Bv-Person: A Large-Scale Dataset For Bird-View Person Re-Identification,
2021
Singapore Management University
Bv-Person: A Large-Scale Dataset For Bird-View Person Re-Identification, Cheng Yan, Guansong Pang, Lei Wang, Jile Jiao, Xuetao Feng, Chunhua Shen, Jingjing Li
Research Collection School Of Computing and Information Systems
Person Re-IDentification (ReID) aims at re-identifying persons from non-overlapping cameras. Existing person ReID studies focus on horizontal-view ReID tasks, in which the person images are captured by the cameras from a (nearly) horizontal view. In this work we introduce a new ReID task, bird-view person ReID, which aims at searching for a person in a gallery of horizontal-view images with the query images taken from a bird's-eye view, i.e., an elevated view of an object from above. The task is important because there are a large number of video surveillance cameras capturing persons from such an elevated view at public …
Interactive Probing Of Multivariate Time Series Prediction Models: A Case Of Freight Rate Analysis,
2021
Singapore Management University
Interactive Probing Of Multivariate Time Series Prediction Models: A Case Of Freight Rate Analysis, Haonan Xu, Haotian Li, Yong Wang
Research Collection School Of Computing and Information Systems
We present an interactive probing tool to create, modify and analyze what-if scenarios for multivariate time series models. The solution is applied to freight trading, where analysts can carry out sensitivity analysis on freight rates by changing demand and supply-related econometric variables and observing their resultant effects on freight indexes. We utilize various visualization techniques to enable intuitive scenario creation, alteration, and comprehension of time series inputs and model predictions. Our tool proved to be useful to the industry practitioners, demonstrated by a case study where freight traders are given hypothetical market scenarios and successfully generated quantitative freight index projection …
Themes, Communities And Influencers Of Online Probiotics Chatter: A Retrospective Analysis From 2009-2017,
2021
Northumbria University
Themes, Communities And Influencers Of Online Probiotics Chatter: A Retrospective Analysis From 2009-2017, Santosh Vijaykumar, Aravind Sesagiri Raamkumar, Kristofor Mccarty, Cuthbert Mutumbwa, Jawwad Mustafa, Cyndy Au
Research Collection Lee Kong Chian School Of Business
We build on recent examinations questioning the quality of online information about probiotic products by studying the themes of content, detecting virtual communities and identifying key influencers in social media using data science techniques. We conducted topic modelling (n = 36,715 tweets) and longitudinal social network analysis (n = 17,834 tweets) of probiotic chatter on Twitter from 2009–17. We used Latent Dirichlet Allocation (LDA) to build the topic models and network analysis tool Gephi for building yearly graphs. We identified the top 10 topics of probiotics-related communication on Twitter and a constant rise in communication activity. However the number of …
A Large-Scale Benchmark For Food Image Segmentation,
2021
Singapore Management University
A Large-Scale Benchmark For Food Image Segmentation, Xiongwei Wu, Xin Fu, Ying Liu, Ee-Peng Lim, Steven C. H. Hoi, Qianru Sun
Research Collection School Of Computing and Information Systems
Food image segmentation is a critical and indispensible task for developing health-related applications such as estimating food calories and nutrients. Existing food image segmentation models are underperforming due to two reasons: (1) there is a lack of high quality food image datasets with fine-grained ingredient labels and pixel-wise location masks—the existing datasets either carry coarse ingredient labels or are small in size; and (2) the complex appearance of food makes it difficult to localize and recognize ingredients in food images, e.g., the ingredients may overlap one another in the same image, and the identical ingredient may appear distinctly in different …
Burst-Induced Multi-Armed Bandit For Learning Recommendation,
2021
Singapore Management University
Burst-Induced Multi-Armed Bandit For Learning Recommendation, Rodrigo Alves, Antoine Ledent, Marius Kloft
Research Collection School Of Computing and Information Systems
In this paper, we introduce a non-stationary and context-free Multi-Armed Bandit (MAB) problem and a novel algorithm (which we refer to as BMAB) to solve it. The problem is context-free in the sense that no side information about users or items is needed. We work in a continuous-time setting where each timestamp corresponds to a visit by a user and a corresponding decision regarding recommendation. The main novelty is that we model the reward distribution as a consequence of variations in the intensity of the activity, and thereby we assist the exploration/exploitation dilemma by exploring the temporal dynamics of the …
Deep Learning For Image Super-Resolution: A Survey,
2021
South China University of Technology
Deep Learning For Image Super-Resolution: A Survey, Zhihao Wang, Jian Chen, Steven C. H. Hoi
Research Collection School Of Computing and Information Systems
Image Super-Resolution (SR) is an important class of image processing techniqueso enhance the resolution of images and videos in computer vision. Recent years have witnessed remarkable progress of image super-resolution using deep learning techniques. This article aims to provide a comprehensive survey on recent advances of image super-resolution using deep learning approaches. In general, we can roughly group the existing studies of SR techniques into three major categories: supervised SR, unsupervised SR, and domain-specific SR. In addition, we also cover some other important issues, such as publicly available benchmark datasets and performance evaluation metrics. Finally, we conclude this survey by …
Online Learning: A Comprehensive Survey,
2021
Singapore Management University
Online Learning: A Comprehensive Survey, Steven C. H. Hoi, Doyen Sahoo, Jing Lu, Peilin Zhao
Research Collection School Of Computing and Information Systems
Online learning represents a family of machine learning methods, where a learner attempts to tackle some predictive (or any type of decision-making) task by learning from a sequence of data instances one by one at each time. The goal of online learning is to maximize the accuracy/correctness for the sequence of predictions/decisions made by the online learner given the knowledge of correct answers to previous prediction/learning tasks and possibly additional information. This is in contrast to traditional batch or offline machine learning methods that are often designed to learn a model from the entire training data set at once. Online …
Challenges And Reflection On Next-Generation Large-Scale Computer Wargame System,
2021
College of Joint Operations, National Defence University, Beijing 100091, China;
Challenges And Reflection On Next-Generation Large-Scale Computer Wargame System, Guangya Si, Yanzheng Wang
Journal of System Simulation
Abstract: In view of the systematic, networked and intelligent characteristics of the future war, the major challenges of the new generation of large computer warfare system are proposed, and the next-generation large-scale computer wargame system is constructed. The key technologies of building a new generation of large computer warfare systems, such as intelligent war modeling, architecture integration, resource service management and human-computer interaction are researched.
Exploring Formal Model Transformation Techniques Within Model Driven Engineering,
2021
College of System Engineering, National University of Defense Technology, Changsha 410073, China;
Exploring Formal Model Transformation Techniques Within Model Driven Engineering, Zhu Zhi, Lei Sen, Yonglin Lei
Journal of System Simulation
Abstract: With the increasing complexity of simulation system and the wide use of simulation models, the higher requirements of the efficiency and quality for simulation models are needed. Currently, model-driven engineering is mostly applied in many simulation software tools, which cannot really carry out the formal analysis at the model level. Based on model driven engineering, the domain specific language with metamodeling and engineering model continuity is designed. Taking a group fire control channel system as the example, the domain specific language is designed and the conceptual models are transformed into other precise semantics to carry out the final executable …
Modeling Research Of Cognition Behavior For Intelligent Wargaming,
2021
College of Joint Operations, National Defence University, Beijing 100091, China;
Modeling Research Of Cognition Behavior For Intelligent Wargaming, Xiaoyuan He, Shengming Guo, Wu Lin, Li Dong, Xu Xiao, Li Li
Journal of System Simulation
Abstract: Aiming at the problem of cognitive behavior modeling in the construction and application of intelligent wargaming system, one modeling framework based on Actor-Operations-Scene (AOS) was proposed for C2 agent in wargaming. Then the realization of cognitive behavior modeling method for C2 agent was explored, including the modeling for the scenario oriented knowledge graph, intelligent situation awareness, operational planning, integrated operational control. It provides a feasible scheme for the construction and application of intelligent wargaming system.
Intelligent Wargaming System: Change Needed By Next Generation Need To Be Changed,
2021
College of Joint Operation, National Defense University, Beijing100091, China;
Intelligent Wargaming System: Change Needed By Next Generation Need To Be Changed, Xiaofeng Hu, Dawei Qi
Journal of System Simulation
Abstract: The future direction of wargaming system is intelligent, and the most significant feature of intelligence is the modeling of cognition. The main problems of wargaming system are summarized, the main difficulties of modeling brought by cognition and the overall framework of intelligent wargaming system design are discussed, the technical ways of transformation and upgrading based on the existing wargaming system are given from four aspects of model construction, system design, wargaming ecology and test inspection. It provides direction and reference to the development and construction of the next generation intelligent wargaming system.
Study On Next-Generation Strategic Wargame System,
2021
College of Joint Operation, National Defense University, Beijing 100091, China;
Study On Next-Generation Strategic Wargame System, Wu Xi, Xianglin Meng, Jingyu Yang
Journal of System Simulation
Abstract: Strategic wargame is an important support to the strategic decision. The research status and challenges of the strategic wargame are analyzed, and the influence of big data and artificial intelligence technology on the strategic wargame system is studied. The prospects and key technologies of the next-generation strategic wargame system are studied, including the construction of event association graph for strategic topics, generation of strategic decision sparse samples based on generative adversarial nets, gaming strategy learning of human-in-loop hybrid enhancement, and public opinion dissemination modeling technology based on social network. The development trend of the strategic wargame is proposed.
Order Sorting Optimization For Four-Way Shuttle System Based On Improved Genetic Algorithm,
2021
1. College of Information and Electrical Engineering, Hunan University of Science and Technology, Xiangtan 411201, China; ;
Order Sorting Optimization For Four-Way Shuttle System Based On Improved Genetic Algorithm, Xinjie He, Shaowu Zhou, Hongqiang Zhang, Lianghong Wu, Zhou You
Journal of System Simulation
Abstract: During the batch outbound operations of the four-way shuttle system, the different execution order of the system's outbound leads to the different interaction time between the four-way shuttle and the hoist will be different, which will affect the system's outbound operation time. According to the operation process of batch outbound, with the order of batch order outflow as the variable and the system outflow time as the objective function, a system order sort optimization model i established. Based to the characteristics of the model, with the improved genetic algorithm, the optimal order of the system is obtained. By changing …
Wargaming Eco-System For Intelligence Growing,
2021
College of Joint Operation, National Defense University, Beijing 100091, China;
Wargaming Eco-System For Intelligence Growing, Wu Lin, Xiaofeng Hu, Jiuyang Tao, Xiaoyuan He
Journal of System Simulation
Abstract: The construction of the next generation intelligent wargaming system can not be accomplished at one move, but through building an ecosystem to gradually grow intelligence. The basic concepts of the intelligent wargame ecosystem, and are defined the idea of dynamic openness, diversified levels and co-evolution are proposed. Drawing lessons from the human intelligence growing process and learning-evolution mechanism, the double helix model of the next generation of wargame cognitive intelligent evolution and growth is constructed. On the basis of the OLTA cycle, the wargame deduction ecosystem system framework is given. The application of the technologies, such as …
Application Of Two-Population Fish Swarm Algorithm In Distributed Portfolio,
2021
School of Management Science and Engineering, Anhui University of Technology, Ma'anshan 243032, China;
Application Of Two-Population Fish Swarm Algorithm In Distributed Portfolio, Fuyu Wang, Tang Tao
Journal of System Simulation
Abstract: Aiming at the disadvantages of artificial fish swarm algorithm, such as low precision and easily falling into local optimum, combining the idea of gravity algorithm and teaching optimization, a two-population fish swarm search algorithm is proposed. Cross-thinking is adopted to optimize the results obtained by the two populations and avoid the local optimization. Metropoils criterion of simulated annealing is added to the standard function verifies the algorithm, and the results show that the two-population fish swarm algorithm is better than the traditional artificial fish swarm algorithm and the known literature algorithm. Based on the known literature, a distributed …
Learning Ant Colony Algorithm For Green Multi-Depot Vehicle Routing Problem,
2021
1. Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China; ;2. Yunnan Key Laboratory of Artificial Intelligence, Kunming University of Science and Technology, Kunming 650500, China;
Learning Ant Colony Algorithm For Green Multi-Depot Vehicle Routing Problem, Hu Rong, Wenbo Chen, Bin Qian, Guo Ning, Fenghong Xiang
Journal of System Simulation
Abstract: Considering the congested roads situation of urban central areas in China, a speed calculation method based on vehicle driving sections is designed, and a model for the Green Multi-Depot Vehicle Routing Problem with Total Fuel-Consumption cost Criterion (TFC-GMDVRP) is established, considering simultaneously the vehicle travel distance, load, and speed factors. A learning ant colony optimization algorithm (LACO), combining a knowledge model and an ant colony optimization algorithm (ACO), is proposed for solving the TFC-GMDVRP. In order to improve the performance and robustness of the algorithm's global search, the parameter knowledge that contains the different …
Hurricane Trajectory Outlier Detection Method Based On Variational Auto-Encode,
2021
College of Systems Engineering, National University of Defense Technology, Changsha 410073, China;
Hurricane Trajectory Outlier Detection Method Based On Variational Auto-Encode, Wanting Qin, Songyang Lao, Tang Jun, Lu Cong
Journal of System Simulation
Abstract: Hurricanes often cause incalculable human and economic losses, and the trajectory outlier detection can provide the auxiliary information or abnormal warning of the disaster. On deep learning, a method of hurricane trajectory outlier detection based on variable auto encoder (VAEOD) is proposed in this paper. The trajectory is divided into equal sequence sub trajectories based on the sliding window as the input of VAE. The trajectory reconstruction model is trained by the VAE. The parallel, vertical and angle distance of reconstructed trajectory and the input trajectory are compared to find out the outlier trajectory segments. The simulation experiment on …
Research And Application On Space-Launching Mission Simulated Rehearsal Technology,
2021
Beijing Institute of Tracking and Communication Technology, Beijing 100094, China;
Research And Application On Space-Launching Mission Simulated Rehearsal Technology, Xiuluo Liu, Wang Jia, Wu Feng, Liu Yang, Ailiang Zhang, Wang Min
Journal of System Simulation
Abstract: High-density space launching tasks need the new requirements for space-launching mission rehearsal. The new concept of space-launching mission simulated rehearsal is proposed, the definition and content are presented in detail,and the technology research objective and key works are analyzed. The technology implementation architecture is established on five dimensions of the domain resources, developing tools, simulation modeling, fundamental function design and domain application. On the basis of simulation, the working process is given, the simulation software architecture is designed, and the simulation application tool is developed. The simulation results are also given, which validate the method and technology.
Mechanism Design For Entities' Passive Dimensional Sensing Interaction In Discrete Event Simulations,
2021
1. Beijing Huaru Technology Co., Ltd., Beijing 100193, China; ;
Mechanism Design For Entities' Passive Dimensional Sensing Interaction In Discrete Event Simulations, Yan Fei, Bin Gan, Zhaodi Chen, Wenjuan Ma, Luyao Li, Zhang Ke
Journal of System Simulation
Abstract: Dimensional sensing interaction mechanism is a method of computing the entities' visibility on the basis of the position and visible range, and informing when and where the entities can perceive each other. Entities' active computing on the relative position needs a lot of computation and is low efficiency, and slow down the simulation execution at last. The mechanism and framework of the passive dimensional sensing interaction, including the spatial grid models, discrete movement models, and passive sense models are researched. Dimensional sensing interaction manager is designed to realize the computation of entities' dimensional sensing interaction in discrete event-based battle …
Research On The Issues Of Next Generation Wargame System Model Engine,
2021
1. College of Joint Operation, National Defense University, Beijing 100091, China; ;
Research On The Issues Of Next Generation Wargame System Model Engine, Yubo Tang, Bilong Shen, Shi Lei, Yi Xing
Journal of System Simulation
Abstract: Aiming at the more and more complex war systems, widely used artificial intelligence technology is needed to make up the human deficiencies in future wargame deduction, which is necessary for the next generation wargame system model engine. To address these challenges, a framework prototype of the next generation wargame model engine based on the experience of the long-term development and application is proposed. The decoupling method for the complexity of structure and computation is researched. The human-computer integration architecture on digital twinning technology is studied. Some new modeling techniques which the threshold of model development is reduced and the …
