Artificial Intelligence and Robotics Commons^™

Generating Music With Sentiments, Chunhui Bao

Dissertations and Theses Collection (Open Access)

In this thesis, I focus on the music generation conditional on human sentiments such as positive and negative. As there are no existing large-scale music datasets annotated with sentiment labels, generating high-quality music conditioned on sentiments is hard. I thus build a new dataset consisting of the triplets of lyric, melody and sentiment, without requiring any manual annotations. I utilize an automated sentiment recognition model (based on the BERT trained on Edmonds Dance dataset) to "label'' the music according to the sentiments recognized from its lyrics. I then train the model of generating sentimental music and call the method Sentimental …

Artificial Intelligence As Augmenting Automation: Implications For Employment, F. Ted Tschang, Esteve Almirall

Research Collection Lee Kong Chian School Of Business

There has been great concern in recent years that artificial intelligence (AI) may cause widespread unemployment, but proponents say that AI augments existing jobs. Both of these positions have substance, but there is a need is to articulate the mechanisms by which AI may actually do both, and in the process, transform work and business organizations alike. We use economic studies showing past transformations automation wrought on the structure of employment and skills (such as the favouring of nonroutine skills) to articulate a ground for discussion. We then use case evidence of AI and automation to show how AI is …

Transfer-Learned Pruned Deep Convolutional Neural Networks For Efficient Plant Classification In Resource-Constrained Environments, Martinson Ofori

Masters Theses & Doctoral Dissertations

Traditional means of on-farm weed control mostly rely on manual labor. This process is time-consuming, costly, and contributes to major yield losses. Further, the conventional application of chemical weed control can be economically and environmentally inefficient. Site-specific weed management (SSWM) counteracts this by reducing the amount of chemical application with localized spraying of weed species. To solve this using computer vision, precision agriculture researchers have used remote sensing weed maps, but this has been largely ineffective for early season weed control due to problems such as solar reflectance and cloud cover in satellite imagery. With the current advances in artificial …

Predicting Anti-Asian Hateful Users On Twitter During Covid-19, Jisun An, Haewoon Kwak, Claire Seungeun Lee, Bogang Jun, Yong-Yeol Ahn

Research Collection School Of Computing and Information Systems

We investigate predictors of anti-Asian hate among Twitter users throughout COVID-19. With the rise of xenophobia and polarization that has accompanied widespread social media usage in many nations, online hate has become a major social issue, attracting many researchers. Here, we apply natural language processing techniques to characterize social media users who began to post anti-Asian hate messages during COVID-19. We compare two user groups—those who posted anti-Asian slurs and those who did not—with respect to a rich set of features measured with data prior to COVID-19 and show that it is possible to predict who later publicly posted anti-Asian …

Self-Supervised Multi-Class Pre-Training For Unsupervised Anomaly Detection And Segmentation In Medical Images, Yu Tian, Fengbei Liu, Guansong Pang, Yuanhong Chen, Yuyuan Liu, Johan W. Verjans, Rajvinder Singh

Research Collection School Of Computing and Information Systems

Unsupervised anomaly detection (UAD) that requires only normal (healthy) training images is an important tool for enabling the development of medical image analysis (MIA) applications, such as disease screening, since it is often difficult to collect and annotate abnormal (or disease) images in MIA. However, heavily relying on the normal images may cause the model training to overfit the normal class. Self-supervised pre-training is an effective solution to this problem. Unfortunately, current self-supervision methods adapted from computer vision are sub-optimal for MIA applications because they do not explore MIA domain knowledge for designing the pretext tasks or the training process. …

Towards Enriching Responses With Crowd-Sourced Knowledge For Task-Oriented Dialogue, Yingxu He, Lizi Liao, Zheng Zhang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Task-oriented dialogue agents are built to assist users in completing various tasks. Generating appropriate responses for satisfactory task completion is the ultimate goal. Hence, as a convenient and straightforward way, metrics such as success rate, inform rate etc., have been widely leveraged to evaluate the generated responses. However, beyond task completion, there are several other factors that largely affect user satisfaction, which remain under-explored. In this work, we focus on analyzing different agent behavior patterns that lead to higher user satisfaction scores. Based on the findings, we design a neural response generation model EnRG. It naturally combines the power of …

Learning Knowledge-Enriched Company Embeddings For Investment Management, Gary Ang, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Relationships between companies serve as key channels through which the effects of past stock price movements and news events propagate and influence future price movements. Such relationships can be implicitly found in knowledge bases or explicitly represented as knowledge graphs. In this paper, we propose KnowledgeEnriched Company Embedding (KECE), a novel multi-stage attentionbased dynamic network embedding model combining multimodal information of companies with knowledge from Wikipedia and knowledge graph relationships from Wikidata to generate company entity embeddings that can be applied to a variety of downstream investment management tasks. Experiments on an extensive set of real-world stock prices and news …

Span-Level Emotion Cause Analysis With Neural Sequence Tagging, Xiangju Li, Wei Gao, Shi Feng, Daling Wang, Shafiq Joty

Research Collection School Of Computing and Information Systems

This paper addresses the task of span-level emotion cause analysis (SECA). It is a finer-grained emotion cause analysis (ECA) task, which aims to identify the specific emotion cause span(s) behind certain emotions in text. In this paper, we formalize SECA as a sequence tagging task for which several variants of neural network-based sequence tagging models to extract specific emotion cause span(s) in the given context. These models combine different types of encoding and decoding approaches. Furthermore, to make our models more "emotionally sensitive'', we utilize the multi-head attention mechanism to enhance the representation of context. Experimental evaluations conducted on two …

Fleet Sizing And Allocation For On-Demand Last-Mile Transportation Systems, Karmel Shehadeh, Hai Wang, Peter Zhang

Research Collection School Of Computing and Information Systems

The last-mile problem refers to the provision of travel service from the nearest public transportation node to home or other destination. Last-Mile Transportation Systems (LMTS), which have recently emerged, provide on-demand shared transportation. In this paper, we investigate the fleet sizing and allocation problem for the on-demand LMTS. Specifically, we consider the perspective of a last-mile service provider who wants to determine the number of servicing vehicles to allocate to multiple last-mile service regions in a particular city. In each service region, passengers demanding last-mile services arrive in batches, and allocated vehicles deliver passengers to their final destinations. The passenger …

Stock Market Trend Forecasting Based On Multiple Textual Features: A Deep Learning Method, Zhenda Hu, Zhaoxia Wang, Seng-Beng Ho, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Stock market trend forecasting is a valuable and challenging research task for both industry and academia. In order to explore the influence of stock news information on the stock market trend, a textual embedding construction method is proposed to encode multiple textual features, including topic features, sentiment features, and semantic features extracted from stock news textual content. In addition, a deep learning method is designed by using financial data and multiple textual features obtained from multiple news textual embeddings for short-term stock market trend prediction. For evaluation, extensive experiments on real stock market data are conducted. The experimental results illustrate …

The Ratio Method: Addressing Complex Tort Liability In The Fourth Industrial Revolution, Harrison C. Margolin, Grant H. Frazier

St. Mary's Law Journal

Emerging technologies of the Fourth Industrial Revolution show fundamental promise for improving productivity and quality of life, though their misuse may also cause significant social disruption. For example, while artificial intelligence will be used to accelerate society’s processes, it may also displace millions of workers and arm cybercriminals with increasingly powerful hacking capabilities. Similarly, human gene editing shows promise for curing numerous diseases, but also raises significant concerns about adverse health consequences related to the corruption of human and pathogenic genomes.

In most instances, only specialists understand the growing intricacies of these novel technologies. As the complexity and speed of …

Generating Synthetic Training Data For Deep Learning-Based Uav Trajectory Prediction, Brendan T. Morris, Stefan Becker, Ronny Hug, Wolfgang Huebner, Michael Arens

Electrical & Computer Engineering Faculty Research

Deep learning-based models, such as recurrent neural networks (RNNs), have been applied to various sequence learning tasks with great success. Following this, these models are increasingly replacing classic approaches in object tracking applications for motion prediction. On the one hand, these models can capture complex object dynamics with less modeling required, but on the other hand, they depend on a large amount of training data for parameter tuning. Towards this end, we present an approach for generating synthetic trajectory data of unmanned-aerial-vehicles (UAVs) in image space. Since UAVs, or rather quadrotors are dynamical systems, they can not follow arbitrary trajectories. …

Modeling And Simulation Of Crowd Multi-Perception Behavior Model In Closed Public Places, Ma Jun, Hu Jun

Journal of System Simulation

Abstract: The social forces-based multi-agent modeling method is used to build the crowd simulation models in most of the existing crowd behavior simulation software systems. From the perspective of cognitive psychology, combined with the spatial logic model of the generalized influence of the crowd obtained by the author’s previous research, and based on the sigmoid function, the mathematical model of the individual visual and auditory perception of the crowd is constructed. Taking the typical subway transfer hall as an example, the objective function of large passenger volume evacuation optimization is established to construct the crowd evacuation simulation model. The simulation …

High Performance Simulation Method And Test Platform For Full Envelop Of Flight Vehicle, Jianlin Wang, Sufang Chen, Tie Ming, Liu Jing, Zhang Jun

Journal of System Simulation

Abstract: In order to meet the needs of the overall performance simulation and verification of the vehicle with large subsamples and massive states, a high-performance simulation method is proposed, in which a parallel simulation architecture based on high-performance computers is established, the technologies and software such as decoupling of simulation tasks, real-time monitoring of simulation, concurrent conflict control and automatic aggregation of large-scale test results are realized, and a test platform for the large-scale parallel verification of flight performance is developed. Simulation results show that the method has high acceleration ratio and scalability, and can complete the verification efficiently, …

Survey Of Evolutionary Behavior Tree Algorithm, Yang Jie, Zhang Qi, Junjie Zeng, Quanjun Yin

Journal of System Simulation

Abstract: Evolutionary behavior tree method is an agent behavior modeling method which uses evolutionary algorithm to generate and optimize behavior tree model. Based on the background knowledge of behavior tree and evolutionary algorithm, three kinds of evolutionary behavior tree algorithms based on genetic programming, grammar evolution and hybrid algorithm as well as corresponding improved algorithms are described, and the advantages and disadvantages of different algorithms are analyzed and compared. The specific applications of evolutionary behavior tree in combat simulation, game artificial intelligence, robotics and other fields are summarized. The future development trends of evolutionary behavior tree are proposed and discussed …

Research On Experimental Method Of Joint Operation Simulation Based On Human-Machine Hybrid Intelligence, Ma Jun, Jingyu Yang, Wu Xi

Journal of System Simulation

Abstract: In view of the difficulties that the joint operation simulation experiment methods are mainly for guiding equipment evaluation and demonstration, which is difficult to effectively support the research of operation problems, a joint operation simulation experiment method based on human-machine hybrid intelligence is proposed. The classification, generation and accumulation process of the knowledge in joint operation simulation experiment are clarified. Through the detailed descriptions of experimental interaction process, experimental operation process, experimental driving mode, simulation operation mode, supporting system structure, etc., a joint operation simulation experiment framework based on man-machine hybrid intelligence is constructed. It provides a new method …

Modeling And Simulation Of Car Following In Fog Based On Cellular Automata, Zhanhong Liu, Xiujian Yang, Xiangji Wu, Huang Zhen

Journal of System Simulation

Abstract: In order to ensure the safety of driving in foggy weather, a microscopic model of car following and lane changing traffic flow is established based on cellular automata. In view of the instability of car following state in foggy weather, dynamic random acceleration is introduced to segment modeling. The simulation accuracy is improved by refining cell size and cell step size and adding position update allowance. The relationship curves of speed and vehicle dispersion with time and the speed density diagram are obtained. The results show that: the vehicle speed fluctuates greatly in medium fog; the dispersion …

Three-Dimensional Visual Dynamic Simulation Of Rice Leaf Cells, Deheng Zhao, Yingding Zhao, Hongyun Yang, Wenlong Yi

Journal of System Simulation

Abstract: To explore the evolution process of rice leaf cell morphology with the help of computer visualization technology, it is necessary to establish the biomechanical relationship between the cell geometry model and its deformation. A dynamic simulation method is proposed for the 3D visualization of leaf cells based on the physical-mechanical properties, in which the cytoskeleton topology is represented by a "half-edge" data structure, and the surface geometries are constructed using a bicubic Bézier surface. The control parameters of a deformed surface are determined through "vertex", "edge" or "face" topological unit query algorithms of the cytoskeleton, and the cell stress-strain …

Dqn-Based Path Planning Method And Simulation For Submarine And Warship In Naval Battlefield, Xiaodong Huang, Haitao Yuan, Bi Jing, Liu Tao

Journal of System Simulation

Abstract: To realize multi-agent intelligent planning and target tracking in complex naval battlefield environment, the work focuses on agents (submarine or warship), and proposes a simulation method based on reinforcement learning algorithm called Deep Q Network (DQN). Two neural networks with the same structure and different parameters are designed to update real and predicted Q values for the convergence of value functions. An ε-greedy algorithm is proposed to design an action selection mechanism, and a reward function is designed for the naval battlefield environment to increase the update velocity and generalization ability of Learning with Experience Replay (LER). Simulation results …

Virus Propagation And System Simulation Based On Cellular Automata Model, Lijuan Zhang, Fuchang Wang, Zhengang Li

Journal of System Simulation

Abstract: A susceptible-latent-infected-cured-immune virus spreading model is established according to the characteristics of epidemic transmission and the actual urban spatial map model. Individuals in the environment are regarded as agents, and the spreading mechanism is established according to the principle of cellular. The effects of different strategies and different characteristics of virus spreading on epidemic have been studied. The role and effect of important factors on epidemic prevention and control method are discussed, and the model is validated taking Shijiazhuang epidemic as an example . The results show that the number of initial latent, the infectivity of disease, vaccination proportion …