Task Processing Research Articles

Collaborative Scheduling Algorithm for Dependent Tasks based on Multi-Agent RL in VEC Environment

To address the problem of limited computing power of vehicles, Vehicle Edge Computing (VEC) allows vehicles to schedule tasks to edge nodes with sufficient resources. In this paper, we propose a multi-agent reinforcement learning (MARL) approach to solve the multi-task scheduling problem in a dynamic VEC environment. First, we model the cooperative scheduling problem of dependent tasks in the VEC environment, considering the task priority and edge node load balancing in the task scheduling process. We define the optimization objective as minimizing the task processing delay and find it is an NP-hard problem. Then, we design a distributed algorithm SCMA based on MARL. The algorithm enables vehicles to find the optimal scheduling strategy by cooperating and sharing resources with each other. Finally, we use SUMO to simulate the road network topology and generate vehicle traffic trajectories. We construct heterogeneous vehicular applications for simulation experiments using the DAG generator. Compared with existing algorithms, the simulation results validate the superiority of the SCMA algorithm.

A Dynamic Memory for Reservoir Computing Utilizing Ion Migration in CuInP2S6

AbstractTime‐series analysis and forecasting play a vital role in the fields of economics and engineering. Neuromorphic computing, particularly recurrent neural networks (RNNs), has emerged as an effective approach to address these tasks. Reservoir computing (RC), a type of RNN, offers a powerful and efficient solution for handling nonlinear information in high‐dimensional spaces and addressing temporal tasks. CuInP2S6 (CIPS), a van der Waals material with ion conductivity, shows promise for sequential task processing. Here, a synapse device based on CIPS is demonstrated that exhibits temporal dynamics under electrical stimulation. By controlling Cu+ ion migration, this study successfully emulates synaptic performance, including potentiation and depression characteristics, and RC. Migration of Cu+ ions is confirmed using piezoresponse and Kelvin probe force microscopy. The device achieves low normalized root mean square errors (NRMSE) of 0.04762 and 0.01402 for the Hénon map and Mackey‐Glass series tasks, respectively. For real‐life time‐series prediction based on the Jena temperature database, an overall NRMSE of 0.03339 is achieved. These results highlight the potential of CIPS ion conductivity for real‐time signal processing in machine learning, expanding applications in neuromorphic computing.

Incentive Oriented Two-Tier Task Offloading Scheme in Marine Edge Computing Networks: A Hybrid Stackelberg-Auction Game Approach

With the increasing exploration of marine resources, various marine wireless devices have been rapidly deployed for different marine applications such as marine navigation, ocean environment monitoring, and seabed resource exploitation. However, due to long transmission delay and low data rate between marine wireless devices and the cloud, it is challenging to satisfy the service requirements of computing-intensive and delay-sensitive tasks. By migrating computing resources from cloud to the near side of ocean, the paradigm of marine edge computing networks, which integrates communication and computation capacities in marine wireless devices, is expected to support a variety of marine tasks (e.g., data collection, monitoring and processing) with low delay and high data rate. However, considering the rationality and selfishness of marine wireless devices and their limited computing-capacity, how to motivate marine wireless devices to conduct task processing becomes an important problem for improving computing efficiency. To address this issue, in this paper, we propose an incentive oriented two-tier task offloading scheme for marine edge computing networks via hybrid Stackelberg-auction game approach, with the objective of improving the offloading efficiency and maximizing marine wireless devices’ utilities. Specifically, for underwater acoustic transmission tier, we exploit multi-access task offloading scheme, in which underwater wireless sensor (UWS) uploads its workloads to an unmanned underwater vehicle (UUV) and a sea surface sink node (SN) via non-orthogonal multiple access (NOMA) transmission. We formulate the utility of each party and model the task offloading process among UWS, UUV and SN as a Stackelberg game to optimize the UWS’s offloading strategy, UUV’s and SN’s price strategies. For radio frequency transmission tier, SN can offload its partial workloads to an unmanned aerial vehicle (UAV) via frequency division multiple access (FDMA) transmission. We provide their utilities and model the offloading process between a SN and a UAV as a double auction game to optimize their bidding strategies. Extensive simulation results are provided to validate the performance of the proposed scheme. Numerical results demonstrate that the proposed algorithms can obtain the optimal solutions and increase the utilities for marine wireless devices.

A Multi-Swarm PSO Approach to Large-Scale Task Scheduling in a Sustainable Supply Chain Datacenter

Supply chain management is a vital part of ensuring service quality and production efficiency in industrial applications. With the development of cloud computing and data intelligence in modern industries, datacenters have become an important basic support for intelligent applications. However, the increase in the number and complexity of tasks makes datacenters face increasingly heavy task processing demands. Therefore, there are problems of long task completion time and long response time in the task scheduling process of the data center. A multi-swarm particle swarm optimization task scheduling approach based on load balancing is proposed in this paper, aiming to reduce the maximum completion time and response time in task scheduling. The proposed approach improves the fitness evaluation function of particle swarms to facilitate load balancing. The new adaptive inertia weight and initialization method design can improve the search efficiency and convergence speed of particles. Meanwhile, the multi-swarm design can avoid the problem of particles falling into local optimum as much as possible. Finally, the proposed algorithm is verified experimentally using the task dataset released by Alibaba datacenter, and compared with other benchmark algorithms. The results show that the proposed algorithm can improve the task scheduling performance of the datacenter in supply chain management when dealing with different workloads and changes in the number of elastic machines.

Neural mechanisms of sequential dependence in time perception: the impact of prior task and memory processing.

Our perception and decision-making are susceptible to prior context. Such sequential dependence has been extensively studied in the visual domain, but less is known about its impact on time perception. Moreover, there are ongoing debates about whether these sequential biases occur at the perceptual stage or during subsequent post-perceptual processing. Using functional magnetic resonance imaging, we investigated neural mechanisms underlying temporal sequential dependence and the role of action in time judgments across trials. Participants performed a timing task where they had to remember the duration of green coherent motion and were cued to either actively reproduce its duration or simply view it passively. We found that sequential biases in time perception were only evident when the preceding task involved active duration reproduction. Merely encoding a prior duration without reproduction failed to induce such biases. Neurally, we observed activation in networks associated with timing, such as striato-thalamo-cortical circuits, and performance monitoring networks, particularly when a "Response" trial was anticipated. Importantly, the hippocampus showed sensitivity to these sequential biases, and its activation negatively correlated with the individual's sequential bias following active reproduction trials. These findings highlight the significant role of memory networks in shaping time-related sequential biases at the post-perceptual stages.

은행권의 경쟁력 확보를 위한 ChatGPT 활용방안 연구

Recently, the banking industry has been implementing AI bankers utilizing artificial intelligence on-site. However, the application of AI bankers has revealed various technical issues, prompting efforts by banks to address and improve them. In this paper, we propose the combination of AI bankers and ChatGPT as one method of improvement. It is anticipated that this combination will alleviate some of the identified issues and bring about diverse changes in banking services. Specifically, we suggest enabling AI bankers to handle customer interactions by leveraging ChatGPT's ability to store and recall previous conversation context. Additionally, we propose expanding the scope of AI bankers by combining them with ChatGPT trained on regional dialects to recognize and incorporate regional expressions. This approach is expected to enhance productivity and efficiency by bankers focusing on other core tasks. Moreover, the introduction of ChatGPT for employees is expected to improve the quality of banking services through accurate task processing, ultimately increasing customer satisfaction.

Penyuluhan Mengenai Artificial Intelligence Untuk Siswa-Siswi SMP dan SMA Sekolah Lentera Harapan Medan

Artificial Intelligence (Artificial Intelligence or AI) is a field that is growing rapidly and has great potential in influencing various aspects of human life. AI education is important for the younger generation in facing future challenges. This study aims to teach the basics of AI to junior high school (SMP) students at Sekolah Lentera Harapan (SLH). Learning sessions are carried out using interactive methods and actively involve students in discussions. The material includes an introduction to AI, the history and purpose of AI, how it works, the types of AI, and the advantages and disadvantages of AI. AI needs data to come up with appropriate answers, and with time, it will learn and improve. There are three types of AI, namely Artificial Narrow Intelligence (limited AI), Artificial General Intelligence (general AI), and Artificial Superintelligence (super AI). The advantages of AI include fast data processing, job efficiency and handling of dangerous tasks. However, there are also drawbacks such as reliance on big data, limitations to the specific capabilities of AI, and security concerns. This research provides insight into AI and promotes optimal use of AI in society.

The fuzzy human-robot collaboration assembly line balancing problem

Consideration is given to the assembly line balancing problem (ALBP) in production lines employed collaborative robots. Human–robot collaboration promises high advantages in manufacturing regarding automation, productivity, accuracy as well as flexibility in production. This technology is really challenging but requires redesigning of assembly lines to effectively involve the available human- and robot-resources. As robots can collaborate with humans sharing the assembly tasks in the same workstation, production managers experience an increasingly complex ALBP setting. Moreover, a crucial issue raised within this context is the variance and uncertainty in processing times for manual (human) work. Processing times for human work are subject to the nature and skills of the human worker. We explore the heuristic solution of this NP-hard problem using a problem-specific metaheuristic. Our aim is to investigate the effects of utilizing collaborate robots in manual assembly lines with respect to both production rate and workload smoothing. Simulation experiments on a real-life case study borrowed from the literature show how to tackle the problem under uncertainty (fuzziness) in task processing times.

Stackelberg game‐based task offloading in mobile edge computing‐enabled hierarchical multi‐coalition unmanned aerial vehicle networks

SummaryThe unmanned aerial vehicle (UAV) coalition networks have been widely used in emergency mission scenarios. The introduction of the mobile edge computing (MEC) paradigm into multi‐coalition UAV networks further improves the mission processing performance of UAV coalitions. In this paper, we investigate the problem of minimizing total task processing delay of UAV members in MEC‐enabled coalition‐based UAV networks. First, we propose a hierarchical offloading model in which multiple UAV heads decide its position selection strategy and multiple UAV members decide its offloading strategy when offloading tasks to UAV heads. Considering data arrival from multiple UAV member nodes at each UAV head, the first come first served (FCFS) queuing model is introduced when the UAV head processes tasks from members. Second, the hierarchical offloading delay minimization problem is formulated as a multi‐leader multi‐follower Stackelberg game. The existence of a Stackelberg equilibrium (SE) is proved by showing that multi‐leader subgame and multi‐follower subgame are exact potential games (EPGs) with Nash equilibrium (NE). We design a best response‐based hierarchical iterative offloading algorithm to solve SE. Finally, the simulation results show that the performance of the proposed scheme is better than that of other benchmark methods and the proposed scheme can effectively reduce the total delay for all UAV members.

A flexible algorithm to offload DAG applications for edge computing

Multi-access Edge Computing (MEC) is an enabling technology to leverage new network applications, such as virtual/augmented reality, by providing faster task processing at the network edge. This is done by deploying servers closer to the end users to run the network applications. These applications are often intensive in terms of task processing, memory usage, and communication; thus mobile devices may take a long time or even not be able to run them efficiently. By transferring (offloading) the execution of these applications to the servers at the network edge, it is possible to achieve a lower completion time (makespan) and meet application requirements. However, offloading multiple entire applications to the edge server can overwhelm its hardware and communication channel, as well as underutilize the mobile devices’ hardware. In this paper, network applications are modeled as Directed Acyclic Graphs (DAGs) and partitioned into tasks, and only part of these tasks are offloaded to the edge server. This is the DAG application partitioning and offloading problem, which is known to be NP-hard. To approximate its solution, this paper proposes the FlexDO algorithm. FlexDO combines a greedy phase with a permutation phase to find a set of offloading decisions, and then chooses the one that achieves the shortest makespan. FlexDO is compared with a proposal from the literature and two baseline solutions, considering realistic DAG applications extracted from the Alibaba Cluster Trace Program. FlexDO results are consistently only 3.9% to 8.9% above the optimal makespan in all test scenarios, which include different levels of CPU availability, a multi-user case, and different communication channel transmission rates. FlexDO outperforms both baseline solutions by a wide margin, and is three times closer to the optimal makespan than its competitor. It achieves up to 87% similarity with the optimal decision and does not burden the edge server.

Minimize average tasks processing time in satellite mobile edge computing systems via a deep reinforcement learning method

Recently, the development of Low Earth Orbit (LEO) satellites and the advancement of the Mobile Edge Computing (MEC) paradigm have driven the emergence of the Satellite Mobile Edge Computing (Sat-MEC). Sat-MEC has been developed to support communication and task computation for Internet of Things (IoT) Mobile Devices (IMDs) in the absence of terrestrial networks. However, due to the heterogeneity of tasks and Sat-MEC servers, it is still a great challenge to efficiently schedule tasks in Sat-MEC servers. Here, we propose a scheduling algorithm based on the Deep Reinforcement Learning (DRL) method in the Sat-MEC architecture to minimize the average task processing time. We consider multiple factors, including the cooperation between LEO satellites, the concurrency and heterogeneity of tasks, the dynamics of LEO satellites, the heterogeneity of the computational capacity of Sat-MEC servers, and the heterogeneity of the initial queue for task computation. Further, we use the self-attention mechanism to act as a Q-network to extract high-dimensional dynamic information of tasks and Sat-MEC servers. In this work, we model the Sat-MEC environment simulation at the application level and propose a DRL-based task scheduling algorithm. The simulation results confirm the effectiveness of our proposed scheduling algorithm, which reduces the average task processing time by 22.1%, 30.6%, and 41.3%, compared to the genetic algorithm(GA), the greedy algorithm, and the random algorithm, respectively.

Evidence against implicit belief processing in a blindfold task.

Understanding what other people think is crucial to our everyday interactions. We seem to be affected by the perspective of others even in situations where it is irrelevant to us. This intrusion from others' perspectives has been referred to as altercentric bias and has been suggested to reflect implicit belief processing. There is an ongoing debate about how robust such altercentric effects are and whether they indeed reflect true mentalizing or result from simpler, domain-general processes. As a critical test for true mentalizing, the blindfold manipulation has been proposed. That is, participants are familiarized with a blindfold that is either transparent or opaque. When they then observe a person wearing this blindfold, they can only infer what this person can or cannot see based on their knowledge of the blindfold's transparency. Here, we used this blindfold manipulation to test whether participants' reaction times in detecting an object depended on the agent's belief about the object's location, itself manipulated with a blindfold. As a second task, we asked participants to detect where the agent was going to look for the object. Across two experiments with a large participant pool (N = 234) and different settings (online/lab), we found evidence against altercentric biases in participants' response times in detecting the object. We did, however, replicate a well-documented reality congruency effect. When asked to detect the agent's action, in turn, participants were biased by their own knowledge of where the object should be, in line with egocentric biases previously found in false belief reasoning. These findings suggests that altercentric biases do not reflect belief processing but lower-level processes, or alternatively, that implicit belief processing does not occur when the belief needs to be inferred from one's own experience.

E‐TOALB: An efficient task offloading in IoT‐fog networks

SummarySmart devices are concerned about the processing and computation of tasks due to their tiny nature. They prefer to offload their tasks to the cloud for processing and computation. Due to the huge amount of data being generated by smart devices, the cloud becomes inefficient in terms of huge delay. Thus, Processing tasks in the cloud can add latency and finally needs to be addressed. Thus, fog computing is an alternative to the latency issue. The tasks are offloaded to fog instead of the cloud. In this paper, e‐TOALB (enhanced task offloading and load balancing), a modified and enhanced nature‐inspired and meta‐heuristic ant colony optimization is used to offload tasks in a fog environment. The results obtained by the proposed method are compared with Particle swarm optimization (PSO), round robin (RR), and ant colony optimization. The numerical results clearly show an improvement in average response time and load sharing among all fog nodes. The results of the proposed model produce low response time, low average service time, and low standard deviation. The proposed scheme aims to find the best possible decision for offloading tasks to nearby fog devices and to find an optimal route for offloading with the least communication cost and average service time.

Utilization of Johnson's Algorithm for Enhancing Scheduling Efficiency and Identifying the Best Operation Sequence: An Illustrative Scenario

This study's primary objective is the enhancement of makespan optimization, thereby minimizing unproductive time for both machinery and tasks. The research employs a case study methodology, focusing on job scheduling within anElectronicsmanufacturing facility, with a particular emphasis on resource availability. It implements Johnson's algorithm and its expanded versions designed for both two-machine and three-machine scenarios within the context of flow shop scheduling. The principal aim is to identify optimal sequences for scheduling. Within this framework, the investigation computes idle time and makespan metrics for individual machines, utilizing task processing durations and in-out timestamps. The findings reveal anoptimal idle time of 6.21 minutes and a makespan of 142.06minutes for scenarios involving two machines. Furthermore, the research extends its analysis to scenarios with three machines, where two machines are combined in each group, resulting in an optimal idle time of 5.22minutes for combined machine A2, 14.98minutes for combined machine A3, and a makespan of 192minutes. This study provides valuable insights applicable to industries dealing with diverse machinery and components, ultimately contributing to improved scheduling and productivity.

Brain-to-brain communication during musical improvisation: a performance case study

Understanding and predicting others' actions in ecological settings is an important research goal in social neuroscience. Here, we deployed a mobile brain-body imaging (MoBI) methodology to analyze inter-brain communication between professional musicians during a live jazz performance. Specifically, bispectral analysis was conducted to assess the synchronization of scalp electroencephalographic (EEG) signals from three expert musicians during a three-part 45 minute jazz performance, during which a new musician joined every five minutes. The bispectrum was estimated for all musician dyads, electrode combinations, and five frequency bands. The results showed higher bispectrum in the beta and gamma frequency bands (13-50 Hz) when more musicians performed together, and when they played a musical phrase synchronously. Positive bispectrum amplitude changes were found approximately three seconds prior to the identified synchronized performance events suggesting preparatory cortical activity predictive of concerted behavioral action. Moreover, a higher amount of synchronized EEG activity, across electrode regions, was observed as more musicians performed, with inter-brain synchronization between the temporal, parietal, and occipital regions the most frequent. Increased synchrony between the musicians' brain activity reflects shared multi-sensory processing and movement intention in a musical improvisation task.

Heterogeneous Regularization-Based Tensor Subspace Clustering for Hyperspectral Band Selection.

Band selection (BS) reduces effectively the spectral dimension of a hyperspectral image (HSI) by selecting relatively few representative bands, which allows efficient processing in subsequent tasks. Existing unsupervised BS methods based on subspace clustering are built on matrix-based models, where each band is reshaped as a vector. They encode the correlation of data only in the spectral mode (dimension) and neglect strong correlations between different modes, i.e., spatial modes and spectral mode. Another issue is that the subspace representation of bands is performed in the raw data space, where the dimension is often excessively high, resulting in a less efficient and less robust performance. To address these issues, in this article, we propose a tensor-based subspace clustering model for hyperspectral BS. Our model is developed on the well-known Tucker decomposition. The three factor matrices and a core tensor in our model encode jointly the multimode correlations of HSI, avoiding effectively to destroy the tensor structure and information loss. In addition, we propose well-motivated heterogeneous regularizations (HRs) on the factor matrices by taking into account the important local and global properties of HSI along three dimensions, which facilitates the learning of the intrinsic cluster structure of bands in the low-dimensional subspaces. Instead of learning the correlations of bands in the original domain, a common way for the matrix-based models, our model learns naturally the band correlations in a low-dimensional latent feature space, which is derived by the projections of two factor matrices associated with spatial dimensions, leading to a computationally efficient model. More importantly, the latent feature space is learned in a unified framework. We also develop an efficient algorithm to solve the resulting model. Experimental results on benchmark datasets demonstrate that our model yields improved performance compared to the state-of-the-art.

A configurable process control method for robotic system-based industrial service improvements

Automation-based robotic solutions are widely employed in innovative industrial manufacturing units to avoid unnecessary process errors and delays in outcomes. The robots' density and controls vary with the process and production demands. This paper introduces a Centralized, Configurable Process Control (CCPC) method for reliable industrial task organization and management. The proposed method's configurable control identifies pre-queuing tasks and automated processing through robotic systems. This method uses state-dependent learning to identify the highly configurable robotic controller to improve the task processing rate. The automated, connected systems improve the task's cooperativeness by concurrent allocation and swapping the industrial tasks through self-decisions. The performance of the automated systems is verified based on state learning and concurrency. The results demonstrated substantial enhancements, with a 12.29% increase in processing rate, a 6.31% drop in mistakes, an 11.1% decrease in process latency, and an 11.68% decrease in pre-queuing ratio compared to conventional methods. These results show that the proposed strategy performs very well and is a cutting-edge option for effective job organization in smart industries. Response: The proposed Adaptive Backstepping Recurrently-Connected Fuzzy-Wavelet-Based Neural Network (ABRFWNN), Task-Level Performance (TLP+SS), and Closed Analytical Form (CAF+DLAM) were among the notable methods compared to prove CCPC's efficacy. The findings prove beyond a reasonable doubt that CCPC performs better than these other approaches, representing a significant improvement in the effectiveness of industrial robots.

Location Privacy-Aware and Energy-Efficient Offloading for Distributed Edge Computing

Driven by the ever-increasing scale and intensity of the computing tasks arising from various mobile applications, distributed edge computing has fostered wide research interests. It can effectively reduce the task processing delay by partitioning the original large-scale task into several small subtasks and offloading them to multiple edge nodes (ENs) for parallel computing. In edge computing, as the mobile user usually tends to offload computing tasks to closer ENs to save transmit power, the attacker may stealthily infer user location by exploiting this feature. Although there have been some pioneering works on offloading related location privacy, they mainly focused on the scenario where each task can only be offloaded to a single EN, and may not be directly applicable to distributed edge computing. Besides, the privacy issues considered in existing works are mainly based on good heuristics, and there is still a lack of concrete examples of location privacy attacks in edge computing. To the best of our knowledge, the location privacy issue in distributed edge computing still remains largely unexplored in existing literature. With this consideration, a location inference attack based on matrix sequential probability ratio test (MSPRT) is identified in this work. Besides, a countermeasure based on dynamic multi-EN selection is proposed, together with a location privacy-aware and energy-efficient distributed offloading scheme based on the generic Lyapunov optimization framework. Both theoretic analysis and simulations based on real-world channel measurements are employed to validate the feasibility of the identified MPSRT attack and the effectiveness of the proposed defense scheme.

Latency Guarantee for Task Computation in Wireless-Powered Cloud Radio Access Networks

With the massive and rapid deployment of Internet of Things (IoT) devices, the number of IoT devices in the cloud radio access network (C-RAN) has increased dramatically. It is intractable to provide deterministic quality of service (QoS) guarantee for task processing due to the task burstiness and the time-varying channels. In order to guarantee latency requirements of energy-limited IoT devices in C-RAN, this paper proposes a statistical latency guarantee scheme for task computation. With the assistance of densely distributed remote radio heads (RRHs) providing wireless power transfer to the IoT devices, a wireless powered edge computing C-RAN model is constructed. Then, the problem of minimizing task latency violation probability is formulated. With the help of effective capacity theory, the problem is decoupled into multiple sub-problems, which are QoS parameter optimization, task offloading optimization, wireless power transfer and energy allocation. Thereafter, low-complexity schemes are designed to jointly optimize the wireless power transfer, energy allocation and task offloading. The effectiveness of the proposed statistical latency guarantee scheme is finally validated by extensive simulations.

비대면 e-서비스접점의 운영최적화 비교 연구

As the wave of digital transformation is rapidly permeating various industries and our daily lives, developing a new business model centered around online platforms for creating customer value is an important operational strategy for deriving competitive advantages. This study proposes an approach to optimize the user-centered operation process with contactless e-service encounter activities on an online platform. In this study, e-service encounter activities are categorized into tasks, e-tangibility, and task processing methods. We analyzed the product introduction approach of selected platform companies based on e-tangible characteristics and customer demand handling methods. The analysis identified commonalities and differences among the case companies. The commonalities found were (1) a user-centric operational method; (2) the importance of securing customer trust through product introductions based on user experience and accurate information; and (3) diverse communication channels for rapid response. The differences in operational approaches to e-service encounter activities among the case companies were primarily due to the unique characteristics of each firm, although the companies offer similar platform services. The results of this study provide valuable insights and significant implications for operational optimization of contactless e-service encounter activities to potential companies that are interested in offering online platform services.