|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Hybrid-augmented intelligence: collaboration and cognition显示文摘人工智能追求的长期目标是使机器能像人一样学习和思考。由于人类面临的许多问题具有不确定性、脆弱性和开放性,任何智能程度的机器都无法完全取代人类,这就需要将人的作用或人的认知模型引入到人工智能系统中,形成混合-增强智能的形态,这种形态是人工智能或机器智能的可行的、重要的成长模式。混合-增强智能可以分为两类基本形式:一类是人在回路的人机协同混合增强智能,另一类是将认知模型嵌入机器学习系统中,形成基于认知计算的混合智能。本文讨论人机协同的混合-增强智能的基本框架,以及基于认知计算的混合-增强智能的基本要素:直觉推理与因果模型、记忆和知识演化;特别论述了直觉推理在复杂问题求解中的作用和基本原理,以及基于记忆与推理的视觉场景理解的认知学习网络;阐述了竞争-对抗式认知学习方法,并讨论了其在自动驾驶方面的应用;最后给出混合-增强智能在相关领域的典型应用。 | Nan-ning ZHENG Zi-yi LIU Peng-ju REN Yong-qiang MA Shi-tao CHEN Si-yu YU Jian-ru XUE Ba-dong CHEN Fei-yue WANG | 2017 | Frontiers of Information Technology & Electronic Engineering2017，18，2： | 51 |
| 2 | 人工智能在智能制造领域的应用研究(英文)显示文摘本文基于作者团队近年来在人工智能技术应用于制造领域的研究与实践,首先,简析了'互联网+人工智能'时代核心技术飞速发展正引发制造领域的模式、手段和生态系统的重大变革以及人工智能的新发展。接着基于人工智能技术与信息通信技术、制造技术及产品有关专业技术等融合,研究提出了智能制造新模式、新手段、新业态,智能制造系统体系架构和智能制造系统技术体系。进而,从智能制造的应用技术、产业和应用示范等角度,简述智能制造领域的国内外发展现状。最后,针对我国人工智能2.0在智能制造领域应用研究内容提出了建议。 | Bo-hu LI Bao-cun HOU Wen-tao YU Xiao-bing LU Chun-wei YANG | 2017 | Frontiers of Information Technology & Electronic Engineering2017，18，1： | 38 |
| 3 | Visual interpretability for deep learning:a survey显示文摘This paper reviews recent studies in understanding neural-network representations and learning neural networks with interpretable/disentangled middle-layer representations.Although deep neural networks have exhibited superior performance in various tasks,interpretability is always Achilles' heel of deep neural networks.At present,deep neural networks obtain high discrimination power at the cost of a low interpretability of their black-box representations.We believe that high model interpretability may help people break several bottlenecks of deep learning,e.g.,learning from a few annotations,learning via human–computer communications at the semantic level,and semantically debugging network representations.We focus on convolutional neural networks(CNNs),and revisit the visualization of CNN representations,methods of diagnosing representations of pre-trained CNNs,approaches for disentangling pre-trained CNN representations,learning of CNNs with disentangled representations,and middle-to-end learning based on model interpretability.Finally,we discuss prospective trends in explainable artificial intelligence. | Quan-shi ZHANG Song-chun ZHU | 2018 | Frontiers of Information Technology & Electronic Engineering2018，19，1： | 32 |
| 4 | Recent advances in efficient computation of deep convolutional neural networks显示文摘Deep neural networks have evolved remarkably over the past few years and they are currently the fundamental tools of many intelligent systems.At the same time,the computational complexity and resource consumption of these networks continue to increase.This poses a significant challenge to the deployment of such networks,especially in real-time applications or on resource-limited devices.Thus,network acceleration has become a hot topic within the deep learning community.As for hardware implementation of deep neural networks,a batch of accelerators based on a field-programmable gate array(FPGA) or an application-specific integrated circuit(ASIC)have been proposed in recent years.In this paper,we provide a comprehensive survey of recent advances in network acceleration,compression,and accelerator design from both algorithm and hardware points of view.Specifically,we provide a thorough analysis of each of the following topics:network pruning,low-rank approximation,network quantization,teacher–student networks,compact network design,and hardware accelerators.Finally,we introduce and discuss a few possible future directions. | Jian CHENG Pei-song WANG Gang LI Qing-hao HU Han-qing LU | 2018 | Frontiers of Information Technology & Electronic Engineering2018，19，1： | 29 |
| 5 | Crowd intelligence in AI 2.0 era显示文摘The Internet based cyber-physical world has profoundly changed the information environment for the development of artificial intelligence(AI), bringing a new wave of AI research and promoting it into the new era of AI 2.0. As one of the most prominent characteristics of research in AI 2.0 era, crowd intelligence has attracted much attention from both industry and research communities. Specifically, crowd intelligence provides a novel problem-solving paradigm through gathering the intelligence of crowds to address challenges. In particular, due to the rapid development of the sharing economy, crowd intelligence not only becomes a new approach to solving scientific challenges, but has also been integrated into all kinds of application scenarios in daily life, e.g., online-tooffline(O2O) application, real-time traffic monitoring, and logistics management. In this paper, we survey existing studies of crowd intelligence. First, we describe the concept of crowd intelligence, and explain its relationship to the existing related concepts, e.g., crowdsourcing and human computation. Then, we introduce four categories of representative crowd intelligence platforms. We summarize three core research problems and the state-of-the-art techniques of crowd intelligence. Finally, we discuss promising future research directions of crowd intelligence. | Wei LI Wen-jun WU Huai-min WANG Xue-qi CHENG Hua-jun CHEN Zhi-hua ZHOU Rong DING | 2017 | Frontiers of Information Technology & Electronic Engineering2017，18，1： | 27 |
| 6 | 跨媒体分析与推理:研究进展与发展方向(英文)显示文摘跨媒体分析与推理是计算机科学的热点问题,也是人工智能中一个具有广阔前景的研究方向。目前,尚未有文献对跨媒体分析与推理的现有方法进行归纳总结并给出它的研究进展、挑战及发展方向。为解决这些问题,本文从七个方面进行综述:(1)跨媒体统一表征理论与模型;(2)跨媒体关联理解与深度挖掘;(3)跨媒体知识图谱构建与学习方法;(4)跨媒体知识演化与推理;(5)跨媒体描述与生成;(6)跨媒体智能引擎;(7)跨媒体智能应用。本文的目标是给出跨媒体分析与推理的方法、进展以及发展方向,吸引更多人关注该领域的最新进展,通过探讨面临的挑战和研究方向,为研究者提供重要参考。 | Yu-xin PENG Wen-wu ZHU Yao ZHAO Chang-sheng XU Qing-ming HUANG Han-qing LU Qing-hua ZHENG Tie-jun HUANG Wen GAO | 2017 | Frontiers of Information Technology & Electronic Engineering2017，18，1： | 23 |
| 7 | Real-time road traffic state prediction based on ARIMA and Kalman filter显示文摘道路交通流预测不仅可以为出行者提供实时有效的信息,而且可以帮助他们选择最佳路径,减少出行时间,实现道路交通路径诱导,缓解交通拥堵。本文提出了一种基于ARIMA模型和Kalman滤波算法的道路交通流预测方法。首先,基于道路交通历史数据建立时间序列的ARIMA模型。其次,结合ARIMA模型和Kalman滤波法构建道路交通预测算法,获取Kalman滤波的测量方程和更新方程。然后,基于历史道路交通数据进行算法的参数设定。最后,以北京的四条路段作为案例,对所提出的方法进行了分析。实验结果表明,基于ARIMA模型和Kalman滤波的实时道路交通状态预测方法是可行的,并且可以获得很高的精度。 | Dong-wei XU Yong-dong WANG Li-min JIA Yong QIN Hong-hui DONG | 2017 | Frontiers of Information Technology & Electronic Engineering2017，18，2： | 22 |
| 8 | Consensus-based three-dimensional multi-UAV formation control strategy with high precision显示文摘本文提出了一种基于二阶一致性的多无人机编队控制策略,通过邻接通信,引入位置和速度协同变量来产生控制命令。提出了协同导航算法和协同控制算法,它们分别控制位置和姿态,联合二者可保持特定几何队形。整个编队系统包含三部分:六自由度无人机模型、协同导航算法、协同控制算法,编队控制策略是闭环和全状态的。协同导航算法是二阶一致性算法,给出期望的加速度、俯仰角速率和偏航角速率。协同控制算法综合考虑纵向和横侧向机动,通过推导状态方程来设计协同控制律。分析了编队的闭环稳定性,给出了稳定的充分必要条件。利用同步技术,抑制了位置数据中的测量误差,提高了控制精度。仿真中,三维编队飞行验证了所提编队控制策略的可行性和有效性。 | Mao-de YAN Xu ZHU Xun-xun ZHANG Yao-hong QU | 2017 | Frontiers of Information Technology & Electronic Engineering2017，18，7： | 18 |
| 9 | Big data storage technologies: a survey显示文摘对于容量快速增长、日趋多元化的大数据,业界亟需开发可行性更好的存储工具。为满足大数据存储需求,存储机制已经形成从传统数据管理系统到No SQL技术的结构化转移。然而,目前可用的大数据存储技术无法为持续增长的异构数据提供一致、可扩展和可用的解决方案。在科学实验、医疗保健、社交网络和电子商务等实际应用中,存储是大数据分析的第一步。截至目前,亚马逊、谷歌和阿帕奇等公司形成了大数据存储方案的行业标准,但尚未有关于大数据存储技术性能和容量提升的深入调查和文献报告。本文旨在对目前可用于大数据的最先进的存储技术进行全面调查,提供了一个明确的大数据存储技术分类方法,以帮助数据分析师和研究人员了解和选择更适合其需求的存储机制。我们使用布鲁尔的CAP定理比较和分析了现有存储方法,评估了不同存储架构的性能,讨论了存储技术的意义、应用及其对其他类别数据的支持。为了加快部署可靠和可扩展的存储系统,文中还突出了未来研究面临的几个挑战。 | Aisha SIDDIQA Ahmad KARIM Abdullah GANI | 2017 | Frontiers of Information Technology & Electronic Engineering2017，18，8： | 15 |
| 10 | A scheduling method based on a hybrid genetic particle swarm algorithm for multifunction phased array radar显示文摘为解决多功能相控阵雷达的任务调度难题,本文提出了一种融合粒子群算法、遗传算法和启发式交错算法的优化算法。通过混沌理论优化粒子群算法的飞行参数,设计动态惯性权重,并引入遗传算法中的交叉、变异操作,使该算法的计算效率和寻优能力均得到大幅度提高。在智能算法的框架下,提出启发式的交错调度算法可进一步利用任务等待期的时间资源。仿真结果表明,与现有方法相比,本文算法效率更高,鲁棒性更强。 | Hao-wei ZHANG Jun-wei XIE Wen-long LU Chuan SHENG Bin-feng ZONG | 2017 | Frontiers of Information Technology & Electronic Engineering2017，18，11： | 13 |
| 11 | From Eliza to XiaoIce:challenges and opportunities with social chatbots显示文摘Conversational systems have come a long way since their inception in the 1960 s.After decades of research and development,we have seen progress from Eliza and Parry in the 1960 s and 1970 s,to task-completion systems as in the Defense Advanced Research Projects Agency(DARPA) communicator program in the 2000 s,to intelligent personal assistants such as Siri,in the 2010 s,to today's social chatbots like Xiao Ice.Social chatbots' appeal lies not only in their ability to respond to users' diverse requests,but also in being able to establish an emotional connection with users.The latter is done by satisfying users' need for communication,affection,as well as social belonging.To further the advancement and adoption of social chatbots,their design must focus on user engagement and take both intellectual quotient(IQ) and emotional quotient(EQ) into account.Users should want to engage with a social chatbot;as such,we define the success metric for social chatbots as conversation-turns per session(CPS).Using Xiao Ice as an illustrative example,we discuss key technologies in building social chatbots from core chat to visual awareness to skills.We also show how Xiao Ice can dynamically recognize emotion and engage the user throughout long conversations with appropriate interpersonal responses.As we become the first generation of humans ever living with artificial intelligenc(AI),we have a responsibility to design social chatbots to be both useful and empathetic,so they will become ubiquitous and help society as a whole. | Heung-yeung SHUM Xiao-dong HE Di LI | 2018 | Frontiers of Information Technology & Electronic Engineering2018，19，1： | 11 |
| 12 | Underwater acoustic communication and the general performance evaluation criteria显示文摘Driven by the huge demand to explore oceans, underwater wireless communications have been rapidly developed in the past few decades. Due to the complex physical characteristics of water, acoustic wave is the only media available for underwater wireless communication at any distance. As a result, underwater acoustic communication(UAC) is the major research field in underwater wireless communication. In this paper, characteristics of underwater acoustic channels are first introduced and compared with terrestrial communication to demonstrate the difficulties in UAC research. To give a general impression of the UAC, current important research areas are mentioned. Furthermore, different principal modulation-based schemes for short-and medium-range communications with high data rates are investigated and summarized. To evaluate the performance of UAC systems in general,three criteria are presented based on the research publications and our years of experience in high-rate short-to medium-range communications. These three criteria provide useful tools to generally guide the design and evaluate the performance of underwater acoustic communication systems. | Jian-guo HUANG Han WANG Cheng-bing HE Qun-fei ZHANG Lian-you JING | 2018 | Frontiers of Information Technology & Electronic Engineering2018，19，8： | 11 |
| 13 | Attention-based encoder-decoder model for answer selection in question answering显示文摘问答技术的重要挑战之一就是解决问题与答案之间的语义空白。机器翻译模型已经被证明能有效的提升解决问题与答案之间的语义空白。本文提出了一种基于注意机制的深度神经网络模型来解决问答系统中的答案选择任务。该模型采用了基于双向长短时记忆(Long short-term memory,LSTM)的编码解码模型,编码解码模型是一个被证明再机器翻译领域取得了突出的成绩。我们还在模型中应用了注意力机制来提升模型的效果。本文在一个公开数据集上验证了实验的有效性,同时通过结合该模型显著提高了问答系统的性能在TREC 2015 liveQA的任务中。 | Yuan-ping NIE Yi HAN Jiu-ming HUANG Bo JIAO Ai-ping LI | 2017 | Frontiers of Information Technology & Electronic Engineering2017，18，4： | 11 |
| 14 | Dolphin swarm algorithm显示文摘群体智能算法采取分布式解决问题的策略,已成功应用于很多传统算法难以解决的优化问题。目前已有粒子群算法、遗传算法、蜂群算法、蚁群算法等已经成功实现且效果良好的算法,但在优化对象日益复杂的今天,这些算法越来越难以满足人们对精度和时间的要求,而改进这些算法所带来的收益也越来越低。在这种情况下,设计一种新的算法来更好地解决优化问题变得越来越有意义。海豚有很多值得关注的生物特性和生活习性,如回声定位、信息交流、合作分工等。通过将这些生物特性和生活习性与群体智能的思想结合起来,引入优化问题中,我们提出了一种新的算法——海豚群算法,并给出了算法的相关定义,详细阐述了算法中搜寻、呼叫、接受、捕猎四个关键阶段。为了验证海豚群算法的效果,使用了10个性质各异的基准函数对海豚群算法以及粒子群算法、遗传算法、蜂群算法进行实验,并将4个函数的收敛速度和基准函数结果进行比较。实验结果表明,海豚群算法在大多数情况下,特别是在低维单峰函数、高维多峰函数、步长函数、带随机变量的函数中表现良好,具有收敛速度先慢后快、阶段性收敛、不易陷入局部最优、对基准函数具体性质没有要求等特点,尤其适用于适应度函数调用次数较多、使用个体较少的优化问题。 | Tian-qi WU Min YAO Jian-hua YANG | 2016 | Frontiers of Information Technology & Electronic Engineering2016，17，8： | 10 |
| 15 | Battle damage assessment based on an improved Kullback-Leibler divergence sparse autoencoder显示文摘为解决深度学习网络中隐藏层节点数难以确定的问题,文中提出一种改进的KL(Kullback-Leibler)散度稀疏自动编码机,并将该方法应用到战斗损伤评估中。该方法能够自动筛选出对数据重建贡献大的隐层特征,舍弃贡献小的隐层特征,从而优化网络结构。在网络预测精度不受影响的前提下,该方法自动筛选隐层特征,提升了计算速度。基于UCI(University of California,Irvine)数据集和BDA(battle damage assessment)战争破坏数据的实验表明,该方法优于其他数据驱动的方法。改进的KL稀疏自动编码机回归网络在保证预测精度的前提下,能提升网络的训练和预测速度,并自动筛选隐层有效特征,优化隐层节点数,优化网络结构。 | Zong-feng QI Qiao-qiao LIU Jun WANG Jian-xun LI | 2017 | Frontiers of Information Technology & Electronic Engineering2017，18，12： | 9 |
| 16 | Development of a novel autonomous lower extremity exoskeleton robot for walking assistance显示文摘Today, exoskeletons are widely applied to provide walking assistance for patients with lower limb motor incapacity. Most existing exoskeletons are under-actuated, resulting in a series of problems, e.g., interference and unnatural gait during walking. In this study, we propose a novel intelligent autonomous lower extremity exoskeleton(Auto-LEE), aiming at improving the user experience of wearable walking aids and extending their application range.Unlike traditional exoskeletons, Auto-LEE has 10 degrees of freedom, and all the joints are actuated independently by direct current motors, which allows the robot to maintain balance in aiding walking without extra support.The new exoskeleton is designed and developed with a modular structure concept and multi-modal human-robot interfaces are considered in the control system. To validate the ability of self-balancing bipedal walking, three general algorithms for generating walking patterns are researched, and a preliminary experiment is implemented. | Yong HE Nan LI Chao WANG Lin-qing XIA Xu YONG Xin-yu WU | 2019 | Frontiers of Information Technology & Electronic Engineering2019，20，3： | 9 |
| 17 | Using heterogeneous patent network features to rank and discover influential inventors显示文摘目的:专利是发现新技术信息独特的信息源,也是竞争情报重要的信息源之一。目前,如何评估科学研究人员的贡献及其研究价值逐渐成为一个新兴的研究热点。本文提出一种利用专利数据异构网络对专利发明人员进行影响力排序的算法。创新点:传统对发明人员进行分析的方法是对发明人的专利数量进行统计分析,但这种方法不够全面。本文提出的基于规则的方法,设计结合网络拓扑结构和专利数据特点,排序过程不断迭代直至符合收敛条件。与传统方法相比,该方法充分利用异构网络中的信息。实验结果表明本算法不仅能有效挖掘具有高影响力的发明人员,而且收敛速度更快、效率更高。方法:不同于传统的排序方法,本文提出的Inventor-Ranking排序算法是一种基于规则的实体排序方法。该方法通过迭代使用这些规则得到排序结果。排序模型建立在发明人员和专利的相互影响进行排序的基础上(图3)。使用本算法和Page Rank算法排序Top 10的发明人员(表2)。实验结果表明,Inventor-Ranking算法比Page Rank算法收敛更快(图10)。结论:本文针对专利数据组成的异构网络,提出异构网络中实体的排序算法。制定了用于影响力排序的规则集合并进行迭代求解。同时,利用LDA主题模型实现发明人实体的兴趣分布与发现。在真实专利数据集上的实验表明,本文提出的算法具有较好的性能与灵活性。 | Yong-ping DU Chang-qing YAO Nan LI | 2015 | Frontiers of Information Technology & Electronic Engineering2015，16，7： | 9 |
| 18 | 2018 special issue on artificial intelligence 2.0:theories and applications显示文摘In July 2017,the Chinese government issued a guideline on developing artificial intelligence(AI),namely,the‘New-Generation Artificial Intelligence Development Plan’,through 2030 to the public,setting a goal of becoming a global innovation center in this field by 2030.According to the development plan,breakthroughs should be made in basic theories of AI in terms of big data intelligence,cross-media com- | Yun-he PAN | 2018 | Frontiers of Information Technology & Electronic Engineering2018，19，1： | 9 |
| 19 | Beamforming techniques for massive MIMO systems in 5G:overview,classification,and trends for future research显示文摘Massive multiple-input multiple-output(MIMO) systems combined with beamforming antenna array technologies are expected to play a key role in next-generation wireless communication systems(5G), which will be deployed in 2020 and beyond. The main objective of this review paper is to discuss the state-of-the-art research on the most favourable types of beamforming techniques that can be deployed in massive MIMO systems and to clarify the importance of beamforming techniques in massive MIMO systems for eliminating and resolving the many technical hitches that massive MIMO system implementation faces. Classifications of optimal beamforming techniques that are used in wireless communication systems are reviewed in detail to determine which techniques are more suitable for deployment in massive MIMO systems to improve system throughput and reduce intra-and inter-cell interference. To overcome the limitations in the literature, we have suggested an optimal beamforming technique that can provide the highest performance in massive MIMO systems, satisfying the requirements of next-generation wireless communication systems. | Ehab ALI Mahamod ISMAIL Rosdiadee NORDIN Nor Fadzilah ABDULAH | 2017 | Frontiers of Information Technology & Electronic Engineering2017，18，6： | 8 |
| 20 | Multi-AUV SOM task allocation algorithm considering initial orientation and ocean current environment显示文摘There is an ocean current in the actual underwater working environment. An improved self-organizing neural network task allocation model of multiple autonomous underwater vehicles(AUVs) is proposed for a three-dimensional underwater workspace in the ocean current. Each AUV in the model will be competed, and the shortest path under an ocean current and different azimuths will be selected for task assignment and path planning while guaranteeing the least total consumption. First, the initial position and orientation of each AUV are determined. The velocity and azimuths of the constant ocean current are determined. Then the AUV task assignment problem in the constant ocean current environment is considered. The AUV that has the shortest path is selected for task assignment and path planning. Finally, to prove the effectiveness of the proposed method, simulation results are given. | Da-qi ZHU Yun QU Simon X.YANG | 2019 | Frontiers of Information Technology & Electronic Engineering2019，20，3： | 8 |
您所在的机构暂未开通此部分的功能，请联系管理员