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.

Improved Scatter Search Algorithm for Multi-skilled Personnel Scheduling of Ship Block Painting

This paper focuses on the optimization method for multi-skilled painting personnel scheduling.The budget working time analysis is carried out considering the influence of operating area,difficulty of spraying area,multi-skilled workers,and worker’s efficiency,then a mathematical model is established to minimize the completion time. The constraints of task priority,paint preparation,pump management,and neighbor avoidance in the ship block painting production are considered. Based on this model,an improved scatter search(ISS)algorithm is designed,and the hybrid approximate dynamic programming(ADP)algorithm is used to improve search efficiency. In addition,the two solution combination methods of path-relinking and task sequence combination are used to enhance the search breadth and depth. The numerical experimental results show that ISS has a significant advantage in solving efficiency compared with the solver in small scale instances;Compared with the scatter search algorithm and genetic algorithm,ISS can stably improve the solution quality. Verified by the production example,ISS effectively shortens the total completion time of the production,which is suitable for scheduling problems in the actual painting production of the shipyard.

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.

基于改进NSGA-Ⅲ的D2D协同MEC多目标优化研究

在当前的移动边缘计算(Mobile Edge Computing,MEC)模型中,由于任务是直接上传到MEC服务器执行,存在边缘服务器的计算压力大、空闲移动设备上的资源未得到充分利用等问题。使用边缘网络中的空闲设备进行协同计算,能够实现用户闲置资源的合理利用,增强MEC的计算能力。因此,提出了一种利用终端直通(Device-to-Device,D2D)进行协同计算的部分卸载MEC模型(D2D Collaborative MEC for Partial Offloading,DCM-PO)。在该模型中,除本地计算和MEC服务器计算外,还能将部分任务上传到空闲D2D设备进行辅助计算。首先,以最小化边缘网络的时延、能耗和费用为目标建立多目标优化问题。然后,在多染色体混合编码、自适应交叉率和变异率等方面对基于参考点的非支配排序遗传算法(Non-dominated Sorting Genetic AlgorithmⅢ,NSGA-Ⅲ)进行改进,使之适合DCM-PO模型中的多目标优化问题求解。最后,仿真结果表明,相比基准MEC模型,DCM-PO模型在多项性能指标上有明显优势。

自动驾驶环境感知多任务去耦-融合算法

自动驾驶车辆在行驶过程中,需要对行人和车辆同时完成目标检测、实例分割和目标跟踪三个任务。提出一种基于深度学习的环境感知模型同时对三个任务进行多任务学习。首先,通过卷积神经网络对连续帧图像提取时空特征;然后,通过注意力机制对时空特征进行去耦再融合,充分利用任务间的相关性,实现不同任务对时空特征的差异化选择;最后,为平衡不同任务间的学习速率,使用动态加权平均的方式对模型进行训练。在KITTI数据集上的实验结果表明,所提模型在目标检测方面,比CenterTrack模型F1得分提高了0.6个百分点;在目标跟踪方面,比TraDeS(Track to Detect and Segment)模型多目标跟踪精度(MOTA)提高了0.7个百分点;在实例分割方面,比SOLOv2(Segmenting Objects by LOcations version 2)模型AP_(50)和AP_(75)分别提高了7.4和3.9个百分点。

基于对比性视觉-文本模型的光场图像质量评估

光场图像作为一种能够捕获场景每个位置光线信息的图像类型,在电子成像、医学影像和虚拟现实等领域具有广泛的应用前景.光场图像质量评估(Light Field Image Quality Assessment,LFIQA)旨在衡量此类图像的质量,但当前方法面临视觉效果与文本模态间异构性的重要挑战.为解决上述问题,本文提出了一种基于文本-视觉的多模态光场图像质量评估模型.具体来说,在视觉模态方面,我们设计了多任务模型,结合边缘自动阈值算法有效丰富了光场图像的关键表示特征.在文本模态方面,基于输入噪声特征与预测噪声特征的对比,准确识别光场图像的噪声类别,并验证了噪声预测对优化视觉表示的重要性.基于上述研究,进一步提出了一种优化的通用噪声文本配置方法,并结合边缘增强策略,显著提升了基线模型在光场图像质量评估中的准确性和泛化能力.此外,通过消融实验,评估了各组件对整体模型性能的贡献,验证了本文方法的有效性和稳健性.实验结果表明,该方法不仅在公开数据集Win5-LID和NBU-LF1.0的实验中表现出色,还在融合数据集中展示出优秀的实验结果,与现有最优算法相比,本文所提方法在两个数据库中的性能分别提升了2%和6%.本文提出的噪声验证策略和配置方法不仅为图像质量评估中的噪声预测任务提供了有价值的参考,也可用于其它噪声预测类型的辅助任务.

DRE-3DC:基于三维表征建模的篇章级关系抽取模型

篇章级关系抽取任务旨在从非结构化文档的多个句子中提取事实,是构建领域知识库和知识问答应用的关键环节,相较于句子级关系抽取,该任务既要求模型能够基于文档结构特征捕获实体间的复杂交互,还要应对严重的关系类别长尾分布问题.现有基于表格的关系抽取模型主要对文档进行“实体/实体”二维建模,采用多层卷积网络或局部注意力机制提取实体间的交互特征,由于未显式对关系语义进行解耦建模,使得模型无法避免类别重叠影响和捕获关系的方向性特征,导致缺乏实体交互的充分语义信息.针对上述挑战,本文提出了一种基于三维表征建模的篇章级关系抽取模型DRE-3DC(Document-Level Relation Extraction with Three-Dimensional Representation Combination Modeling),对二维表格建模方式进行扩展,形成“实体/实体/关系”三维表征建模,采用基于形变卷积的三重注意力机制有效区分和聚合不同语义空间下的实体间及实体与关系的交互表征,自适应地增强模型对文档结构特征的聚合.同时,采用多任务学习方法增强模型对文档整体关系类别组合的感知来缓解篇章级关系抽取任务中的关系类别长尾分布问题.在DocRED和Revisit-DocRED两个篇章级关系抽取数据集上进行的实验结果表明,DRE-3DC模型性能良好,并通过消融实验、对比分析和实例分析,验证了本文所提方法的有效性.

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。

基于带阈值的BPE-dropout多任务学习的端到端语音识别

针对语音识别任务中出现的未登录词问题,提出一种带阈值的BPE-dropout多任务学习语音识别方法.该方法采用带随机性的字节对编码算法,在形成子词时引入带字数阈值的策略,将子词作为建模单元,编码器部分采用Conformer结构,与链接时序分类和注意力机制相结合.为进一步提升模型性能,引入动态参数对损失函数进行动态调节,并同时进行多任务训练和解码.实验结果表明,该方法采用子词作为建模单元可有效解决未登录词问题,在多任务学习框架下进一步提升了模型的识别性能.在公开数据集THCHS30和ST-CMDS上,该模型实现了超过95%的识别准确率.

基于障碍物和车位检测的单阶段多任务YOLO-Parking算法研究

文章提出一种基于YOLOv4的端到端多任务网络模型用于自动泊车系统中的感知任务,以环视图像(around view monitor, AVM)作为网络输入,基于卷积网络提取图像特征信息,通过YOLO和DMPR-PS(directional marking-point regression-parking slot)检测头实现停车位与障碍物并行检测。在PS 2.0公开数据集上进行验证的结果表明,所提出的多任务检测方法能够同时检测停车位和障碍物,障碍物识别平均精度均值达到89.72%,车位识别查准率达到93.53%,网络检测速率为34.0帧/s,在满足自动泊车感知任务需求的同时提升了系统的检测效率。该文研究成果对自动泊车感知技术的发展具有一定的意义。

基于改进U-Net模型的农业大棚遥感提取方法

农业大棚是一种农业设施,依据表面透光度分为阳棚和阴棚。大范围统计农业大棚对农业设施普查、农业政策制定、县域经济发展规划具有重要意义。针对人工统计费时费力问题,基于卷积神经网络和高分辨率遥感影像实现农业大棚遥感信息提取。针对U-Net模型对遥感影像中语义信息提取不足和边缘信息利用不充分问题,提出以下改进方案:1)优化语义分割任务,使用ConvNeXt和注意力机制提取遥感影像中农业大棚的深层语义信息;2)引入边缘检测任务,采用门控卷积层和拼接操作融合编码器的语义特征和解码器输出的图像梯度,进而结合边缘信息优化分割结果。经测试,改进后的模型能同时提取阴阳2种大棚信息且识别效果良好,相对传统方法有较大提高。

基于编-解码器结构的无人机群多任务联邦学习

针对传统联邦学习在无人机群应用中的局限性——要求所有参与者执行相同任务并拥有相同的模型结构,本文探索一种适用于无人机群的多任务联邦学习方法,设计一种新的编-解码器架构,以加强执行不同任务的无人机之间的知识共享.首先,为执行相同任务的无人机建立直接的知识分享机制,通过直接聚合方式实现同任务知识的有效融合;其次,对于执行不同任务的无人机,从所有无人机的编-解码器架构中提取编码器部分,构建一个全局编码器;最后,在训练环节,将本地编码器和全局编码器的信息整合到损失函数中,并通过迭代更新使本地解码器逐步逼近全局解码器,从而实现跨任务间的知识高效共享.实验结果表明:相较于传统方法,所提出的方法使无人机群在3个单任务上的性能分别提升1.79%、0.37%和2.78%,仅在1个任务上性能略微下降0.38%,但整体性能仍提升2.38%.

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.

GEA-NMT:图卷积增强的多任务低资源机器翻译模型

在低资源语种上训练高质量机器翻译系统的主要障碍是平行语料的稀缺,一些低资源语言在语言上与高资源语言相关或相似,相似的语言可能使用相同的字符集或类似的句法结构.本文利用低资源语种上的单语数据及与之相关联的高资源语种和目标语言的平行语料,尝试将翻译知识进行迁移,从而完成低资源语种和目标语言间的翻译模型训练.本文提出一种图卷积增强的多任务训练低资源神经机器翻译模型(GCN Enhanced multi-task Adapting Neural Machine Translation,GEA-NMT),结合降噪自编码器、生成对抗训练、回译和桥接方法,并使用图神经网络学习句法依赖关系以进一步提升低资源语种上的神经机器翻译模型效果.

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.

一种多任务学习结合U-Net的微动脉瘤图像分割方法

微动脉瘤是检测糖尿病初期视网膜病变的关键病灶,针对微动脉瘤图像分割问题,提出了多种图像预处理技术与多任务学习网络相结合的方法。该方法使用了多种图像预处理技术,在UNet中引入了注意力机制,并将微动脉瘤图像分割作为主任务,微动脉瘤存在性检测作为副任务,利用多任务学习结合U-Net来提升主任务分割效果。在国际公开数据集上进行实验,获得了AUC为9.48%以及AP为51.40%的结果,与单任务图像分割相比,AP值提升了3.82%,由实验结果可知该方法能够提升微动脉瘤的分割效果。

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.

基于多任务双层注意力优化的TCN-BiGRU综合能源负荷短期预测

基于多元负荷预测是综合能源系统(IES)生产计划和能源调度的前提,提出一种基于多任务双层注意力优化的时序卷积网络与双向门控循环单元相结合(TCN-BiGRU)的综合能源负荷短期预测方法。首先,将特征集通过最大互信息系数法进行相关性分析,构建不同负荷的输入特征集;然后,输入多任务学习平台进行离线训练,其中的共享层采用高效通道注意力网络(ECANet)优化的TCN,特定任务层则采用自注意力机制优化的BiGRU;最后,选取亚利桑那州立大学坦佩校区冬季和夏季典型日的实际数据进行在线测试。测试结果表明,对比多种深度神经网络模型,所提方法在冬季和夏季的多元负荷加权平均绝对百分比误差分别最大降低了69.35%和73.26%,加权均方根误差分别最大降低70.11%和79.46%。