Resource Type

Journal Article 511

Year

2023 68

2022 65

2021 64

2020 46

2019 40

2018 37

2017 42

2016 18

2015 9

2014 9

2013 13

2012 8

2011 7

2010 11

2009 4

2008 7

2007 12

2006 8

2005 13

2004 5

open ︾

Keywords

Machine learning 42

Deep learning 34

Artificial intelligence 16

Reinforcement learning 14

Active learning 4

Distributed optimization 4

Bayesian optimization 3

Big data 3

3D printing 2

Adaptive dynamic programming 2

Additive manufacturing 2

Attention 2

Autonomous driving 2

Autonomous learning 2

Blockchain 2

CANbus 2

COVID-19 2

Chemical engineering 2

Collaborative filtering 2

open ︾

Search scope:

排序： Display mode:

Dynamic value iteration networks for the planning of rapidly changing UAV swarms Research Articles

Wei Li, Bowei Yang, Guanghua Song, Xiaohong Jiang,li2ui2@zju.edu.cn,boweiy@zju.edu.cn,ghsong@zju.edu.cn,jiangxh@zju.edu.cn

Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 5,   Pages 615-766 doi: 10.1631/FITEE.1900712

Abstract: In an unmanned aerial vehicle ad-hoc network (UANET), sparse and rapidly mobile unmanned aerial vehicles (UAVs)/nodes can dynamically change the UANET topology. This may lead to UANET service performance issues. In this study, for planning rapidly changing UAV swarms, we propose a dynamic value iteration network (DVIN) model trained using the method with the connection information of UANETs to generate a state value spread function, which enables UAVs/nodes to adapt to novel physical locations. We then evaluate the performance of the DVIN model and compare it with the non-dominated sorting genetic algorithm II and the exhaustive method. Simulation results demonstrate that the proposed model significantly reduces the decision-making time for UAV/node with a high average success rate.

Keywords： 动态值迭代网络；场景式Q学习；无人机自组网；NSGA-II；路径规划    

HTML PDF Collect

Personalizing a Service Robot by Learning Human Habits from Behavioral Footprints Article

Kun Li, Max Q.-H. Meng

Engineering 2015, Volume 1, Issue 1,   Pages 79-84 doi: 10.15302/J-ENG-2015024

Abstract:

For a domestic personal robot, personalized services are as important as predesigned tasks, because the robot needs to adjust the home state based on the operator's habits. An operator's habits are composed of cues, behaviors, and rewards. This article introduces behavioral footprints to describe the operator's behaviors in a house, and applies the inverse reinforcement learning technique to extract the operator's habits, represented by a reward function. We implemented the proposed approach with a mobile robot on indoor temperature adjustment, and compared this approach with a baseline method that recorded all the cues and behaviors of the operator. The result shows that the proposed approach allows the robot to reveal the operator's habits accurately and adjust the environment state accordingly.

Keywords： personalized robot     habit learning     behavioral footprints    

HTML PDF Collect

A deep Q-learning network based active object detection model with a novel training algorithm for service Research Article

Shaopeng LIU, Guohui TIAN, Yongcheng CUI, Xuyang SHAO

Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 11,   Pages 1673-1683 doi: 10.1631/FITEE.2200109

Abstract: The DQN model is designed to fit the Q-values of various actions, and includes state space, feature extraction

Keywords： Active object detection     Deep Q-learning network     Training method     Service robots    

HTML PDF Collect

Minimax Q-learning design for H∞ control of linear discrete-time systems Research Articles

Xinxing LI, Lele XI, Wenzhong ZHA, Zhihong PENG,lixinxing_1006@163.com,xilele.bit@gmail.com,zhawenzhong@126.com,peng@bit.edu.cn

Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 3,   Pages 438-451 doi: 10.1631/FITEE.2000446

Abstract: The method is an effective approach for attenuating the effect of disturbances on practical systems, but it is difficult to obtain the ler due to the nonlinear Hamilton–Jacobi–Isaacs equation, even for linear systems. This study deals with the design of an ler for linear discrete-time systems. To solve the related game algebraic Riccati equation (GARE), a novel model-free method is developed, on the basis of an offline algorithm, which is shown to be Newton’s method for solving the GARE. The proposed method, which employs off-policy , learns the optimal control policies for the controller and the disturbance online, using only the state samples generated by the implemented behavior policies. Different from existing -learning methods, a novel gradient-based policy improvement scheme is proposed. We prove that the method converges to the saddle solution under initially admissible control policies and an appropriate positive learning rate, provided that certain persistence of excitation (PE) conditions are satisfied. In addition, the PE conditions can be easily met by choosing appropriate behavior policies containing certain excitation noises, without causing any excitation noise bias. In the simulation study, we apply the proposed method to design an load-frequency controller for an electrical power system generator that suffers from load disturbance, and the simulation results indicate that the obtained load-frequency controller has good disturbance rejection performance.

Keywords： H∞ control     Zero-sum dynamic game     Reinforcement learning     Adaptive dynamic programming     Minimax Q-learning    

HTML PDF Collect

Unsupervised object detection with scene-adaptive concept learning Research Articles

Shiliang Pu, Wei Zhao, Weijie Chen, Shicai Yang, Di Xie, Yunhe Pan,xiedi@hikvision.com

Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 5,   Pages 615-766 doi: 10.1631/FITEE.2000567

Abstract: Object detection is one of the hottest research directions in computer vision, has already made impressive progress in academia, and has many valuable applications in the industry. However, the mainstream detection methods still have two shortcomings: (1) even a model that is well trained using large amounts of data still cannot generally be used across different kinds of scenes; (2) once a model is deployed, it cannot autonomously evolve along with the accumulated unlabeled scene data. To address these problems, and inspired by theory, we propose a novel scene-adaptive evolution algorithm that can decrease the impact of scene changes through the concept of object groups. We first extract a large number of object proposals from unlabeled data through a pre-trained detection model. Second, we build the dictionary of object concepts by clustering the proposals, in which each cluster center represents an object prototype. Third, we look into the relations between different clusters and the object information of different groups, and propose a graph-based group information propagation strategy to determine the category of an object concept, which can effectively distinguish positive and negative proposals. With these pseudo labels, we can easily fine-tune the pre-trained model. The effectiveness of the proposed method is verified by performing different experiments, and the significant improvements are achieved.

Keywords： 视觉知识；无监督视频目标检测；场景自适应学习    

HTML PDF Collect

Communicative Learning: A Unified Learning Formalism Review

Luyao Yuan, Song-Chun Zhu

Engineering 2023, Volume 25, Issue 6,   Pages 77-100 doi: 10.1016/j.eng.2022.10.017

Abstract:

In this article, we propose a communicative learning (CL) formalism that unifies existing machine learning paradigms, such as passive learning, active learning, algorithmic teaching, and so forth, and facilitates the development of new learning methods. Arising from human cooperative communication, this formalism poses learning as a communicative process and combines pedagogy with the burgeoning field of machine learning. The pedagogical insight facilitates the adoption of alternative information sources in machine learning besides randomly sampled data, such as intentional messages given by a helpful teacher. More specifically, in CL, a teacher and a student exchange information with each other collaboratively to transmit and acquire certain knowledge. Each agent has a mind, which includes the agent's knowledge, utility, and mental dynamics. To establish effective communication, each agent also needs an estimation of its partner's mind. We define expressive mental representations and learning formulation sufficient for such recursive modeling, which endows CL with human-comparable learning efficiency. We demonstrate the application of CL to several prototypical collaboration tasks and illustrate that this formalism allows learning protocols to go beyond Shannon's communication limit. Finally, we present our contribution to the foundations of learning by putting forth hierarchies in learning and defining the halting problem of learning.

Keywords： Artificial intelligencehine     Cooperative communication     Machine learning     Pedagogy     Theory of mind    

HTML PDF Collect

Interactive image segmentation with a regression based ensemble learning paradigm Article

Jin ZHANG, Zhao-hui TANG, Wei-hua GUI, Qing CHEN, Jin-ping LIU

Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 7,   Pages 1002-1020 doi: 10.1631/FITEE.1601401

Abstract: To achieve fine segmentation of complex natural images, people often resort to an interactive segmentation paradigm, since fully automatic methods often fail to obtain a result consistent with the ground truth. However, when the foreground and background share some similar areas in color, the fine segmentation result of conventional interactive methods usually relies on the increase of manual labels. This paper presents a novel interactive image segmentation method via a regression-based ensemble model with semi-supervised learning. The task is formulated as a non-linear problem integrating two complementary spline regressors and strengthening the robustness of each regressor via semi-supervised learning. First, two spline regressors with a complementary nature are constructed based on multivariate adaptive regression splines (MARS) and smooth thin plate spline regression (TPSR). Then, a regressor boosting method based on a clustering hypothesis and semi-supervised learning is proposed to assist the training of MARS and TPSR by using the region segmentation information contained in unlabeled pixels. Next, a support vector regression (SVR) based decision fusion model is adopted to integrate the results of MARS and TPSR. Finally, the GraphCut is introduced and combined with the SVR ensemble results to achieve image segmentation. Extensive experimental results on benchmark datasets of BSDS500 and Pascal VOC have demonstrated the effectiveness of our method, and the com-parison with experiment results has validated that the proposed method is comparable with the state-of-the-art methods for in-teractive natural image segmentation.

Keywords： Interactive image segmentation     Multivariate adaptive regression splines (MARS)     Ensemble learning     Thin-plate spline regression (TPSR)     Semi-supervised learning     Support vector regression (SVR)    

HTML PDF Collect

Interactive visual labelling versus active learning: an experimental comparison Research

Mohammad CHEGIN, Jürgen BERNARD, Jian CUI, Fatemeh CHEGINI, Alexei SOURIN, Keith Keith, Tobias SCHRECK

Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 4,   Pages 524-535 doi: 10.1631/FITEE.1900549

Abstract: Methods from supervised machine learning allow the classification of new data automatically and are tremendously helpful for data analysis. The quality of supervised maching learning depends not only on the type of algorithm used, but also on the quality of the labelled dataset used to train the classifier. Labelling instances in a training dataset is often done manually relying on selections and annotations by expert analysts, and is often a tedious and time-consuming process. Active learning algorithms can automatically determine a subset of data instances for which labels would provide useful input to the learning process. Interactive visual labelling techniques are a promising alternative, providing effective visual overviews from which an analyst can simultaneously explore data records and select items to a label. By putting the analyst in the loop, higher accuracy can be achieved in the resulting classifier. While initial results of interactive visual labelling techniques are promising in the sense that user labelling can improve supervised learning, many aspects of these techniques are still largely unexplored. This paper presents a study conducted using the mVis tool to compare three interactive visualisations, similarity map, scatterplot matrix (SPLOM), and parallel coordinates, with each other and with active learning for the purpose of labelling a multivariate dataset. The results show that all three interactive visual labelling techniques surpass active learning algorithms in terms of classifier accuracy, and that users subjectively prefer the similarity map over SPLOM and parallel coordinates for labelling. Users also employ different labelling strategies depending on the visualisation used.

Keywords： Interactive visual labelling     Active learning     Visual analytics    

HTML PDF Collect

Development of a new method for RMR and Q classification method to optimize support system in tunneling

Asghar RAHMATI,Lohrasb FARAMARZI,Manouchehr SANEI

Frontiers of Structural and Civil Engineering 2014, Volume 8, Issue 4,   Pages 448-455 doi: 10.1007/s11709-014-0262-x

Abstract: Rock mass classification system is very suitable for various engineering design and stability analysis. classification method is confirmed by Japan Highway Public Corporation that this method can figure out either strength or deformability of rock mass, further appropriating the amount of rock bolts, thickness of shotcrete, and size of pitch of steel ribs just after the blasting procedure. Based on these advantages of method, in this study, according to data of five deep and long tunnels in Iran, two equations for estimating the value of method from and classification systems were developed. These equations as a new method were able to optimize the support system for and classification systems. From classification and its application in these case studies, it is pointed out that the method for the design of support systems in underground working is more reliable than the and classification systems.

Keywords： JH classification     Q and RMR classification     new method    

HTML PDF Collect

An approach for evaluating fire resistance of high strength Q460 steel columns

Wei-Yong WANG, Guo-Qiang LI, Bao-lin YU

Frontiers of Structural and Civil Engineering 2014, Volume 8, Issue 1,   Pages 26-35 doi: 10.1007/s11709-014-0239-9

Abstract: To develop a methodology for evaluating fire resistance of high strength Q460 steel columns, the loadbearing capacity of high strength Q460 steel columns is investigated.evaluating load bearing capacity of mild steel columns at room temperature is extended to high strength Q460steel columns with due consideration to high temperature properties of high strength Q460 steel.The critical temperature of high strength Q460 steel column is presented and compared with mild steel

Keywords： high strength Q460 steel     load bearing capacity     temperature    

HTML PDF Collect

A traffic-aware Q-network enhanced routing protocol based on GPSR for unmanned aerial vehicle ad-hoc Research Articles

Yi-ning Chen, Ni-qi Lyu, Guang-hua Song, Bo-wei Yang, Xiao-hong Jiang,ch19930611@zju.edu.cn,lvniqi@gmail.com,ghsong@zju.edu.cn,boweiy@zju.edu.cn,jiangxh@zju.edu.cn

Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 9,   Pages 1308-1320 doi: 10.1631/FITEE.1900401

Abstract: In dense traffic unmanned aerial vehicle (UAV) ad-hoc networks, traffic congestion can cause increased delay and packet loss, which limit the performance of the networks; therefore, a strategy is required to control the traffic. In this study, we propose TQNGPSR, a traffic-aware enhanced protocol based on greedy perimeter stateless routing (GPSR), for UAV ad-hoc networks. The protocol enforces a strategy using the congestion information of neighbors, and evaluates the quality of a wireless link by the algorithm, which is a algorithm. Based on the evaluation of each wireless link, the protocol makes routing decisions in multiple available choices to reduce delay and decrease packet loss. We simulate the performance of TQNGPSR and compare it with AODV, OLSR, GPSR, and QNGPSR. Simulation results show that TQNGPSR obtains higher packet delivery ratios and lower end-to-end delays than GPSR and QNGPSR. In high node density scenarios, it also outperforms AODV and OLSR in terms of the packet delivery ratio, end-to-end delay, and throughput.

Keywords： Traffic balancing     Reinforcement learning     Geographic routing     Q-network    

HTML PDF Collect

Interactive medical image segmentation with self-adaptive confidence calibration

沈楚云,李文浩,徐琪森,胡斌,金博,蔡海滨,朱凤平,李郁欣,王祥丰

Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 9,   Pages 1332-1348 doi: 10.1631/FITEE.2200299

Abstract: Interactive medical image segmentation based on human-in-the-loop machine learning is a novel paradigm that draws on human expert knowledge to assist medical image segmentation. However, existing methods often fall into what we call interactive misunderstanding, the essence of which is the dilemma in trading off short- and long-term interaction information. To better use the interaction information at various timescales, we propose an interactive segmentation framework, called interactive MEdical image segmentation with self-adaptive Confidence CAlibration (MECCA), which combines action-based confidence learning and multi-agent reinforcement learning. A novel confidence network is learned by predicting the alignment level of the action with short-term interaction information. A confidence-based reward-shaping mechanism is then proposed to explicitly incorporate confidence in the policy gradient calculation, thus directly correcting the model’s interactive misunderstanding. MECCA also enables user-friendly interactions by reducing the interaction intensity and difficulty via label generation and interaction guidance, respectively. Numerical experiments on different segmentation tasks show that MECCA can significantly improve short- and long-term interaction information utilization efficiency with remarkably fewer labeled samples. The demo video is available at https://bit.ly/mecca-demo-video.

Keywords： Medical image segmentation     Interactive segmentation     Multi-agent reinforcement learning     Confidence learning     Semi-supervised learning    

HTML Collect

The Index System Design of the High Building Fire Hazard Assessment

Liu Aihua,Shi Shiliang,Wu Chao

Strategic Study of CAE 2006, Volume 8, Issue 9,   Pages 90-94

Abstract:

Aiming at the characteristics of the high building fire, setting the fire site scene, this paper carries out stage partition for fire on the angle of the countermeasure for fire, conducts accident analysis aiming at every stage applying FEA and ETA，finds out the related factors that affects fire development and stretch，and establishes the multiple-levels index system of high building fire hazard assessment. This index system can offer scientific basis for safe management of building, and can also lay the foundation for high building fire hazard assessment.

Keywords： high building fire hazard     index system     the fire site scene     stage partition for fire    

HTML PDF Collect

Strategies and Principles of Distributed Machine Learning on Big Data Review

Eric P. Xing,Qirong Ho,Pengtao Xie,Dai Wei

Engineering 2016, Volume 2, Issue 2,   Pages 179-195 doi: 10.1016/J.ENG.2016.02.008

Abstract:

The rise of big data has led to new demands for machine learning (ML) systems to learn complex models, with millions to billions of parameters, that promise adequate capacity to digest massive datasets and offer powerful predictive analytics (such as high-dimensional latent features, intermediate representations, and decision functions) thereupon. In order to run ML algorithms at such scales, on a distributed cluster with tens to thousands of machines, it is often the case that significant engineering efforts are required—and one might fairly ask whether such engineering truly falls within the domain of ML research. Taking the view that “big” ML systems can benefit greatly from ML-rooted statistical and algorithmic insights—and that ML researchers should therefore not shy away from such systems design—we discuss a series of principles and strategies distilled from our recent efforts on industrial-scale ML solutions. These principles and strategies span a continuum from application, to engineering, and to theoretical research and development of big ML systems and architectures, with the goal of understanding how to make them efficient, generally applicable, and supported with convergence and scaling guarantees. They concern four key questions that traditionally receive little attention in ML research: How can an ML program be distributed over a cluster? How can ML computation be bridged with inter-machine communication? How can such communication be performed? What should be communicated between machines? By exposing underlying statistical and algorithmic characteristics unique to ML programs but not typically seen in traditional computer programs, and by dissecting successful cases to reveal how we have harnessed these principles to design and develop both high-performance distributed ML software as well as general-purpose ML frameworks, we present opportunities for ML researchers and practitioners to further shape and enlarge the area that lies between ML and systems.

Keywords： Machine learning     Artificial intelligence big data     Big model     Distributed systems     Principles     Theory     Data-parallelism     Model-parallelism    

HTML PDF Collect

MDLB: a metadata dynamic load balancing mechanism based on reinforcement learning Research Articles

Zhao-qi Wu, Jin Wei, Fan Zhang, Wei Guo, Guang-wei Xie,17034203@qq.com

Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 7,   Pages 963-1118 doi: 10.1631/FITEE.1900121

Abstract: With the growing amount of information and data, s have been widely used in many applications, including the Google File System, Amazon S3, Hadoop Distributed File System, and Ceph, in which load balancing of plays an important role in improving the input/output performance of the entire system. Unbalanced load on the server leads to a serious bottleneck problem for system performance. However, most existing load balancing strategies, which are based on subtree segmentation or hashing, lack good dynamics and adaptability. In this study, we propose a (MDLB) mechanism based on (RL). We learn that the algorithm and our RL-based strategy consist of three modules, i.e., the policy selection network, load balancing network, and parameter update network. Experimental results show that the proposed MDLB algorithm can adjust the load dynamically according to the performance of the servers, and that it has good adaptability in the case of sudden change of data volume.

Keywords： 面向对象的存储系统；元数据；动态负载均衡；强化学习；Q_learning    

HTML PDF Collect

Title Author Date Type Operation

Dynamic value iteration networks for the planning of rapidly changing UAV swarms

Wei Li, Bowei Yang, Guanghua Song, Xiaohong Jiang,li2ui2@zju.edu.cn,boweiy@zju.edu.cn,ghsong@zju.edu.cn,jiangxh@zju.edu.cn

Journal Article

Personalizing a Service Robot by Learning Human Habits from Behavioral Footprints

Kun Li, Max Q.-H. Meng

Journal Article

A deep Q-learning network based active object detection model with a novel training algorithm for service

Shaopeng LIU, Guohui TIAN, Yongcheng CUI, Xuyang SHAO

Journal Article

Minimax Q-learning design for H∞ control of linear discrete-time systems

Xinxing LI, Lele XI, Wenzhong ZHA, Zhihong PENG,lixinxing_1006@163.com,xilele.bit@gmail.com,zhawenzhong@126.com,peng@bit.edu.cn

Journal Article

Unsupervised object detection with scene-adaptive concept learning

Shiliang Pu, Wei Zhao, Weijie Chen, Shicai Yang, Di Xie, Yunhe Pan,xiedi@hikvision.com

Journal Article

Communicative Learning: A Unified Learning Formalism

Luyao Yuan, Song-Chun Zhu

Journal Article

Interactive image segmentation with a regression based ensemble learning paradigm

Jin ZHANG, Zhao-hui TANG, Wei-hua GUI, Qing CHEN, Jin-ping LIU

Journal Article

Interactive visual labelling versus active learning: an experimental comparison

Mohammad CHEGIN, Jürgen BERNARD, Jian CUI, Fatemeh CHEGINI, Alexei SOURIN, Keith Keith, Tobias SCHRECK

Journal Article

Development of a new method for RMR and Q classification method to optimize support system in tunneling

Asghar RAHMATI,Lohrasb FARAMARZI,Manouchehr SANEI

Journal Article

An approach for evaluating fire resistance of high strength Q460 steel columns

Wei-Yong WANG, Guo-Qiang LI, Bao-lin YU

Journal Article

A traffic-aware Q-network enhanced routing protocol based on GPSR for unmanned aerial vehicle ad-hoc

Yi-ning Chen, Ni-qi Lyu, Guang-hua Song, Bo-wei Yang, Xiao-hong Jiang,ch19930611@zju.edu.cn,lvniqi@gmail.com,ghsong@zju.edu.cn,boweiy@zju.edu.cn,jiangxh@zju.edu.cn

Journal Article

Interactive medical image segmentation with self-adaptive confidence calibration

沈楚云,李文浩,徐琪森,胡斌,金博,蔡海滨,朱凤平,李郁欣,王祥丰

Journal Article

The Index System Design of the High Building Fire Hazard Assessment

Liu Aihua,Shi Shiliang,Wu Chao

Journal Article

Strategies and Principles of Distributed Machine Learning on Big Data

Eric P. Xing,Qirong Ho,Pengtao Xie,Dai Wei

Journal Article

MDLB: a metadata dynamic load balancing mechanism based on reinforcement learning

Zhao-qi Wu, Jin Wei, Fan Zhang, Wei Guo, Guang-wei Xie,17034203@qq.com

Journal Article