scholarly journals Dynamic Item Block and Prediction Enhancing Block for Sequential Recommendation

2019 ◽  
Author(s):  
Guibing Guo ◽  
Shichang Ouyang ◽  
Xiaodong He ◽  
Fajie Yuan ◽  
Xiaohua Liu
Keyword(s):  
Multiple Scales ◽  
Building Blocks ◽  
User Preferences ◽  
Inner Product ◽  
Time Step ◽  
Multi Scale ◽  
Basic Model ◽  
Single Scale ◽  
Series Of Experiments ◽  
Item Representation

Sequential recommendation systems have become a research hotpot recently to suggest users with the next item of interest (to interact with). However, existing approaches suffer from two limitations: (1) The representation of an item is relatively static and fixed for all users. We argue that even a same item should be represented distinctively with respect to different users and time steps. (2) The generation of a prediction for a user over an item is computed in a single scale (e.g., by their inner product), ignoring the nature of multi-scale user preferences. To resolve these issues, in this paper we propose two enhancing building blocks for sequential recommendation. Specifically, we devise a Dynamic Item Block (DIB) to learn dynamic item representation by aggregating the embeddings of those who rated the same item before that time step. Then, we come up with a Prediction Enhancing Block (PEB) to project user representation into multiple scales, based on which many predictions can be made and attentively aggregated for enhanced learning. Each prediction is generated by a softmax over a sampled itemset rather than the whole item space for efficiency. We conduct a series of experiments on four real datasets, and show that even a basic model can be greatly enhanced with the involvement of DIB and PEB in terms of ranking accuracy. The code and datasets can be obtained from https://github.com/ouououououou/DIB-PEB-Sequential-RS

scholarly journals Time-Aware Multi-Scale RNNs for Time Series Modeling

2021 ◽  
Author(s):  
Zipeng Chen ◽  
Qianli Ma ◽  
Zhenxi Lin
Keyword(s):  
Time Series ◽  
Time Series Data ◽  
Multiple Scales ◽  
Multivariate Time Series ◽  
Human Motion ◽  
Series Data ◽  
Time Step ◽  
Multi Scale ◽  
Important Time ◽  
Time Aware

Multi-scale information is crucial for modeling time series. Although most existing methods consider multiple scales in the time-series data, they assume all kinds of scales are equally important for each sample, making them unable to capture the dynamic temporal patterns of time series. To this end, we propose Time-Aware Multi-Scale Recurrent Neural Networks (TAMS-RNNs), which disentangle representations of different scales and adaptively select the most important scale for each sample at each time step. First, the hidden state of the RNN is disentangled into multiple independently updated small hidden states, which use different update frequencies to model time-series multi-scale information. Then, at each time step, the temporal context information is used to modulate the features of different scales, selecting the most important time-series scale. Therefore, the proposed model can capture the multi-scale information for each time series at each time step adaptively. Extensive experiments demonstrate that the model outperforms state-of-the-art methods on multivariate time series classification and human motion prediction tasks. Furthermore, visualized analysis on music genre recognition verifies the effectiveness of the model.

Multi-Scale Classification Based on Remote Sensing

2014 ◽  
Vol 580-583 ◽  
pp. 2853-2859
Author(s):  
Peng Li Li ◽  
Wei Ping Ti ◽  
Jia Chun Li
Keyword(s):  
Remote Sensing ◽  
Multiple Scales ◽  
Know How ◽  
Multi Scale ◽  
Single Scale ◽  
The Difference ◽  
Feature Values ◽  
Nearest Neighbour Classifier ◽  
Scale Classification

Due to the broadly application of remote sensing imagery, there is an eager need for the classification of objects in the images. The multi-scale classification based on object oriented analysis is not a usual approach for image classification because the users of multi-scale classification do not know how to use the information from multiple scales to do multi-scale classification. Many users rely on some easily accessible tools. nearest neighbour classifier, to do multi-scale classification. The multi-scale classification classifies the images from different scales. The feature values of the object vary from different scales and they may have some trends against scales. These trends may help us to understand multi-scale classification better. This is the scale dependency of features. The difference between multi-scale classification and single-scale classification is not only multiple scales, but also the use of information from different scales. In order to explore the connection between different scales, the research of new features is necessary.

A Taxonomic Analysis of Perspectives in Generating Space-Time Research Questions in Environmental Sciences

2016 ◽  
Vol 7 (2) ◽  
pp. 50-60 ◽  
Author(s):  
Xinyue Ye ◽  
Bing She ◽  
Huanyang Zhao ◽  
Xiaoyan Zhou
Keyword(s):  
Environmental Science ◽  
Multiple Scales ◽  
Global Scale ◽  
Space Time ◽  
Three Dimensions ◽  
Workflow Systems ◽  
Multi Scale ◽  
Taxonomic Analysis ◽  
Single Scale ◽  
Research Questions

Research questions in environment science can be decomposed into three basic dimensions: space, time and statistics. The combinations of these three dimensions reflect the diverse perspectives of observations across multiple scales. One can classify these scales into four types: individual, local, meso, and global. Following this multi-dimensional and multi-scale framework, this paper conducts a taxonomic analysis that systematically classifies research questions in environmental science. This taxonomic analysis includes papers from a leading environmental science journal. The results show that the majority of research questions are directed at local and global scale analyses. Studies that incorporate many scales of analysis are not necessarily more sophisticated than studies that investigate a single scale. Nonetheless, it's beneficial to explore more possibilities by investigating data at different perspectives. This taxonomy could help generating research questions and providing guidance for building analytic workflow systems to fill the gaps in future scientific endeavors.

Multi-Scale Shapelets Discovery for Time-Series Classification

2020 ◽  
Vol 19 (03) ◽  
pp. 721-739
Author(s):  
Borui Cai ◽  
Guangyan Huang ◽  
Yong Xiang ◽  
Maia Angelova ◽  
Limin Guo ◽  
...  
Keyword(s):  
Time Series ◽  
Classification Accuracy ◽  
Multiple Scales ◽  
Quality Measurement ◽  
Time Series Classification ◽  
High Quality ◽  
Major Task ◽  
Multi Scale ◽  
Single Scale ◽  
Local Patterns

Shapelets are subsequences of time-series that represent local patterns and can improve the accuracy and the interpretability of time-series classification. The major task of time-series classification using shapelets is to discover high quality shapelets. However, this is challenging since local patterns may have various scales/lengths rather than a unified scale. In this paper, we resolve this problem by discovering shapelets with multiple scales. We propose a novel Multi-Scale Shapelet Discovery (MSSD) algorithm to discover expressive multi-scale shapelets by extending initial single-scale shapelets (i.e., shapelets with a unified scale). MSSD adopts a bi-directional extension process and is robust to extend single-shapelets obtained by different methods. A supervised shapelet quality measurement is further developed to qualify the extension of shapelets. Comprehensive experiments conducted on 25 UCR time-series datasets show that multi-scale shapelets discovered by MSSD improve classification accuracy by around 10% (in average), compared with single-scale shapelets discovered by counterpart methods.

scholarly journals A New Water Environmental Load and Allocation Modeling Framework at the Medium–Large Basin Scale

Water ◽  
2019 ◽  
Vol 11 (11) ◽  
pp. 2398
Author(s):  
Qiankun Liu ◽  
Jingang Jiang ◽  
Changwei Jing ◽  
Zhong Liu ◽  
Jiaguo Qi
Keyword(s):  
Local Governments ◽  
Multiple Scales ◽  
Economic Benefits ◽  
Modeling Framework ◽  
Analytic Hierarchy ◽  
Gini Coefficients ◽  
Multi Scale ◽  
Single Scale ◽  
Basin Scale ◽  
Waste Load

Waste load allocation (WLA), as a well-known total pollutant control strategy, is designed to distribute pollution responsibilities among polluters to alleviate environmental problems, but the current policy is unfair and limited to single scale or single pollution types. In this paper, a new, alternative, multi-scale, and multi-pollution WLA modeling framework was developed, with a goal of producing optimal and fair allocation quotas at multiple scales. The new WLA modeling framework integrates multi-constrained environmental Gini coefficients (EGCs) and Delphi-analytic hierarchy process (Delphi-AHP) optimization models to achieve the stated goal. The new WLA modeling framework was applied in a case study in the Xian-jiang watershed in Zhejiang Province, China, in order to test its validity and usefulness. The results, in comparison with existing practices by the local governments, suggest that the simulated pollutant load quota at the watershed scale is much fairer than the existing policies and even has some environmental economic benefits at the pollutant source scale. As the new WLA is a process-based modeling framework, it should be possible to adopt this approach in other similar geographic areas.

scholarly journals Predicting the Future with Multi-scale Successor Representations

2018 ◽  
Author(s):  
Ida Momennejad ◽  
Marc W. Howard
Keyword(s):  
Laplace Transform ◽  
Medial Temporal Lobe ◽  
Multiple Scales ◽  
Multi Scale ◽  
Neural Representations ◽  
Single Scale ◽  
Large Trees ◽  
The Future ◽  
The Laplace Transform ◽  
Common Principle

AbstractThe successor representation (SR) is a candidate principle for generalization in reinforcement learning, computational accounts of memory, and the structure of neural representations in the hippocampus. Given a sequence of states, the SR learns a predictive representation for every given state that encodes how often, on average, each upcoming state is expected to be visited, even if it is multiple steps ahead. A discount or scale parameter determines how many steps into the future SR’s generalizations reach, enabling rapid value computation, subgoal discovery, and flexible decision-making in large trees. However, SR with a single scale could discard information for predicting both the sequential order of and the distance between states, which are common problems in navigation for animals and artificial agents. Here we propose a solution: an ensemble of SRs with multiple scales. We show that the derivative of multi-scale SR can reconstruct both the sequence of expected future states and estimate distance to goal. This derivative can be computed linearly: we show that a multi-scale SR ensemble is the Laplace transform of future states, and the inverse of this Laplace transform is a biologically plausible linear estimation of the derivative. Multi-scale SR and its derivative could lead to a common principle for how the medial temporal lobe supports both map-based and vector-based navigation.

scholarly journals BIDIRECTIONAL MULTI-SCALE ATTENTION NETWORKS FOR SEMANTIC SEGMENTATION OF OBLIQUE UAV IMAGERY

2021 ◽  
Vol V-2-2021 ◽  
pp. 75-82
Author(s):  
Y. Lyu ◽  
G. Vosselman ◽  
G.-S. Xia ◽  
M. Y. Yang
Keyword(s):  
Multiple Scales ◽  
Semantic Segmentation ◽  
The Novel ◽  
Oblique View ◽  
Attention Networks ◽  
Multi Scale ◽  
Single Scale ◽  
Aerial Platforms ◽  
Oblique Images ◽  
Scale Variation

Abstract. Semantic segmentation for aerial platforms has been one of the fundamental scene understanding task for the earth observation. Most of the semantic segmentation research focused on scenes captured in nadir view, in which objects have relatively smaller scale variation compared with scenes captured in oblique view. The huge scale variation of objects in oblique images limits the performance of deep neural networks (DNN) that process images in a single scale fashion. In order to tackle the scale variation issue, in this paper, we propose the novel bidirectional multi-scale attention networks, which fuse features from multiple scales bidirectionally for more adaptive and effective feature extraction. The experiments are conducted on the UAVid2020 dataset and have shown the effectiveness of our method. Our model achieved the state-of-the-art (SOTA) result with a mean intersection over union (mIoU) score of 70.80%.

scholarly journals A Middleware-Based Approach for Multi-Scale Mobility Simulation

2021 ◽  
Vol 13 (2) ◽  
pp. 22
Author(s):  
Xavier Boulet ◽  
Mahdi Zargayouna ◽  
Gérard Scemama ◽  
Fabien Leurent
Keyword(s):  
Modeling And Simulation ◽  
Transportation Networks ◽  
External Control ◽  
Independent Mobility ◽  
Time Step ◽  
Time Representation ◽  
Multi Scale ◽  
Networks Analysis ◽  
Maximal Benefit ◽  
Do So

Modeling and simulation play an important role in transportation networks analysis. In the literature, authors have proposed many traffic and mobility simulations, with different features and corresponding to different contexts and objectives. They notably consider different scales of simulations. The scales refer to the represented entities, as well as to the space and the time representation of the transportation environment. However, we often need to represent different scales in the same simulation, for instance to represent a neighborhood interacting with a wider region. In this paper, we advocate for the reuse of existing simulations to build a new multi-scale simulation. To do so, we propose a middleware model to couple independent mobility simulations, working at different scales. We consider all the necessary processing and workflow to allow for a coherent orchestration of these simulations. We also propose a prototype implementation of the middleware. The results show that such a middleware is capable of creating a new multi-scale mobility simulation from existing ones, while minimizing the incoherence between them. They also suggest that, to have a maximal benefit from the middleware, existing mobility simulation platforms should allow for an external control of the simulations, allowing for executing a time step several times if necessary.

Multi-Scale Virtual Reality of Sintering

2007 ◽  
Vol 534-536 ◽  
pp. 573-576
Author(s):  
Eugene Olevsky
Keyword(s):  
Global Scale ◽  
Initial State ◽  
Model Framework ◽  
Time Step ◽  
Computational Framework ◽  
Multi Scale ◽  
Scale Modeling ◽  
History Of ◽  
On Line ◽  
Damage Criteria

The directions of further developments in the modeling of sintering are pointed out, including multi-scale modeling of sintering, on-line sintering damage criteria, particle agglomeration, sintering with phase transformations. A true multi-scale approach is applied for the development of a new meso-macro methodology for modeling of sintering. The developed macroscopic level computational framework envelopes the mesoscopic simulators. No closed forms of constitutive relationships are assumed for the parameters of the material. When a time-step of the calculations is finished for one macroscopic element, the mesostructures of the next element are restored from the initial state according to the history of loading. The model framework is able to predict the final dimensions of the sintered specimen on a global scale and identify the granular structure in any localized area for prediction of the material properties.

scholarly journals DCPNet: A Densely Connected Pyramid Network for Monocular Depth Estimation

Sensors ◽  
2021 ◽  
Vol 21 (20) ◽  
pp. 6780
Author(s):  
Zhitong Lai ◽  
Rui Tian ◽  
Zhiguo Wu ◽  
Nannan Ding ◽  
Linjian Sun ◽  
...  
Keyword(s):  
Multiple Scales ◽  
Feature Fusion ◽  
State Of The Art ◽  
Depth Estimation ◽  
Multi Scale ◽  
Pyramid Structure ◽  
Benchmark Datasets ◽  
The Common ◽  
Monocular Depth ◽  
Multiple Stages

Pyramid architecture is a useful strategy to fuse multi-scale features in deep monocular depth estimation approaches. However, most pyramid networks fuse features only within the adjacent stages in a pyramid structure. To take full advantage of the pyramid structure, inspired by the success of DenseNet, this paper presents DCPNet, a densely connected pyramid network that fuses multi-scale features from multiple stages of the pyramid structure. DCPNet not only performs feature fusion between the adjacent stages, but also non-adjacent stages. To fuse these features, we design a simple and effective dense connection module (DCM). In addition, we offer a new consideration of the common upscale operation in our approach. We believe DCPNet offers a more efficient way to fuse features from multiple scales in a pyramid-like network. We perform extensive experiments using both outdoor and indoor benchmark datasets (i.e., the KITTI and the NYU Depth V2 datasets) and DCPNet achieves the state-of-the-art results.

Sign in / Sign up

Export Citation Format

Share Document