A Multi-Task Deep Learning Framework for Simultaneous Detection of Thoracic Pathology through Image Classification

Thoracic diseases pose significant risks to an individual's chest health and are among the most perilous medical diseases. They can impact either one or both lungs, which leads to a severe impairment of a person’s ability to breathe normally. Some notable examples of such diseases encompass pneumonia, lung cancer, coronavirus disease 2019 (COVID-19), tuberculosis, and chronic obstructive pulmonary disease (COPD). Consequently, early and precise detection of these diseases is paramount during the diagnostic process. Traditionally, the primary methods employed for the detection involve the use of X-ray imaging or computed tomography (CT) scans. Nevertheless, due to the scarcity of proficient radiologists and the inherent similarities between these diseases, the accuracy of detection can be compromised, leading to imprecise or erroneous results. To address this challenge, scientists have turned to computer-based solutions, aiming for swift and accurate diagnoses. The primary objective of this study is to develop two machine learning models, utilizing single-task and multi-task learning frameworks, to enhance classification accuracy. Within the multi-task learning architecture, two principal approaches exist soft parameter sharing and hard parameter sharing. Consequently, this research adopts a multi-task deep learning approach that leverages CNNs to achieve improved classification performance for the specified tasks. These tasks, focusing on pneumonia and COVID-19, are processed and learned simultaneously within a multi-task model. To assess the effectiveness of the trained model, it is rigorously validated using three different real-world datasets for training and testing.

Multi-Agent模式下的城市暴雨内涝应急决策方法研究

为厘清应对暴雨内涝灾害动态决策过程中决策主体、决策、决策方案等决策要素间的不确定关系,提出1种多主体(Multi-Agent)和贝叶斯决策网络(BDN)相结合的应急决策方法。首先分阶段构建“主体-任务”可视化网络,分析暴雨内涝灾害各应急阶段的主要任务和参与的决策主体;在考虑到决策要素间的动态不确定性可能造成决策风险的前提下,运用Multi-Agent和BDN方法探究各决策要素间的影响关系,以便进行方案集优选。研究结果表明:该方法具有实用性和现实意义,研究结果可为城市暴雨内涝灾害的应急决策提供理论参考。

Multi-tasking to Address Diversity in Language Learning

With focus now placed on the learner, more attention is given to his learning style, multiple intelligence and developing learning strategies to enable him to make sense of and use of the target language appropriately in varied contexts and with different uses of the language. To attain this, the teacher is tasked with designing, monitoring and processing language learning activities for students to carry out and in the process learn by doing and reflecting on the learning process they went through as they interacted socially with each other. This paper describes a task named"The Fishbowl Technique"and found to be effective in large ESL classes in the secondary level in the Philippines.

Multi-task Coalition Parallel Formation Strategy Based on Reinforcement Learning

代理人联盟是代理人协作和合作的一种重要方式。形成一个联盟，代理人能提高他们的能力解决问题并且获得更多的实用程序。在这份报纸，新奇多工联盟平行形成策略被介绍，并且多工联盟形成的过程是一个 Markov 决定过程的结论理论上被证明。而且，学习的加强被用来解决多工联盟平行的代理人行为策略，和这个过程形成被描述。在多工面向的领域，策略罐头有效地并且平行形式多工联盟。

A Distributed Algorithm for Parallel Multi-task Allocation Based on Profit Sharing Learning

经由联盟形成的任务分配是在多代理人系统(妈) 的几应用程序域的基本研究挑战，例如资源分配，灾难反应管理等等。怎么以一种分布式的方式分配许多未解决的任务到一些代理人，主要处理。在这篇论文，我们在自我组织、自我学习的代理人之中建议一个分布式的平行多工分配算法。处理状况，我们在二维的房间地理上驱散代理人和任务，然后介绍为寻找它的任务由的一个单个代理人的分享学习的利润(PSL ) 不断自我学习。我们也在代理人之中为通讯和协商介绍策略分配真实工作量到每个 tasked 代理人。最后，评估建议算法的有效性，我们把它与 Shehory 和 Krau 被许多研究人员在最近的年里讨论的分布式的任务分配算法作比较。试验性的结果证明建议算法罐头快速为每项任务形成一个解决的联盟。而且，建议算法罐头明确地告诉我们每个 tasked 代理人的真实工作量，并且能因此为实际控制任务提供一本特定、重要的参考书。

Face Detection Detection, Alignment Alignment, Quality Assessment and Attribute Analysis with Multi-Task Hybrid Convolutional Neural Networks

This paper proposes a universal framework,termed as Multi-Task Hybrid Convolutional Neural Network(MHCNN),for joint face detection,facial landmark detection,facial quality,and facial attribute analysis.MHCNN consists of a high-accuracy single stage detector(SSD)and an efficient tiny convolutional neural network(T-CNN)for joint face detection refinement,alignment and attribute analysis.Though the SSD face detectors achieve promising results,we find that applying a tiny CNN on detections further boosts the detected face scores and bounding boxes.By multi-task training,our T-CNN aims to provide five facial landmarks,facial quality scores,and facial attributes like wearing sunglasses and wearing masks.Since there is no public facial quality data and facial attribute data as we need,we contribute two datasets,namely FaceQ and FaceA,which are collected from the Internet.Experiments show that our MHCNN achieves face detection performance comparable to the state of the art in face detection data set and benchmark(FDDB),and gets reasonable results on AFLW,FaceQ and FaceA.

Pedestrian Attributes Recognition in Surveillance Scenarios with Hierarchical Multi-Task CNN Models

Pedestrian attributes recognition is a very important problem in video surveillance and video forensics. Traditional methods assume the pedestrian attributes are independent and design handcraft features for each one. In this paper, we propose a joint hierarchical multi-task learning algorithm to learn the relationships among attributes for better recognizing the pedestrian attributes in still images using convolutional neural networks(CNN). We divide the attributes into local and global ones according to spatial and semantic relations, and then consider learning semantic attributes through a hierarchical multi-task CNN model where each CNN in the first layer will predict each group of such local attributes and CNN in the second layer will predict the global attributes. Our multi-task learning framework allows each CNN model to simultaneously share visual knowledge among different groups of attribute categories. Extensive experiments are conducted on two popular and challenging benchmarks in surveillance scenarios, namely, the PETA and RAP pedestrian attributes datasets. On both benchmarks, our framework achieves superior results over the state-of-theart methods by 88.2% on PETA and 83.25% on RAP, respectively.

Algorithm Design of CPCI Backboard's Interrupts Management Based on VxWorks'Multi-Tasks

This paper begins with a brief introduction of the embedded real-time operating system VxWorks and CompactPCI standard, then gives the programming interfaces of Peripheral Controller Interface （PCI） configuring, interrupts handling and multi-tasks programming interface under VxWorks, and then emphasis is placed on the software frameworks of CPCI interrupt management based on multi-tasks. This method is sound in design and easy to adapt, ensures that all possible interrupts are handled in time, which makes it suitable for data acquisition systems with multi-channels, a high data rate, and hard real-time high energy physics.

Gini Coefficient-based Task Allocation for Multi-robot Systems With Limited Energy Resources

Nowadays, robots generally have a variety of capabilities, which often form a coalition replacing human to work in dangerous environment, such as rescue, exploration, etc. In these operating conditions, the energy supply of robots usually cannot be guaranteed. If the energy resources of some robots are consumed too fast, the number of the future tasks of the coalition will be affected. This paper will develop a novel task allocation method based on Gini coefficient to make full use of limited energy resources of multi-robot system to maximize the number of tasks. At the same time, considering resources consumption,we incorporate the market-based allocation mechanism into our Gini coefficient-based method and propose a hybrid method,which can flexibly optimize the task completion number and the resource consumption according to the application contexts.Experiments show that the multi-robot system with limited energy resources can accomplish more tasks by the proposed Gini coefficient-based method, and the hybrid method can be dynamically adaptive to changes of the work environment and realize the dual optimization goals.

Genetic Algorithm Based Combinatorial Auction Method for Multi-Robot Task Allocation

An improved genetic algorithm is proposed to solve the problem of bad real-time performance or inability to get a global optimal/better solution when applying single-item auction （SIA） method or combinatorial auction method to multi-robot task allocation. The genetic algorithm based combinatorial auction （GACA） method which combines the basic-genetic algorithm with a new concept of ringed chromosome is used to solve the winner determination problem （WDP） of combinatorial auction. The simulation experiments are conducted in OpenSim, a multi-robot simulator. The results show that GACA can get a satisfying solution in a reasonable shot time, and compared with SIA or parthenogenesis algorithm combinatorial auction （PGACA） method, it is the simplest and has higher search efficiency, also, GACA can get a global better/optimal solution and satisfy the high real-time requirement of multi-robot task allocation.

Identification and Analysis of Multi-tasking Product Information Search Sessions with Query Logs

Purpose： This research aims to identify product search tasks in online shopplng ana analyze the characteristics of consumer multi-tasking search sessions. Design/methodology/approach： The experimental dataset contains 8,949 queries of 582 users from 3,483 search sessions. A sequential comparison of the Jaccard similarity coefficient between two adjacent search queries and hierarchical clustering of queries is used to identify search tasks. Findings： （1） Users issued a similar number of queries （1.43 to 1.47） with similar lengths （7.3-7.6 characters） per task in mono-tasking and multi-tasking sessions, and （2） Users spent more time on average in sessions with more tasks, but spent less time for each task when the number of tasks increased in a session. Research limitations： The task identification method that relies only on query terms does not completely reflect the complex nature of consumer shopping behavior.Practical implications： These results provide an exploratory understanding of the relationships among multiple shopping tasks, and can be useful for product recommendation and shopping task prediction. Originality/value： The originality of this research is its use of query clustering with online shopping task identification and analysis, and the analysis of product search session characteristics.

Multi-Task Learning for Semantic Relatedness and Textual Entailment

Recently, several deep learning models have been successfully proposed and have been applied to solve different Natural Language Processing (NLP) tasks. However, these models solve the problem based on single-task supervised learning and do not consider the correlation between the tasks. Based on this observation, in this paper, we implemented a multi-task learning model to joint learn two related NLP tasks simultaneously and conducted experiments to evaluate if learning these tasks jointly can improve the system performance compared with learning them individually. In addition, a comparison of our model with the state-of-the-art learning models, including multi-task learning, transfer learning, unsupervised learning and feature based traditional machine learning models is presented. This paper aims to 1) show the advantage of multi-task learning over single-task learning in training related NLP tasks, 2) illustrate the influence of various encoding structures to the proposed single- and multi-task learning models, and 3) compare the performance between multi-task learning and other learning models in literature on textual entailment task and semantic relatedness task.

AMTS:Adaptive Multi-Objective Task Scheduling Strategy in Cloud Computing

Task scheduling in cloud computing environments is a multi-objective optimization problem, which is NP hard. It is also a challenging problem to find an appropriate trade-off among resource utilization, energy consumption and Quality of Service(QoS) requirements under the changing environment and diverse tasks. Considering both processing time and transmission time, a PSO-based Adaptive Multi-objective Task Scheduling(AMTS) Strategy is proposed in this paper. First, the task scheduling problem is formulated. Then, a task scheduling policy is advanced to get the optimal resource utilization, task completion time, average cost and average energy consumption. In order to maintain the particle diversity, the adaptive acceleration coefficient is adopted. Experimental results show that the improved PSO algorithm can obtain quasi-optimal solutions for the cloud task scheduling problem.

基于邻域采样的多任务图推荐算法

近年来,图神经网络(GNN)成为解决协同过滤的主流方法之一。它通过构建用户-物品图,模拟用户与物品的交互关系,并用GNN学习它们的特征表示。尽管现有在模型结构上的研究已取得了较大进展,但如何在图结构上更有效地进行负采样仍未有效解决。为此,提出一种基于邻域采样的多任务图推荐算法。该算法提出了一种基于GNN的邻域采样策略,该策略以每个用户为中心构建子图,将次高阶物品作为用户邻域采样的负样本,可以更有效地挖掘强负样本并提高采样质量。通过GNN对图结点进行信息聚合与特征提取,得到结点的最终嵌入表示。设计一种余弦边际损失来过滤部分冗余负样本,以有效减少采样过程中的噪声数据。同时,该算法引入了多任务策略对模型进行联合优化,以增强模型的泛化能力。在3个公开数据集上进行的大量实验表明,该算法在大多数情况下明显优于其他主流算法。

旅游自动问答系统中多任务问句分类研究

目前旅游产业信息化建设需要构建旅游自动问答系统,其中问句分类是问答系统的重要组成部分,传统问句类别体系角度单一,且传统分类模型对不平衡的问句数据集表现欠佳。针对这一问题,该文从问题主题和问句答案类型两个角度构建了旅游领域的问句类别体系架构,并提出多任务问句分类模型MT-Bert,在BERT上进行多任务训练,并加入自注意力机制,使用Softmax分类器,并设计了多任务融合损失函数。在山西旅游数据集的结果表明,MT-Bert在两种类别体系的微平均F1值分别为97.6%、91.7%,且避免了非平衡数据的预测失败问题,可以有效处理非平衡数据。

分布式3D打印服务的实时多任务调度研究

针对分布式3D打印机(3DPs)在工业物联网(IIoT)中共享、协作、生产全球化的定制产品过程中,3D打印任务(3DPTs)在分布式3D打印机上分配工作量不平衡,以及提交的每个模型的定制属性和实时性等问题,文章提出了用于IIoT中个性化3D打印的实时绿色感知多任务调度架构,给出了一种稳健的在线分配算法,使得每个3D打印任务能够精确地满足用户定义属性,并且平衡了分布式3D打印机之间工作负荷,同时开发了一种基于优先级的自适应实时多任务调度(ARMPS)算法,实时调度每一个3D打印任务,满足3D打印任务的实时性以及动态性要求。在高负载下进行仿真实验,经性能评估测试,表明所提出的算法具有稳健性,调度架构具有鲁棒性和可扩展性。

基于交叉注意力的多任务交通场景检测模型

感知是自动驾驶的基础和关键,但大多数单个模型无法同时完成交通目标、可行驶区域和车道线等多项检测任务。提出一种基于交叉注意力的多任务交通场景检测模型,可以同时检测交通目标、可行驶区域和车道线。使用编解码网络提取初始特征,利用混合空洞卷积对初始特征进行强化,并通过交叉注意力模块得到分割和检测特征图。在分割特征图上进行语义分割,在检测特征图上进行目标检测。实验结果表明:在具有挑战性的BDD100K数据集中,所提模型在任务精度和总体计算效率方面优于其他多任务模型。

基于激光雷达点云的动态驾驶场景多任务分割网络

在自动驾驶场景理解任务中进行准确的可行驶区域以及动静态物体分割对于后续的局部运动规划和运动控制至关重要。然而当前基于激光雷达点云的通用语义分割方法并不能在车端边缘计算设备上实现实时且鲁棒的预测,且不能预测当前时刻的物体运动状态。为解决该问题本文提出一种可行驶区域及动静态物体多任务分割网络MultiSegNet。该网络利用激光雷达输出的深度图及处理后得到的残差图像作为编码空间特征和运动特征的表征输入到网络用于特征学习,从而避免直接处理无序高密度点云。针对深度图在不同方向视角内目标分布数量差异较大的特点,本文提出了变分辨率分组输入策略。该方法能在降低网络计算量的同时提高网络的分割精度。为适配不同尺度目标所需要的卷积感受野尺寸本文提出了深度值引导的分层空洞卷积模块。同时本文为有效关联并融合不同时域下物体的空间位置和姿态信息提出了时空运动特征增强网络。为验证所提出MultiSegNet的有效性,本文在大规模点云驾驶场景数据集SemanticKITTI及nuScenes上进行验证。结果表明:可行驶区域、静态物体和动态物体的分割IoU分别达到98%、97%和70%,性能优于主流网络,且在边缘计算设备上实现实时推理。

基于1DCNN融合多源表型数据的杨树干旱胁迫评估方法

目前关于不同杨树品种抗旱性的研究主要集中在利用传统测量方法获取形态结构和生理生化表型参数进而分析杨树的抗旱性,依据多源成像传感器提取的表型参数指标确定杨树干旱胁迫等级的方法较为少见。为了阐明杨树耐旱的表型机制、筛选抗旱性树种和明确杨树抗旱等级,本文以杨树不同性别的喜水和耐旱品种为研究对象,在杨树苗期进行梯度干旱胁迫处理,通过热红外以及RGB多源成像传感器获取杨树冠层温度参数与颜色植被指数表型数据,并建立基于1DCNN的多任务分类模型划分杨树苗期品种抗旱等级与干旱胁迫等级等2个分类任务,探究杨树性别与生长时间对杨树干旱胁迫响应机制的影响。结果表明,以27组数据变量降维后的4个特征作为模型变量,与传统机器学习算法SVM、RF、XGBoost相比,本文提出的1DCNN多任务分类模型在杨树品种抗旱等级分类与单株干旱胁迫等级分类2个任务中的模型分类精度皆达到最优,分类准确率分别为81.8%和62.3%;引入杨树的性别和生长时间后共6个特征作为模型的输入变量后,杨树苗期品种抗旱等级与干旱胁迫等级的分类精度显著提高,1DCNN多任务分类模型在2个分类任务中的准确率分别达到93.5%与76.6%,模型分类准确率分别提高11.7个百分点与14.3个百分点。研究结果表明,通过热红外与RGB成像传感器获取多源表型数据,并建立1DCNN多任务分类模型对实现杨树干旱胁迫等级评估的可行性,同时表明杨树的性别和生长时间作为模型输入变量能够有效提升模型的分类精度,可为筛选杨树抗旱性品种提供新的思路与方法。

预算约束下多任务联邦学习激励机制

联邦学习是一种实现数据隐私保护的分布式机器学习范式,性能取决于数据源的质量和数据规模。客户端是理性个体,参与联邦学习将耗费计算、通信和隐私等成本,需要通过激励提高客户端的参与意愿。因此联邦学习能成功应用的关键之一是尽可能多地激励高质量数据客户端参与训练。多任务联邦学习环境下客户端拥有面向不同任务且质量不同的数据,并具有执行能力的约束。为提高多个学习任务的整体性能,在预算受限的条件下设计一种面向任务的客户选择和报酬机制。通过分析影响模型精度的重要因素,提出一种基于客户端数据样本分布特征的质量评估标准,并结合客户端成本信息,设计一种逆向拍卖的激励机制(EMD-MQMFL),实现客户端的任务指派和支付策略。从理论上分析和证明了该机制具有诚实性、个人理性以及预算可行性,并通过大量实验验证了该方法在联邦学习性能上的有效性。在MNIST、Fashion-MNIST、Cifar-10数据集上的实验结果表明,EMD-MQMFL在数据不平衡的情况下,平均模型精度比已有的机制至少提高5.6个百分点。