-making processes in each group. The computational modeling results showed similar levels of model-based behavior in the IGD and AUD groups. However, we observed distinct neural correlates of the model-based reward prediction error (RPE) between the two groups. The IGD group exhibited insula-specific activation associated with model-based RPE, while the AUD group showed prefrontal activation, particularly in the orbitofrontal cortex and superior frontal gyrus. Furthermore, individuals with IGD demonstrated hyper-connectivity between the insula and brain regions in the salience network in the context of model-based RPE. The findings suggest potential differences in the neurobiological mechanisms underlying model-based behavior in IGD and AUD, albeit shared cognitive features observed in computational modeling analysis. As the first neuroimaging study to compare IGD and AUD in terms of the model-based system, this study provides novel insights into distinct decision-making processes in IGD.

TOFDS: A Two-Stage Task Execution Method for Fake News in Digital Twin-Empowered Socio-Cyber World

Owing to the breakthrough in mobile wireless communication technologies, almost everyone has been immersed into social networks, while fake news and misinformation are also being pushed into people’s minds with astonishing speed and breadth. The rising disparity between limited computing resources and the exploding news size necessitates innovative solutions to handle the challenge posed by booming data volume and make it more likely to differentiate fake news. In response to the aforementioned dilemma, the social-aware computation offloading system is analyzed, where the digital twin (DT) paradigm is used to simulate tasks offloading and assess the associated costs. Next, to obtain the best offloading choice, we fully consider the social relationship constraints and further propose an online task execution method that includes two stages of cluster selection and computing offloading, named TOFDS. Specifically, it exploits the technologies from multiobjective optimization and deep reinforcement learning (DRL) and realizes the joint optimization of resource utilization, load balancing, service latency, and energy consumption. Eventually, the comparative experiments demonstrate that TOFDS performs well when dealing with fake news data and can adapt to changes in dataset size and service clusters.

Meta-heuristic Algorithms to Optimize Two-Stage Task Scheduling in the Cloud

Meta-heuristic Algorithms to Optimize Two-Stage Task Scheduling in the Cloud

FFMAVP: a new classifier based on feature fusion and multitask learning for identifying antiviral peptides and their subclasses.

Antiviral peptides (AVPs) are widely found in animals and plants, with high specificity and strong sensitivity to drug-resistant viruses. However, due to the great heterogeneity of different viruses, most of the AVPs have specific antiviral activities. Therefore, it is necessary to identify the specific activities of AVPs on virus types. Most existing studies only identify AVPs, with only a few studies identifying subclasses by training multiple binary classifiers. We develop a two-stage prediction tool named FFMAVP that can simultaneously predict AVPs and their subclasses. In the first stage, we identify whether a peptide is AVP or not. In the second stage, we predict the six virus families and eight species specifically targeted by AVPs based on two multiclass tasks. Specifically, the feature extraction module in the two-stage task of FFMAVP adopts the same neural network structure, in which one branch extracts features based on amino acid feature descriptors and the other branch extracts sequence features. Then, the two types of features are fused for the following task. Considering the correlation between the two tasks of the second stage, a multitask learning model is constructed to improve the effectiveness of the two multiclass tasks. In addition, to improve the effectiveness of the second stage, the network parameters trained through the first-stage data are used to initialize the network parameters in the second stage. As a demonstration, the cross-validation results, independent test results and visualization results show that FFMAVP achieves great advantages in both stages.

Model-free decision making resists improved instructions and is enhanced by stimulus-response associations

Human behaviour may be thought of as supported by two different computational-learning mechanisms, model-free and model-based respectively. In model-free strategies, stimulus-response associations are strengthened when actions are followed by a reward and weakened otherwise. In model-based learning, previous to selecting an action, the current values of the different possible actions are computed based on a detailed model of the environment. Previous research with the two-stage task suggests that participants’ behaviour usually shows a mixture of both strategies. But, interestingly, a recent study by da Silva and Hare (2020) found that participants primarily deploy model-based behaviour when they are given detailed instructions about the structure of the task. In the present study, we reproduce this essential experiment. Our results confirm that improved instructions give rise to a stronger model-based component. Crucially, we also found a significant effect of reward that became stronger under conditions that favoured the development of strong stimulus-response associations. This suggests that the effect of reward, often taken as indicator of a model-free component, is related to stimulus-response learning.

Opponent learning with different representations in the cortico-basal ganglia pathways can develop obsession-compulsion cycle.

Obsessive-compulsive disorder (OCD) has been suggested to be associated with impairment of model-based behavioral control. Meanwhile, recent work suggested shorter memory trace for negative than positive prediction errors (PEs) in OCD. We explored relations between these two suggestions through computational modeling. Based on the properties of cortico-basal ganglia pathways, we modeled human as an agent having a combination of successor representation (SR)-based system that enables model-based-like control and individual representation (IR)-based system that only hosts model-free control, with the two systems potentially learning from positive and negative PEs in different rates. We simulated the agent's behavior in the environmental model used in the recent work that describes potential development of obsession-compulsion cycle. We found that the dual-system agent could develop enhanced obsession-compulsion cycle, similarly to the agent having memory trace imbalance in the recent work, if the SR- and IR-based systems learned mainly from positive and negative PEs, respectively. We then simulated the behavior of such an opponent SR+IR agent in the two-stage decision task, in comparison with the agent having only SR-based control. Fitting of the agents' behavior by the model weighing model-based and model-free control developed in the original two-stage task study resulted in smaller weights of model-based control for the opponent SR+IR agent than for the SR-only agent. These results reconcile the previous suggestions about OCD, i.e., impaired model-based control and memory trace imbalance, raising a novel possibility that opponent learning in model(SR)-based and model-free controllers underlies obsession-compulsion. Our model cannot explain the behavior of OCD patients in punishment, rather than reward, contexts, but it could be resolved if opponent SR+IR learning operates also in the recently revealed non-canonical cortico-basal ganglia-dopamine circuit for threat/aversiveness, rather than reward, reinforcement learning, and the aversive SR + appetitive IR agent could actually develop obsession-compulsion if the environment is modeled differently.

Concepts of phenomenological irreversible quantum thermodynamics II: time dependent statistical ensembles of bipartite systems

Abstract The wide-spread opinion is that original quantum mechanics is a reversible theory, but this statement is only true for undecomposed systems that are those systems for which sub-systems are out of consideration. Taking sub-systems into account, as it is by definition necessary for decomposed systems, the interaction Hamiltonians –which are absent in undecomposed systems– can be a source of irreversibility in decomposed systems. Thus, the following two-stage task arises: How to modify von Neumann’s equation of undecomposed systems so that irreversibility appears, and how this modification affects decomposed systems? The first step was already done in Muschik (“Concepts of phenomenological irreversible quantum thermodynamics: closed undecomposed Schottky systems in semi-classical description,” J. Non-Equilibrium Thermodyn., vol. 44, pp. 1–13, 2019) and is repeated below, whereas the second step to formulate a quantum thermodynamics of decomposed systems is performed here by modifying the von Neumann equations of the sub-systems by a procedure wich is similar to that of Lindblad’s equation (G. Lindblad, “On the generators of quantum dynamical semigroups,” Commun. Math. Phys., vol. 48, p. 119130, 1976), but different because the sub-systems interact with one another through partitions.

Quality-Aware Task Allocation for Mobile Crowd Sensing Based on Edge Computing

In the field of mobile crowd sensing (MCS), the traditional client–cloud architecture faces increasing challenges in communication and computation overhead. To address these issues, this paper introduces edge computing into the MCS system and proposes a two-stage task allocation optimization method under the constraint of limited computing resources. The method utilizes deep reinforcement learning for the selection of optimal edge servers for task deployment, followed by a greedy self-adaptive stochastic algorithm for the recruitment of sensing participants. In simulations, the proposed method demonstrated a 20% improvement in spatial coverage compared with the existing RBR algorithm and outperformed the LCBPA, SMA, and MOTA algorithms in 41, 42, and 48 tasks, respectively. This research contributes to the optimization of task allocation in MCS and advances the integration of edge computing in MCS systems.

Integrating Categorization and Decision-Making.

Though individual categorization or decision processes have been studied separately in many previous investigations, few studies have investigated how they interact by using a two-stage task of first categorizing and then deciding. To address this issue, we investigated a categorization-decision task in two experiments. In both, participants were shown six faces varying in width, first asked to categorize the faces, and then decide a course of action for each face. Each experiment was designed to include three groups, and for each group, we manipulated the probabilistic contingencies between stimulus, category assignments, and decision consequences. For each group, each participant received three different sequences of category response, category feedback, decision response, and decision feedback. We found that participants were only partially responsive in the appropriate directions to the contingencies assigned to each group. Comparisons of results from different sequences provided evidence for empirical interference effects of categorization on decisions. The empirical interference effect is defined as the difference between the probability of taking a hostile action in decision-alone conditions and the total probability of taking a hostile action in categorization-decision conditions. To test competing accounts for multiple empirical results, including two-stage choice probabilities and empirical interference effects, we compared a quantum cognition model versus a two-stage exemplar categorization model at both aggregate and individual levels. Using a Bayesian information criterion, we found that the quantum model provided an overall better model fit than the exemplar model. Although both models predicted empirical interference effects, the exemplar model was able to generate probabilistic deviation by incorporating category information of the first stage into the feature representation of the subsequent decision stage, while the quantum model produced interference effect by superposition, measurement, and quantumentanglement.

Machine Learning-Based Two-Stage Task Offloading Optimization for Power Distribution Internet of Things

The increase in the number of services in the power distribution grid leads to a massive increase in task data. Power distribution internet of things (PDIoT) is the specific application of internet of things (IoT) in the power distribution grid. By deploying a large number of PDIoT devices, the voltage, active power, reactive power, and harmonic parameters are collected to support distribution grid services such as fault identification and status detection. Therefore, PDIoT utilizes massive devices to collect and offload tasks to the edge server through 5G network for real-time data processing. However, how to dynamically select edge servers and channels to meet the energy-efficient and low-latency task offloading requirements of PDIoT devices still faces several technical challenges such as task offloading decisions coupling among devices, unobtainable global state information, as well as interrelation of various quality of service (QoS) metrics such as energy efficiency and delay. To this end, we firstly construct a joint optimization problem to maximize the weighted difference between energy efficiency and delay of devices in PDIoT. Then, the joint optimization problem is decomposed into a large-timescale server selection problem and a small-timescale channel selection problem. Next, we propose an ML-based two-stage task offloading algorithm, where the large-timescale problem is solved by two-side matching in the first stage, and the small-timescale problem is solved by adaptive ε -greedy learning in the second stage. Finally, simulation results show that compared with the task offloading delay-first matching algorithm and the matching theory-based task offloading strategy, the proposed algorithm performs superior in terms of energy efficiency and delay.

An attention-based deep convolutional neural network for classification and grading of interferents in serum specimens

Accurate diagnosis depends on the provision of high-quality and efficient laboratory testing in which the serum test is one of the most important tools. However, for various reasons, interferents in serum specimens exist, which affect the accuracy of biochemical tests. Hemolysis, icterus, and lipemia (HIL) are the three most frequent interferents in serum samples. Determining their existence and degree of interference in serum samples before testing is essential to improve test quality. In this study, a deep learning model for classifying and grading HIL interferences is designed under the assumption that the serum color images contain information on the category and degree of interference. Because the major features of the classification and grading should be obtained from the liquid region of the serum, an auxiliary segmentation task was designed to assist the main classification task. The segmentation result provided the position information of the serum region for the main classification task as a spatial attention mechanism, which helped the network to focus on learning the significant features selectively with a channel attention mechanism. The method unified the two-stage task of 3-class classification and 5-degree grading of interferents into one model. The accuracy of the 15-class classification was 98.62%, and the degree grading accuracy of the three serum interferents (HIL) reached 98.74, 98.52, and 98.54%, respectively. This research provides a new approach to realize the automatic classification and grading of HIL interferents in serum specimens.

Multi robot cooperative rescue based on two-stage task allocation algorithm

Task allocation is an important issue in the decision-making of multi robot fire rescue in underground garage. In this paper, a multi robot and multi-objective optimization model is constructed. According to the real-time requirements of fire rescue in the underground garage scene, a two-stage multi robot task allocation algorithm based on ant colony and contract net protocol is proposed, which solves the global deficiency of the allocation result based on contract net protocol and the defect that ant colony optimization can not respond to environmental changes in real time. The comparative test results in dynamic environment show that the two-stage task allocation algorithm is similar to ant colony optimization in global cost, and its real-time performance is better than ant colony optimization.

SR-DSFF and FENet-ReID: A Two-Stage Approach for Cross Resolution Person Re-Identification.

In real-life scenarios, the accuracy of person re-identification (Re-ID) is subject to the limitation of camera hardware conditions and the change of image resolution caused by factors such as camera focusing errors. People call this problem cross-resolution person Re-ID. In this paper, we improve the recognition accuracy of cross-resolution person Re-ID by enhancing the image enhancement network and feature extraction network. Specifically, we treat cross-resolution person Re-ID as a two-stage task: the first stage is the image enhancement stage, and we propose a Super-Resolution Dual-Stream Feature Fusion sub-network, named SR-DSFF, which contains SR module and DSFF module. The SR-DSFF utilizes the SR module recovers the resolution of the low-resolution (LR) images and then obtains the feature maps of the LR images and super-resolution (SR) images, respectively, through the dual-stream feature fusion with learned weights extracts and fuses feature maps from LR and SR images in the DSFF module. At the end of SR-DSFF, we set a transposed convolution to visualize the feature maps into images. The second stage is the feature acquisition stage. We design a global-local feature extraction network guided by human pose estimation, named FENet-ReID. The FENet-ReID obtains the final features through multistage feature extraction and multiscale feature fusion for the Re-ID task. The two stages complement each other, making the final pedestrian feature representation has the advantage of accurate identification compared with other methods. Experimental results show that our method improves significantly compared with some state-of-the-art methods.

EmergEventMine: End-to-End Chinese Emergency Event Extraction Using a Deep Adversarial Network

With the rapid development of the internet and social media, extracting emergency events from online news reports has become an urgent need for public safety. However, current studies on the text mining of emergency information mainly focus on text classification and event recognition, only obtaining a general and conceptual cognition about an emergency event, which cannot effectively support emergency risk warning, etc. Existing event extraction methods of other professional fields often depend on a domain-specific, well-designed syntactic dependency or external knowledge base, which can offer high accuracy in their professional fields, but their generalization ability is not good, and they are difficult to directly apply to the field of emergency. To address these problems, an end-to-end Chinese emergency event extraction model, called EmergEventMine, is proposed using a deep adversarial network. Considering the characteristics of Chinese emergency texts, including small-scale labelled corpora, relatively clearer syntactic structures, and concentrated argument distribution, this paper simplifies the event extraction with four subtasks as a two-stage task based on the goals of subtasks, and then develops a lightweight heterogeneous joint model based on deep neural networks for realizing end-to-end and few-shot Chinese emergency event extraction. Moreover, adversarial training is introduced into the joint model to alleviate the overfitting of the model on the small-scale labelled corpora. Experiments on the Chinese emergency corpus fully prove the effectiveness of the proposed model. Moreover, this model significantly outperforms other existing state-of-the-art event extraction models.

Two-Stage Task Offloading Optimization With Large Deviation Delay Analysis in IoT Networks

In the edge computing Internet of Things network, we minimize the offloading overhead (caused by the bandwidth cost for data transmission and computation resource consumption for task remote processing) while providing the end-to-end (E2E) delay provisioning. Under the scenario, a tandem queue consisting of a transmission queue and a computing process queue is formed by the tasks offloaded to the edge server via wireless link and then processed through the computing resource. Due to the tandem queue, the offloading decision and computing resource allocation are coupled over the tandem queue. To make the problem tractable, we decouple the above two operations and propose a two-stage offloading filtering and computing resource allocation policy. After decouple, we then investigate the delay bound violation probability of the tandem queue by leveraging large deviation analysis. Further, we reveal that under the same E2E delay provisioning, the offloading overhead under the proposed decoupled policy can approach to the non-decoupled optimum by selecting an appropriate value of control parameter. Simulation results verify the theoretical analysis and show the efficiency of the proposed policy.

Model-based learning retrospectively updates model-free values

Reinforcement learning (RL) is widely regarded as divisible into two distinct computational strategies. Model-free learning is a simple RL process in which a value is associated with actions, whereas model-based learning relies on the formation of internal models of the environment to maximise reward. Recently, theoretical and animal work has suggested that such models might be used to train model-free behaviour, reducing the burden of costly forward planning. Here we devised a way to probe this possibility in human behaviour. We adapted a two-stage decision task and found evidence that model-based processes at the time of learning can alter model-free valuation in healthy individuals. We asked people to rate subjective value of an irrelevant feature that was seen at the time a model-based decision would have been made. These irrelevant feature value ratings were updated by rewards, but in a way that accounted for whether the selected action retrospectively ought to have been taken. This model-based influence on model-free value ratings was best accounted for by a reward prediction error that was calculated relative to the decision path that would most likely have led to the reward. This effect occurred independently of attention and was not present when participants were not explicitly told about the structure of the environment. These findings suggest that current conceptions of model-based and model-free learning require updating in favour of a more integrated approach. Our task provides an empirical handle for further study of the dialogue between these two learning systems in the future.

Learning-Aided Beam Prediction in mmWave MU-MIMO Systems for High-Speed Railway

The problem of beam alignment and tracking in high mobility scenarios such as high-speed railway (HSR) becomes extremely challenging, since large overhead cost and significant time delay are introduced for fast time-varying channel estimation. To tackle this challenge, we propose a learning-aided beam prediction scheme for HSR networks, which predicts the beam directions and the channel amplitudes within a period of future time with fine time granularity, using a group of observations. Concretely, we transform the problem of high-dimensional beam prediction into a two-stage task, i.e., a low-dimensional parameter estimation and a cascaded hybrid beamforming operation. In the first stage, the location and speed of a certain terminal are estimated by maximum likelihood criterion, and a data-driven data fusion module is designed to improve the final estimation accuracy and robustness. Then, the probable future beam directions and channel amplitudes are predicted, based on the HSR scenario priors including deterministic trajectory, motion model, and channel model. Furthermore, we incorporate a learnable non-linear mapping module into the overall beam prediction to allow non-linear tracks. Both of the proposed learnable modules are model-based and have a good interpretability. Compared to the existing beam management scheme, the proposed beam prediction has (near) zero overhead cost and time delay. Simulation results verify the effectiveness of the proposed scheme.