The Future Of Work Now: Automl At 84.51°And Kroger,
2020
Babson College
The Future Of Work Now: Automl At 84.51°And Kroger, Thomas H. Davenport, Steven M. Miller
Research Collection School Of Computing and Information Systems
One of the most frequently-used phrases at business events these days is “the future of work.” It’s increasingly clear that artificial intelligence and other new technologies will bring substantial changes in work tasks and business processes. But while these changes are predicted for the future, they’re already present in many organizations for many different jobs. The job and incumbents described below are an example of this phenomenon.
Foodbot: A Goal-Oriented Just-In-Time Healthy Eating Interventions Chatbot,
2020
Singapore Management University
Foodbot: A Goal-Oriented Just-In-Time Healthy Eating Interventions Chatbot, Philips Kokoh Prasetyo, Palakorn Achananuparp, Ee-Peng Lim
Research Collection School Of Computing and Information Systems
Recent research has identified a few design flaws in popular mobile health (mHealth) applications for promoting healthy eating lifestyle, such as mobile food journals. These include tediousness of manual food logging, inadequate food database coverage, and a lack of healthy dietary goal setting. To address these issues, we present Foodbot, a chatbot-based mHealth application for goal-oriented just-in-time (JIT) healthy eating interventions. Powered by a large-scale food knowledge graph, Foodbot utilizes automatic speech recognition and mobile messaging interface to record food intake. Moreover, Foodbot allows users to set goals and guides their behavior toward the goals via JIT notification prompts, interactive …
Dual-Slam: A Framework For Robust Single Camera Navigation,
2020
Singapore Management University
Dual-Slam: A Framework For Robust Single Camera Navigation, Huajian Huang, Wen-Yan Lin, Siying Liu, Dong Zhang, Sai-Kit Yeung
Research Collection School Of Computing and Information Systems
SLAM (Simultaneous Localization And Mapping) seeks to provide a moving agent with real-time self-localization. To achieve real-time speed, SLAM incrementally propagates position estimates. This makes SLAM fast but also makes it vulnerable to local pose estimation failures. As local pose estimation is ill-conditioned, local pose estimation failures happen regularly, making the overall SLAM system brittle. This paper attempts to correct this problem. We note that while local pose estimation is ill-conditioned, pose estimation over longer sequences is well-conditioned. Thus, local pose estimation errors eventually manifest themselves as mapping inconsistencies. When this occurs, we save the current map and activate two …
Gesture Enhanced Comprehension Of Ambiguous Human-To-Robot Instructions,
2020
Singapore Management University
Gesture Enhanced Comprehension Of Ambiguous Human-To-Robot Instructions, Weerakoon Mudiyanselage Dulanga Kaveesha Weerakoon, Vigneshwaran Subbaraju, Nipuni Karumpulli, Minh Anh Tuan Tran, Qianli Xu, U-Xuan Tan, Joo Hwee Lim, Archan Misra
Research Collection School Of Computing and Information Systems
This work demonstrates the feasibility and benefits of using pointing gestures, a naturally-generated additional input modality, to improve the multi-modal comprehension accuracy of human instructions to robotic agents for collaborative tasks.We present M2Gestic, a system that combines neural-based text parsing with a novel knowledge-graph traversal mechanism, over a multi-modal input of vision, natural language text and pointing. Via multiple studies related to a benchmark table top manipulation task, we show that (a) M2Gestic can achieve close-to-human performance in reasoning over unambiguous verbal instructions, and (b) incorporating pointing input (even with its inherent location uncertainty) in M2Gestic results in a significant …
Chess As A Testing Grounds For The Oracle Approach To Ai Safety,
2020
Smith College
Chess As A Testing Grounds For The Oracle Approach To Ai Safety, James D. Miller, Roman Yampolskiy, Olle Häggström, Stuart Armstrong
Faculty and Staff Scholarship
To reduce the danger of powerful super-intelligent AIs, we might make the first such AIs oracles that can only send and receive messages. This paper proposes a possibly practical means of using machine learning to create two classes of narrow AI oracles that would provide chess advice: those aligned with the player's interest, and those that want the player to lose and give deceptively bad advice. The player would be uncertain which type of oracle it was interacting with. As the oracles would be vastly more intelligent than the player in the domain of chess, experience with these oracles might …
Trainable Structure Tensors For Autonomous Baggage Threat Detection Under Extreme Occlusion,
2020
Center for Cyber-Physical Systems (C2PS), Khalifa University, United Arab Emirates
Trainable Structure Tensors For Autonomous Baggage Threat Detection Under Extreme Occlusion, Taimur Hassan, Samet Akçay, Mohammed Bennamoun, Salman Khan, Naoufel Werghi
Computer Vision Faculty Publications
Detecting baggage threats is one of the most difficult tasks, even for expert officers. Many researchers have developed computer-aided screening systems to recognize these threats from the baggage X-ray scans. However, all of these frameworks are limited in identifying the contraband items under extreme occlusion. This paper presents a novel instance segmentation framework that utilizes trainable structure tensors to highlight the contours of the occluded and cluttered contraband items (by scanning multiple predominant orientations), while simultaneously suppressing the irrelevant baggage content. The proposed framework has been extensively tested on four publicly available X-ray datasets where it outperforms the state-of-the-art frameworks …
Eeg Classification Based On Multi-Domain Features And Random Subspace Ensemble,
2020
Key Laboratory of Data Engineering and Visual Computing, College of Computer Science and Technology Chongqing University of Posts and Telecommunications, Chongqing 400065, China;
Eeg Classification Based On Multi-Domain Features And Random Subspace Ensemble, Deng Xin, Can Long, Jianxun Mi, Boxian Zhang, Kaiwei Sun, Wang Jin
Journal of System Simulation
Abstract: Aiming at the preprocessing feature extraction and classification recognition in BCI system, a method for EEG classification of motion imagery based on random subspaces ensemble learning of multi-domain features is proposed. Based on the analysis on the ERD/ERS characteristics of motion imagery (MI) signals, the multi-domain features of best effective time and frequency bands are extracted as the feature vectors, and the scale of the random subspace ensemble with cross-validation is adaptively chosen, and the EEG classification is realized by using linear discriminant analysis (LDA) classifiers ensemble. The test results show that the accuracy of the multi-domain features and …
The Expansion From System Simulation To Domain Simulation,
2020
1. College of Systems Engineering, National University of Defense Technology, Changsha 410073, China; ;2. The PLA's 31002 Unit, Beijing 100094, China;
The Expansion From System Simulation To Domain Simulation, Xiaogang Qiu, Yazhou Chen, Zhang Peng
Journal of System Simulation
Abstract: With the generalization of simulation application and complex system simulation becoming the focus, domain simulation is becoming more and more important. In 1995 United States Department of Defense (DoD) presented the master plan of modeling and simulation, which gives birth to the basic idea of domain simulation. The advances in information technology such as network technology and cloud computing help domain simulation to access to use. Taking the change of simulation research object as the basis, the development of simulation research from the aspects of model researches, simulation tools and simulation applications are summarized. The goal of domain simulation …
Review On Agv Scheduling Optimization,
2020
1. School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, China; ;
Review On Agv Scheduling Optimization, Jianlin Fu, Hengzhi Zhang, Zhang Jian, Liangkui Jiang
Journal of System Simulation
Abstract: AGV scheduling plays an important role in improving the efficiency and reducing manufacturing cost, but it is also a very complex combinatorial optimization procedure. AGV scheduling optimization is divided into three types, AGV static scheduling, AGV dynamic scheduling and AGV simultaneous scheduling with other resources scheduling. Various methods are summarized and listed, including traditional analysis method, modeling and simulation method, intelligent optimization algorithm and hybrid optimization method, and the advantages and disadvantages of each method are also analyzed. The deficiencies of AGV scheduling research are pointed out and the research directions for future are presented.
Evaluation On Geo-Registration Accuracy Of Outdoor Augmented Reality,
2020
1. Institute of Geospatial Information, Information Engineering University, Zhengzhou 450001, China; ;2. 61618 Troops, Beijing 100094, China; ;
Evaluation On Geo-Registration Accuracy Of Outdoor Augmented Reality, Deng Chen, You Xiong, Meixia Zhi
Journal of System Simulation
Abstract: Geo-registration technology is a key technology for the combination of augmented reality and geographic information systems, and its registration accuracy has a significant impact on the availability of ARGIS. Aiming at this application, the basic concepts and principles of augmented reality geo-registration technology are analyzed, and the method for quantitative evaluation of geo-registration accuracy is proposed. Combined with the pre-acquired high-precision geographic information data, a variety of outdoor geo-registration experiments are carried out by using the different hardware devices, and the quantitative accuracy of different geo-registration methods is evaluated. The geo-registration errors and the problems existing in the practical …
Research On Recursive Variable Sampling Period Scheduling Algorithm Based On Two-Parameter Priority,
2020
College of Electrical and Information Engineering Dalian Jiaotong University, Dalian 116028, China;
Research On Recursive Variable Sampling Period Scheduling Algorithm Based On Two-Parameter Priority, Weiguo Shi, Xu Chao, Wang Xun, Xiangtai Wang
Journal of System Simulation
Abstract: A recursive variable sampling periodic dynamic scheduling algorithm based on two-parameter priority is proposed for the resource-constrained network control system. The network demand degree and network urgency double parameter of the control loop are calculated, and the two-parameter weight is established by the two-square root mapping function which is created by the absolute value of the control loop error to realize the scheduling of the sensor priority. The comprehensive analysis of the control loop performance recursively adjusts the sampling period of each control loop, and completes the scheduling adjustment under the premise of ensuring the stability of the …
Finite Element Method Evaluation On Chest Blunt Injury By Rubber Projectile,
2020
College of Equipment Management and Support, Engineering University of People's Armed Police, Xi'an 710086, China;
Finite Element Method Evaluation On Chest Blunt Injury By Rubber Projectile, Wang Song, Renjun Zhan, Xiongyi Duan
Journal of System Simulation
Abstract: In order to reveal the non-lethal injury mechanism of rubber projectile and improve its safety service level, the 18.4 mm rubber projectile finite element model and the improved chest blunt injury assessment model are constructed and verified. The virtual impact test experiments under different loads are carried out, and the stress-time response and deformation-time response data are obtained. The results show that the time to reach the peak stress (less than 0.2 ms) is much shorter than the time to reach the maximum deformation variable (4~5 ms), which means the damage is not caused by the impact itself …
Simulation Analysis On Penetration To Aircraft Carrier Of Image Homing Rocket,
2020
Artillery and Air Defense Academy of PLA, Hefei 230031, China;
Simulation Analysis On Penetration To Aircraft Carrier Of Image Homing Rocket, Shidong Fang, Chen Dong, Quanli Ning, Zhang Jie, Li Yong
Journal of System Simulation
Abstract: The effect of image homing rocket projectile penetrating aircraft carrier is the important basis for its operation. According to the characteristics of projectile and aircraft carrier, the geometric equivalent model and simulation model are established, and the penetration process is simulated by LS-DYNA. Simulation results are verified by the failure form and penetration limit velocity, and show the correctness of the model. Using the established models, the penetration processes are simulated under the different conditions. The overall force on the projectile is analyzed according to the extreme acceleration value of projectile. Based on the analysis of some collected key …
Simulation On Vehicles Mandatory Lane Changing And Merging Process In Case Of Road Bottleneck,
2020
1. China Research Center for Emergency Management, Wuhan University of Technology, Wuhan 430070, China; ;2. School of Safety Science and Emergency Management, Wuhan University of Technology, Wuhan 430070, China;
Simulation On Vehicles Mandatory Lane Changing And Merging Process In Case Of Road Bottleneck, Lü Wei, Feizhou Huo
Journal of System Simulation
Abstract: A microscopic dynamic traffic flow model based on vehicle's mandatory lane changing behavior is established. Under the condition of road bottleneck, three macroscopic traffic flow characteristics of traffic flow, lane speed distribution and space-time diagram, and two microscopic traffic flow characteristics of merging distance and vehicle's travel time are analyzed. The simulation results show that, the total flow of arbitrary cross section of the bottleneck road can represent the overall traffic capacity, and the road bottleneck can reduce the total traffic flow by 10% to 35%, and cause a delay of 17% to 42% to the vehicle travel time …
Operation Loss Reduction Control For Large-Scale Wind Farm Based On Hybrid Modeling Simulation,
2020
Department of control and computer engineering, North China Electric Power University, Beijing 102206, China;
Operation Loss Reduction Control For Large-Scale Wind Farm Based On Hybrid Modeling Simulation, Yunqi Xiao, Wang Yi
Journal of System Simulation
Abstract: Due to the large number of transformers and collection lines in large-scale wind farms, the losses of collecting system is serious in actual operation. A reactive power/voltage control strategy is proposed, which takes wind turbines as the distributed reactive power sources to optimize the power flow in wind farm and reduce the overall losses of collector system. To improve the efficiency of wind farm modeling and multi-scene loss reduction simulation, a hybrid modeling and simulation scheme based on combining object model configuration and control algorithm programming is proposed. The wind farm model consists of module configuration, and can be …
Delay Model Of Vehicles At Urban Road Drop-Off Area,
2020
1. Beijing advanced innovation center for future urban design, Beijing University of Civil Engineering and Architecture, Beijing 100044, China; ;
Delay Model Of Vehicles At Urban Road Drop-Off Area, Lifan Zhang, Pengpeng Jiao, Mingkai Si
Journal of System Simulation
Abstract: A model for calculating the delay of the drop-off vehicles at urban road drop-off area is proposed. The traffic organization modes of the independent drop-off area and the road drop-off area are analysed. The “queue up to drop off” mode process is divided into two stages, a delay model of drop-off vehicle based on queuing theory and gap theory is established, and an optimization algorithm is presented. Taking the entrance section of Anzhen Hospital in Beijing as the test object, the model is tested by VISSIM simulation software and real survey data. The influence of drop-off rate and drop-off …
Design Of Fragment Warhead Simulation System Based On Mvc Distributed Framework,
2020
1. School of Artificial Intelligence, Nanjing Vocational College of Information Technology, Nanjing 210043, China; ;2. School of Energy and Power Engineering, Nanjing University of Science and Technology, Nanjing 210094, China;
Design Of Fragment Warhead Simulation System Based On Mvc Distributed Framework, He Miao, Wang Hao, Huang Yong, Xue Shao, Yinqing Shen
Journal of System Simulation
Abstract: Numerical computation and visualization simulation are carried out for the whole physical process from the explosion of warhead to the fragments impacting target. The whole system is designed and implemented by using MVC architecture, Framework component library and JSON data format computer software technology, which make the system scalable, cross-platform and easy to maintain. The distributed computing architecture is designed according to the high computation, large data volume and multi-user concurrency in user scenarios. The simulation experiment results show that the distributed simulation of the system can satisfy the concurrent needs of multi-users, and the visual simulation effect …
Research On Geographical Battlefield Environment Model Facing Autonomous Platform,
2020
Institute of Geographical Spatial Information, Information Engineering University, Zhengzhou 450001, China;
Research On Geographical Battlefield Environment Model Facing Autonomous Platform, You Xiong, Jiangpeng Tian
Journal of System Simulation
Abstract: Battlefield environment model is an abstraction and description of the complex battlefield environment for specific needs. It supports the research and application of the nature and evolution of the battlefield environment. However, the existing battlefield environment model is mainly oriented to human war activities to describe the battlefield environment,and lacks the design for unmanned autonomous platforms. A multi-level battlefield environment model structure which couples the advantages of humans and machines is proposed, which can give full play to the machine's rapid numerical calculation capabilities at the geometric and feature levels, as well as human cognitive experience at the element, …
Design And Simulation On Autonomous Landing Of A Quad Tilt Rotor,
2020
1. School of Navigation, Wuhan University of Technology, Wuhan 430063, China; ;2. Intelligent Transportation Systems Research Center, Wuhan 430063, China; ;3. National Engineering Research Center for Water Transport Safety, Wuhan 430063, China; ;
Design And Simulation On Autonomous Landing Of A Quad Tilt Rotor, Supu Xiu, Yuanqiao Wen, Changshi Xiao, Haiwen Yuan, Wenqiang Zhan
Journal of System Simulation
Abstract: Aiming at the under-actuation of general quadrotors, a novel quad tilt rotor model is proposed. The model decouples the y-direction translation and roll rotation of a quadrotor by the four servos used respectively for the tilting control of the four propellers to realized the tilt hover and tilt flight of the UAV, the UAV can keep a tilt attitude which increases the maneuverability and the precise pose position and attitude control of the tilt UAV and ensures a good performance on the trajectory tracking and landing. A 5-degree polynomial optimization is used in UAV trajectory planning for the strong …
Numerical Research On Ballistic Limit Of Whipple Shield In High-Velocity Range,
2020
Beijing Institute of Mechanical Equipment, Beijing 100854, China;
Numerical Research On Ballistic Limit Of Whipple Shield In High-Velocity Range, Yixiao Li, Shengjie Wang
Journal of System Simulation
Abstract: Limited by the acceleration ability of two-stage light gas guns, few hypervelocity impact experiment of Whipple shield with projectile speed higher than 8 km/s has been performed. The ballistic limit equations can't fully describe the protection ability of Whipple shield in high-velocity range because of the lack of experimental data. GRAY three-phase equation of state is used in the material point method calculation program to simulate the penetration of thick target plate and the high-velocity impact of Whipple shield. The numerical result of Whipple shield ballistic limit shows that the ballistic limit in high-velocity range is higher than the …
