• 정보처리학회논문지B
• /
• 제8B권6호
• /
• pp.601-608
• /
• 2001

The automated assignment of multiple tasks to executing agents is a key problem in the area of multi-agent systems. In many domains, significant savings can be achieved by reallocating tasks among agents with different costs for handling tasks. The automation of task reallocation among self-interested agents requires that the individual agents use a common negotiation protocol that prescribes how they have to interact in order to come to an agreement on "who does what". In this paper, we introduce the multi-agent Traveling Salesman Problem(TSP) as an example of task reallocation problem, and suggest the Vickery auction as an interagent negotiation protocol for solving this problem. In general, auction-based protocols show several advantageous features: they are easily implementable, they enforce an efficient assignment process, and they guarantce an agreement even in scenarios in which the agents possess only very little domain-specific Knowledge. Furthermore Vickrey auctions have the additional advantage that each interested agent bids only once and that the dominant strategy is to bid one′s true valuation. In order to apply this market-based protocol into task reallocation among self-interested agents, we define the profit of each agent, the goal of negotiation, tasks to be traded out through auctions, the bidding strategy, and the sequence of auctions. Through several experiments with sample multi-agent TSPs, we show that the task allocation can improve monotonically at each step and then finally an optimal task allocation can be found with this protocol.

• 대한영상의학회지
• /
• 제83권6호
• /
• pp.1208-1218
• /
• 2022

최근, 의료 분야에서 인공지능은 많은 발전을 통해 다양한 분야로 확장하며 활용되고 있다. 하지만 대부분의 인공지능 기술들은 하나의 모델이 하나의 태스크만을 수행할 수 있도록 개발되고 있으며, 이는 의사들의 복잡한 판독 과정을 인공지능으로 설계하는데 한계로 작용한다. 멀티 태스크 러닝은 이러한 한계를 극복하기 위한 최적의 방안으로 알려져 있다. 다양한 태스크들을 동시에 하나의 모델로 학습함으로써, 효율적이고 일반화에 유리한 모델을 만들수 있다. 본 종설에서는 멀티 태스크 러닝에 대한 개념과 종류, 유사 개념 등에 대해 알아보고, 연구 사례들을 통해 의료 분야에서의 멀티 태스크 러닝의 활용 현황과 향후 가능성을 살펴보고자 한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권4호
• /
• pp.1100-1122
• /
• 2023

Scheduling user-submitted cloud tasks to the appropriate virtual machine (VM) in cloud computing is critical for cloud providers. However, as the demand for cloud resources from user tasks continues to grow, current evolutionary algorithms (EAs) cannot satisfy the optimal solution of large-scale cloud task scheduling problems. In this paper, we first construct a large- scale multi-objective cloud task problem considering the time and cost functions. Second, a multi-objective optimization algorithm based on multi-factor optimization (MFO) is proposed to solve the established problem. This algorithm solves by decomposing the large-scale optimization problem into multiple optimization subproblems. This reduces the computational burden of the algorithm. Later, the introduction of the MFO strategy provides the algorithm with a parallel evolutionary paradigm for multiple subpopulations of implicit knowledge transfer. Finally, simulation experiments and comparisons are performed on a large-scale task scheduling test set on the CloudSim platform. Experimental results show that our algorithm can obtain the best scheduling solution while maintaining good results of the objective function compared with other optimization algorithms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권11호
• /
• pp.5546-5559
• /
• 2019

Facial action units (AUs) have recently drawn increased attention because they can be used to recognize facial expressions. A variety of methods have been designed for frontal-view AU detection, but few have been able to handle multi-view face images. In this paper we propose a method for multi-view facial AU detection using a fused multilayer, multi-task, and multi-label deep learning network. The network can complete two tasks: AU detection and facial view detection. AU detection is a multi-label problem and facial view detection is a single-label problem. A residual network and multilayer fusion are applied to obtain more representative features. Our method is effective and performs well. The F1 score on FERA 2017 is 13.1% higher than the baseline. The facial view recognition accuracy is 0.991. This shows that our multi-task, multi-label model could achieve good performance on the two tasks.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2022년도 추계학술발표대회
• /
• pp.308-310
• /
• 2022

With the rise of the Al wave, task-oriented dialogue systems have become one of the popular research directions in academia and industry. Currently, task-oriented dialogue systems mainly adopt pipelined form, which mainly includes natural language understanding, dialogue state decision making, dialogue state tracking and natural language generation. However, pipelining is prone to error propagation, so many task-oriented dialogue systems in the market are only for single-round dialogues. Usually single- domain dialogues have relatively accurate semantic understanding, while they tend to perform poorly on multi-domain, multi-round dialogue datasets. To solve these issues, we developed a paddle-based multi-domain task-oriented Chinese dialogue system. It is based on NEZHA-base pre-training model and CrossWOZ dataset, and uses intention recognition module, dichotomous slot recognition module and NER recognition module to do DST and generate replies based on rules. Experiments show that the dialogue system not only makes good use of the context, but also effectively addresses long-term dependencies. In our approach, the DST of dialogue tracking state is improved, and our DST can identify multiple slotted key-value pairs involved in the discourse, which eliminates the need for manual tagging and thus greatly saves manpower.

• 방송공학회논문지
• /
• 제25권5호
• /
• pp.742-749
• /
• 2020

본 논문에서는 하나의 공용 신경망을 사용하여 음소와 감정을 모두 인식하는 방법과 공용 신경망 학습을 위한 다중 학습 방법을 제안한다. 공용 신경망은 동일한 동작을 수행하여 두 정보를 모두 인식하며, 이는 인간이 하나의 청각기관으로 여러 정보를 동시에 인식하는 구조에 해당한다. 다중 학습은 여러 정보를 위한 공통 모델링을 진행하므로 여러 정보에 대한 일반화된 학습을 진행시켜 기존의 정보별 개별 학습에서 나타나는 과적합을 감소시키고 인식 성능을 향상시킨다. 또한, 다중 학습에서 음소 인식에 가중치를 부여하여 음소 인식 성능을 추가 향상시키는 방법을 제안한다. 동일한 특성벡터와 신경망을 사용할 때, 제안한 다중 학습이 적용된 공용 신경망의 성능이 각 정보별로 학습시킨 개별 신경망에 비하여 우수한 것을 확인하였다.

• Smart Structures and Systems
• /
• 제31권4호
• /
• pp.383-392
• /
• 2023

Post-earthquake building condition assessment is crucial for subsequent rescue and remediation and can be automated by emerging computer vision and deep learning technologies. This study is based on an endeavour for the 2nd International Competition of Structural Health Monitoring (IC-SHM 2021). The task package includes five image segmentation objectives - defects (crack/spall/rebar exposure), structural component, and damage state. The structural component and damage state tasks are identified as the priority that can form actionable decisions. A multi-task Convolutional Neural Network (CNN) is proposed to conduct the two major tasks simultaneously. The rest 3 sub-tasks (spall/crack/rebar exposure) were incorporated as auxiliary tasks. By synchronously learning defect information (spall/crack/rebar exposure), the multi-task CNN model outperforms the counterpart single-task models in recognizing structural components and estimating damage states. Particularly, the pixel-level damage state estimation witnesses a mIoU (mean intersection over union) improvement from 0.5855 to 0.6374. For the defect detection tasks, rebar exposure is omitted due to the extremely biased sample distribution. The segmentations of crack and spall are automated by single-task U-Net but with extra efforts to resample the provided data. The segmentation of small objects (spall and crack) benefits from the resampling method, with a substantial IoU increment of nearly 10%.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제10권8호
• /
• pp.319-330
• /
• 2021

최근 오픈 도메인 자연어 질문 응답 분야에서는 다중 작업, 다중 홉 질문 응답에 관한 연구들이 활발히 진행되어 오고 있다. 본 논문에서는 이러한 다중 작업, 다중 홉 질문들에 효과적으로 응답하기 위해, 계층적 그래프 기반의 새로운 심층 신경망 모델을 제안한다. 제안 모델에서는 계층적 그래프와 그래프 신경망을 이용해 여러 문단들로부터 서로 다른 수준의 맥락 정보를 얻어낸 후, 이들을 활용하여 답변 유형, 뒷받침 문장들과 답변 영역 등을 동시에 예측해낸다. 본 논문에서는 오픈 도메인 자연어 질문 응답 데이터 집합인 HotpotQA를 이용한 실험들을 통해, 제안 모델의 높은 성능과 긍정적 효과를 입증한다.

• 아동학회지
• /
• 제38권3호
• /
• pp.75-90
• /
• 2017

Objective: This study aimed to identify children's cognitive processing and performance characteristics while multiple task performance. It confirmed whether their multiple task performance and psychological refractory period (PRP) varied by task condition (stimulus onset asynchrony [SOA] and task difficulty) and stimulus modality. Methods: Seventy 5-year-olds were recruited. Multi-task tools were developed using the E-prime software. The children were required to respond to two stimuli (visual or auditory) presented with microscopic time difference and their response times (RTs) were recorded. Results: As the SOA increased, the RTs in the first task increased, while the RTs in the second task and PRP decreased. The RTs of the first and second tasks, and the PRP for difficult tasks, were significantly longer than those for easy tasks were. Additionally, there was an interaction effect between the SOA and task difficulty. Although there was no main effect of stimulus modality, task difficulty moderated the modality effect. In the high difficulty condition, the RTs of the first and second tasks and PRP for the visual-visual task were significantly longer than those for auditory-auditory task were. Conclusion: These results inform theoretical discussions on children's multi-task mechanism, and the loss of multiple task performance. Additionally, they provide practical implications and information on the composition of multi-tasks suitable for children in educational environments.

• International Journal of Computer Science & Network Security
• /
• 제23권3호
• /
• pp.31-48
• /
• 2023

The popularization of smart devices and subsequent optimization of their sensing capacity has resulted in a novel mobile crowdsensing (MCS) pattern, which employs smart devices as sensing nodes by recruiting users to develop a sensing network for multiple-task performance. This technique has garnered much scholarly interest in terms of sensing range, cost, and integration. The MCS is prevalent in various fields, including environmental monitoring, noise monitoring, and road monitoring. A complete MCS life cycle entails task allocation, data collection, and data aggregation. Regardless, specific drawbacks remain unresolved in this study despite extensive research on this life cycle. This article mainly summarizes single-task, multi-task allocation, and space-time multi-task allocation at the task allocation stage. Meanwhile, the quality, safety, and efficiency of data collection are discussed at the data collection stage. Edge computing, which provides a novel development idea to derive data from the MCS system, is also highlighted. Furthermore, data aggregation security and quality are summarized at the data aggregation stage. The novel development of multi-modal data aggregation is also outlined following the diversity of data obtained from MCS. Overall, this article summarizes the three aspects of the MCS life cycle, analyzes the issues underlying this study, and offers developmental directions for future scholars' reference.