Multivariate time series prediction is still playing an important role in many fields such as finance, transportation and energy. It is still a challenging work to make long-term prediction of multivariate time series...
详细信息
ISBN:
(纸本)9781450385053
Multivariate time series prediction is still playing an important role in many fields such as finance, transportation and energy. It is still a challenging work to make long-term prediction of multivariate time series. the existing traditional methods based on statistics have a good prediction effect for the periodic data, but they can not capture the complex dependence between multiple time series and the prediction of long term. In this paper, we propose a new deep learning framework for complex sequence prediction based on multi-stage attentions, especially dynamic and non-periodic time series. MulRNN (Multi-Stage-Attention-RNN) uses convolutional neural network (CNN) and recurrent neural network (RNN) to extract short-term locally dependent patterns between variables, and introduces attention mechanisms to discover long-term patterns of time series. In addition, we use the traditional autoregressive model to solve the scale insensitivity problem of the neural network. Finally, we validate our proposed model on financial and energy datasets, and our method (MulRNN) achieves significant performance improvements over several advanced baseline methods in terms of time series prediction.
Trial and error learning is an approach with uncertain consequences. How to maintain policy security, stability, and efficiency under controlled circumstances, posing a significant academic challenge. Such as Reinforc...
详细信息
American scientist Adelman first used DNA molecules to solve the NP-complete problem, thus creating a new research field. As an advanced interdisciplinary subject, it has attracted many scholars because of its high pa...
详细信息
Convolutional neural networks based regional proposal networks (RPN) have recently achieved breakthrough results in a variety of medical image detection tasks. Among them, 3D RPN network in conjunction with advanced R...
详细信息
Mobile crowdsensing (MCS) is a human-driven sensing paradigm that empowers ordinary citizens to use their mobile devices and become active observers of the environment. Due to the large number of devices participating...
详细信息
ISBN:
(纸本)9781538678107
Mobile crowdsensing (MCS) is a human-driven sensing paradigm that empowers ordinary citizens to use their mobile devices and become active observers of the environment. Due to the large number of devices participating in MCS tasks, MCS services generate a huge amount of data which needs to be transmitted over the network, while the inherent mobility of users can quickly make information obsolete, and requires efficient data processing. Since the traditional cloud-based architecture may increase the data propagation latency and network traffic, novel solutions are needed to optimize the amount of data which is transmitted over the network. In our previous work we have shown that edge computing is a promising technology to decentralize MCS services and reduce the complexity of data processing by moving computation in the proximity of mobile users. In this paper, we introduce a novel approach to reduce the amount of redundant data in the hierarchical edge-based MCS ecosystem. In particular, we propose the usage of Bloom filter data structure on mobile devices and edge servers to enable users participating in MCS tasks to make autonomous informed decisions on whether to contribute data to the edge servers or not. Bloom filter proves to be an efficient technique to obviate redundant sensor activity on collocated mobile devices, reduce the complexity of data processing and network traffic, while in the same time gives useful indication whether MCS data is valuable at a certain location and point in time. We evaluate Bloom filter with respect to filter size and probability of false positives, and analyze the number of lost data readings in relation to expected number of different elements. Our analysis shows that both filter size and error rate are sufficiently small to be used in MCS.
Provides an abstract for each of the tutorial presentations and may include a brief professional biography of each presenter. the complete presentations were not made available for publication as part of the conferenc...
详细信息
Provides an abstract for each of the tutorial presentations and may include a brief professional biography of each presenter. the complete presentations were not made available for publication as part of the conference proceedings.
the amount of data output from a computer simulation has grown to terabytes and petabytes as increasingly complex simulations are being run on massively-parallel systems. As we approach exa-flop computing in the next ...
详细信息
ISBN:
(纸本)9781509050048
the amount of data output from a computer simulation has grown to terabytes and petabytes as increasingly complex simulations are being run on massively-parallel systems. As we approach exa-flop computing in the next decade, it is expected that the I/O subsystem will not be able to write out these large volumes of data. In this paper, we explore the use of machine learning to compress the data before it is written out. Despite the computational constraints that limit us to using very simple learning algorithms, our results show that machine learning is a viable option for compressing unstructured data. Further, by using a better sampling algorithm to generate the training set, we can obtain more accurate results compared to random sampling, at no extra cost.
Presents the introductory welcome message from the conference proceedings. May include the conference officers' congratulations to all involved withthe conference event and publication of the proceedings record.
Presents the introductory welcome message from the conference proceedings. May include the conference officers' congratulations to all involved withthe conference event and publication of the proceedings record.
暂无评论