摘要 :
This paper analyzes the influence different disease control and prevention strategies on the out- break of COVID-19 in a susceptible-infected-quarantined-recovered-died (SIQDR) model. This paper builds a continuous dynamical syste...
展开
This paper analyzes the influence different disease control and prevention strategies on the out- break of COVID-19 in a susceptible-infected-quarantined-recovered-died (SIQDR) model. This paper builds a continuous dynamical system model and a discrete Monte Carlo model to simulate the spread of COVID-19. This paper discusses how different control and prevention policies affect the spread of COVID-19. Besides, this paper also measures the impact of different policies on the economy to help the government choose a more appropriate policy.
收起
摘要 :
The growing availability of the data collected from smart manufacturing is changing the paradigms of production monitoring and control. The increasing complexity and content of the wafer manufacturing process in addition to the ti...
展开
The growing availability of the data collected from smart manufacturing is changing the paradigms of production monitoring and control. The increasing complexity and content of the wafer manufacturing process in addition to the time-varying unexpected disturbances and uncertainties, make it infeasible to do the control process with model-based approaches. As a result, data-driven soft-sensing modeling has become more prevalent in wafer process diagnostics. Recently, deep learning has been utilized in soft sensing system with promising performance on highly nonlinear and dynamic time-series data. Despite its successes in soft-sensing systems, however, the underlying logic of the deep learning framework is hard to understand. In this paper, we propose a deep learning-based model for defective wafer detection using a highly imbalanced dataset. To understand how the proposed model works, the deep visualization approach is applied. Additionally, the model is then fine-tuned guided by the deep visualization. Extensive experiments are performed to validate the effectiveness of the proposed system. The results provide an interpretation of how the model works and an instructive fine-tuning method based on the interpretation.
收起
摘要 :
The growing availability of the data collected from smart manufacturing is changing the paradigms of production monitoring and control. The increasing complexity and content of the wafer manufacturing process in addition to the ti...
展开
The growing availability of the data collected from smart manufacturing is changing the paradigms of production monitoring and control. The increasing complexity and content of the wafer manufacturing process in addition to the time-varying unexpected disturbances and uncertainties, make it infeasible to do the control process with model-based approaches. As a result, data-driven soft-sensing modeling has become more prevalent in wafer process diagnostics. Recently, deep learning has been utilized in soft sensing system with promising performance on highly nonlinear and dynamic time-series data. Despite its successes in soft-sensing systems, however, the underlying logic of the deep learning framework is hard to understand. In this paper, we propose a deep learning-based model for defective wafer detection using a highly imbalanced dataset. To understand how the proposed model works, the deep visualization approach is applied. Additionally, the model is then fine-tuned guided by the deep visualization. Extensive experiments are performed to validate the effectiveness of the proposed system. The results provide an interpretation of how the model works and an instructive fine-tuning method based on the interpretation.
收起
摘要 :
As the most important capital market, how formulating a reasonable stock trading strategy to improve capital return and reduce trading risk has always been the focus of people’s attention. In recent years, with the development of...
展开
As the most important capital market, how formulating a reasonable stock trading strategy to improve capital return and reduce trading risk has always been the focus of people’s attention. In recent years, with the development of data-driven AI technology, people have begun to try to apply it to stock market data analysis to minimize the trading risk caused by the uncertainty of price fluctuations in the stock market. Accordingly, in this paper, we solve the complex stock trading decision-making problem by exploiting the deep reinforcement learning techniques. Briefly, in this paper, we consider two trading models: 1) for trading a specific single blue chip stock, we design a new trading agent based on Double Deep Q-Network (DDQN) to maximize the return for such specific blue chip stock purchase and sale; 2) To further reduce the risk of stock trading, for the more common multi-stock trading scenarios, we utilize twin-delayed deep deterministic policy gradient (TD3) technique to design a multi-stock collaborative trading agent for achieving the goals of risk hedging and maximizing returns. We further evaluated the efficiency of the proposed trading agents in stock price prediction accuracy and returns based on the actual U.S. Stock Market data.
收起
摘要 :
In recent years, data-driven and AI-based intelligent transportation systems have been greatly developed to alleviate the public's concern about the increasingly severe traffic congestion and traffic safety issues. For supporting ...
展开
In recent years, data-driven and AI-based intelligent transportation systems have been greatly developed to alleviate the public's concern about the increasingly severe traffic congestion and traffic safety issues. For supporting various safety-related ITS applications, vehicular edge computing (VEC) has been proposed as a promising technology that can effectively provide computing power and storage capacity support for vehicles in close proximity. However, in the face of the instability of communication between vehicles and other devices caused by the high-speed motion of vehicles and the complex relative motion between vehicles, how to effectively realize the relatively stable arithmetic power sharing between vehicles and edge computing devices is a critical problem that must be solved to realize VEC. Therefore, in this paper, we propose a distributed online offloading method, called Candidate Utilization-based Deep Reinforcement Learning (CU-DRL) algorithm, by exploiting the deep reinforcement learning technique. We further evaluate and demonstrate the effectiveness and correctness of the proposed CU-DRL model through simulations.
收起
摘要 :
The cryptocurrency market has been growing rapidly in recent years. The volume of transactions and the number of participants in the cryptocurrency market makes it huge enough that we cannot ignore it. At the same time, the global...
展开
The cryptocurrency market has been growing rapidly in recent years. The volume of transactions and the number of participants in the cryptocurrency market makes it huge enough that we cannot ignore it. At the same time, the global stock market has also reached a new height in the past two years. However, due to the COVID epidemic and other political and economic-related factors in the last two years, the uncertainty in the capital market remains high, and short-term large fluctuations occur frequently; thus, many investors have suffered substantial losses. Pairs trading, an advanced statistical arbitrage method, is believed to hedge the risk and profit off the market regardless of market condition. Amongst the vast literature on pairs trading, there have been investors trading a pair of cryptocurrencies or a pair of stocks using machine learning or empirical methods. This research probes the boundary of utilizing machine learning methods to do pairs trading with one stock asset and another cryptocurrency. Briefly, we built an assets pool with both stocks and cryptocurrencies to find the best trading pair. In addition, we applied mainstream machine learning models to the trading strategy. We finally evaluated the accuracy of the proposed method in prediction and compared their returns based on the actual U.S. Stock and Cryptocurrency Market data. The test results show that our method outperforms other state-of-the-art methods.
收起
摘要 :
SUMMARY & CONCLUSIONSThis paper presents a review of the stochastic modeling approaches in the literature for representing the phase-dependent behavior and quantitatively analyzing the dependability attributes of class of systems known as phased-mission systems (PMS, hereafter).The operational life (or mission) of a PMS can be split into a sequence of phases, each characterized by a specific workload, configuration, and operating conditions. Several dependability critical systems, such as aircraft control systems, missile flight systems and space probe navigation systems, exhibit phased-mission structures. Hence, their dependability modeling and evaluation is of utter relevance. However, PMSs offer several challenges to the modeling and quantitative analysis of dependability attributes, as their dynamic aspects can easily stretch the ability of classical modeling approaches. Because of it, researchers and practitioners in the field of dependability modelling and evaluation have devoted substantial effort to the definition of approaches that can accommodate phase-dependent behaviors of systems.The inherent complexity of PMSs has been managed resorting to combinatorial modeling methods, such as fault-trees, reliability diagrams and binary decision diagrams, as well as state-based representations such as Markov chains and Petri nets. Distinct approaches have been applied to represent the randomness of failure/repair event occurrence times, the possible uncertainty associated with phase ordering and duration, and the dependence that may exist between the residual lifetimes of system components in subsequent phases.As a result, a rich repertoire of proposed techniques is now available, which received contributions from many different research groups and integrated diverse approaches combining them in original ways. In the paper, we will explore these approaches and techniques, describing the challenges that drove the study of this class of complex systems and the outcomes of this yet unfinished research effort....
展开
SUMMARY & CONCLUSIONSThis paper presents a review of the stochastic modeling approaches in the literature for representing the phase-dependent behavior and quantitatively analyzing the dependability attributes of class of systems known as phased-mission systems (PMS, hereafter).The operational life (or mission) of a PMS can be split into a sequence of phases, each characterized by a specific workload, configuration, and operating conditions. Several dependability critical systems, such as aircraft control systems, missile flight systems and space probe navigation systems, exhibit phased-mission structures. Hence, their dependability modeling and evaluation is of utter relevance. However, PMSs offer several challenges to the modeling and quantitative analysis of dependability attributes, as their dynamic aspects can easily stretch the ability of classical modeling approaches. Because of it, researchers and practitioners in the field of dependability modelling and evaluation have devoted substantial effort to the definition of approaches that can accommodate phase-dependent behaviors of systems.The inherent complexity of PMSs has been managed resorting to combinatorial modeling methods, such as fault-trees, reliability diagrams and binary decision diagrams, as well as state-based representations such as Markov chains and Petri nets. Distinct approaches have been applied to represent the randomness of failure/repair event occurrence times, the possible uncertainty associated with phase ordering and duration, and the dependence that may exist between the residual lifetimes of system components in subsequent phases.As a result, a rich repertoire of proposed techniques is now available, which received contributions from many different research groups and integrated diverse approaches combining them in original ways. In the paper, we will explore these approaches and techniques, describing the challenges that drove the study of this class of complex systems and the outcomes of this yet unfinished research effort.
收起
摘要 :
SUMMARY & CONCLUSIONSThis paper presents a review of the stochastic modeling approaches in the literature for representing the phase-dependent behavior and quantitatively analyzing the dependability attributes of class of systems known as phased-mission systems (PMS, hereafter).The operational life (or mission) of a PMS can be split into a sequence of phases, each characterized by a specific workload, configuration, and operating conditions. Several dependability critical systems, such as aircraft control systems, missile flight systems and space probe navigation systems, exhibit phased-mission structures. Hence, their dependability modeling and evaluation is of utter relevance. However, PMSs offer several challenges to the modeling and quantitative analysis of dependability attributes, as their dynamic aspects can easily stretch the ability of classical modeling approaches. Because of it, researchers and practitioners in the field of dependability modelling and evaluation have devoted substantial effort to the definition of approaches that can accommodate phase-dependent behaviors of systems.The inherent complexity of PMSs has been managed resorting to combinatorial modeling methods, such as fault-trees, reliability diagrams and binary decision diagrams, as well as state-based representations such as Markov chains and Petri nets. Distinct approaches have been applied to represent the randomness of failure/repair event occurrence times, the possible uncertainty associated with phase ordering and duration, and the dependence that may exist between the residual lifetimes of system components in subsequent phases.As a result, a rich repertoire of proposed techniques is now available, which received contributions from many different research groups and integrated diverse approaches combining them in original ways. In the paper, we will explore these approaches and techniques, describing the challenges that drove the study of this class of complex systems and the outcomes of this yet unfinished research effort....
展开
SUMMARY & CONCLUSIONSThis paper presents a review of the stochastic modeling approaches in the literature for representing the phase-dependent behavior and quantitatively analyzing the dependability attributes of class of systems known as phased-mission systems (PMS, hereafter).The operational life (or mission) of a PMS can be split into a sequence of phases, each characterized by a specific workload, configuration, and operating conditions. Several dependability critical systems, such as aircraft control systems, missile flight systems and space probe navigation systems, exhibit phased-mission structures. Hence, their dependability modeling and evaluation is of utter relevance. However, PMSs offer several challenges to the modeling and quantitative analysis of dependability attributes, as their dynamic aspects can easily stretch the ability of classical modeling approaches. Because of it, researchers and practitioners in the field of dependability modelling and evaluation have devoted substantial effort to the definition of approaches that can accommodate phase-dependent behaviors of systems.The inherent complexity of PMSs has been managed resorting to combinatorial modeling methods, such as fault-trees, reliability diagrams and binary decision diagrams, as well as state-based representations such as Markov chains and Petri nets. Distinct approaches have been applied to represent the randomness of failure/repair event occurrence times, the possible uncertainty associated with phase ordering and duration, and the dependence that may exist between the residual lifetimes of system components in subsequent phases.As a result, a rich repertoire of proposed techniques is now available, which received contributions from many different research groups and integrated diverse approaches combining them in original ways. In the paper, we will explore these approaches and techniques, describing the challenges that drove the study of this class of complex systems and the outcomes of this yet unfinished research effort.
收起
摘要 :
Disk and memory faults are the leading causes of server breakdown. A proactive solution is to predict such hardware failure at the runtime and then isolate the hardware at risk and backup the data. However, the current model-based...
展开
Disk and memory faults are the leading causes of server breakdown. A proactive solution is to predict such hardware failure at the runtime and then isolate the hardware at risk and backup the data. However, the current model-based predictors are incapable of using the discrete time-series data, such as the values of device attributes, which conveys high-level information of the device behavior. In this paper, we propose a novel deep-learning based prediction scheme for system-level hardware failure prediction. We normalize the distribution of samples’ attributes from different vendors to make use of diverse training sets. We propose a temporal Convolution Neural Network based model that is insensitive to the noise in the time dimension. Finally, we design a loss function to train the model with extremely imbalanced samples effectively. Experimental results from an open S.M.A.R.T data set and an industrial data set show the effectiveness of the proposed scheme.
收起
摘要 :
Disk and memory faults are the leading causes of server breakdown. A proactive solution is to predict such hardware failure at the runtime and then isolate the hardware at risk and backup the data. However, the current model-based...
展开
Disk and memory faults are the leading causes of server breakdown. A proactive solution is to predict such hardware failure at the runtime and then isolate the hardware at risk and backup the data. However, the current model-based predictors are incapable of using the discrete time-series data, such as the values of device attributes, which conveys high-level information of the device behavior. In this paper, we propose a novel deep-learning based prediction scheme for system-level hardware failure prediction. We normalize the distribution of samples’ attributes from different vendors to make use of diverse training sets. We propose a temporal Convolution Neural Network based model that is insensitive to the noise in the time dimension. Finally, we design a loss function to train the model with extremely imbalanced samples effectively. Experimental results from an open S.M.A.R.T data set and an industrial data set show the effectiveness of the proposed scheme.
收起