A Sense Embedding of Deep Convolutional Neural Networks for Sentiment Classification

Cui, Zhijian; Shi, Xiaodong; Chen, Yidong; Guo, Yinmei

doi:10.14257/ijgdc.2016.9.11.06

Cited by 3 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Distance-based methods: DTW [4] ; Feature-based methods: TSBF [6] , BOSS [7] ; ensemble-based methods: PROP [12] , COTE [13] ; Neural network methods: FCN [17] , ResNet [22] , OS-CNN [26] ,…”

Section: Experiments Results and Analysismentioning

confidence: 99%

“…Fully convolutional network (FCN) [15] uses convolution layer to replace the last full connection layer of deep multilayer perceptron (MLP) [16] , and adds batch standardization layer and global pooling layer to prevent the network from over fitting, which enhance the feature extraction ability of the network. Based on convolutional neural network, multi-scale convolutional neural networks (MCNN) [17] performs identity mapping, smoothing and downsampling to extract the multi-scale features of time series data, respectively, and solve the problem of feature loss. However, its classification performance largely depends on the selection of super parameters and the quality of data preprocessing [18] [19] .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Long-Short-Term Memory Based on Adaptive Convolutional Network for Time Series Classification

2023

Neural Process Lett

View full text Add to dashboard Cite

Deep learning technology is the most effective method to solve time series classification tasks. The existing algorithms based on deep learning usually obtain features with fixed step convolution, so they cannot effectively extract and focus on important multi-scale features. Based on the complexity and long-term dependence of time series data, an end-to-end model called as Adaptive Convolutional Network Long-Short-Term Memory (ACN-LSTM) is proposed in this paper. This network is composed of two branches: long-short-term memory and adaptive convolution neural network. The LSTM uses memory cells and gate mechanism to control the transmission of sequence information and fully extract the correlation information of time series to enhance the discriminative power of the network. The ACN obtains the local characteristics of time series by stacking one-dimensional convolutional neural block. Then the multi-scale convolutional neural block is used to capture different scales of information, which is consist of concatenated convolutional layers with different kernel size.Meanwhile, in order to adaptively adjust the feature information between layers, an inter-layer adaptive channel feature adjustment mechanism is proposed. The ACN-LSTM not only fully extracts long-term time correlation information, but also fuses adaptively and pays attention to important multi-scale features to achieve more accurate classification results. The experiment results with 65 UCR standard datasets illustrate that the proposed ACN-LSTM achieves highest arithmetic mean rank and geometric mean rank, compared with other methods, which are 2.815 and 2.322, respectively, and also achieves the lowest mean error with 0.127, which indicates that ACN-LSTM is effective in univariate time series classification.

show abstract

Section: Experiments Results and Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Long-Short-Term Memory Based on Adaptive Convolutional Network for Time Series Classification

2023

Neural Process Lett

View full text Add to dashboard Cite

show abstract

“…Long short-term memory networks and convolutional neural networks have shown promise in modeling time series data. 23,[27][28][29][30] To exploit the favorable properties of both LSTMs and convolutional neural networks for time series, we used Conv-LSTM layers, conceptualized in 2015 by Shi et al 26 and successfully used by Rahman and Adjeroh. 23 This approach allows for a reduction in the number of LSTM time steps from 10 080 (ie, 1 time step for every minute) to 7 (ie, 1 time step for every day of the week).…”

Section: Convolutional-long Short-term Memory Model With Time Series ...mentioning

confidence: 99%

Association of Selective Serotonin Reuptake Inhibitor Use With Abnormal Physical Movement Patterns as Detected Using a Piezoelectric Accelerometer and Deep Learning in a Nationally Representative Sample of Noninstitutionalized Persons in the US

et al. 2022

View full text Add to dashboard Cite

IMPORTANCESelective serotonin reuptake inhibitors (SSRIs) are a common first-line treatment for some psychiatric disorders, including depression and anxiety; although they are generally well tolerated, SSRIs have known adverse effects, including movement problems, sleep disruption, and gastrointestinal problems (eg, nausea and upset stomach). No large-scale studies using naturalistic, longitudinal, objective data have validated physical activity findings, and actigraphy data are well suited to address this task. OBJECTIVES To evaluate whether differences in physical movement exist among individuals treated with SSRIs compared with control participants and to identify the unique features of the movement of patients treated with SSRIs. DESIGN, SETTING, AND PARTICIPANTS This cross-sectional study examines longitudinally collected wearable movement data within a cross-sectional sample of 7162 participants from the 2005-2006 National Health and Nutrition Examination Survey (NHANES), a nationally representative population-based sample of noninstitutionalized persons in the US having both medication information and passive movement data. Statistical analysis was performed from April 1, 2021, to February 1, 2022.EXPOSURES The use of SSRIs (sertraline hydrochloride, escitalopram oxalate, fluoxetine hydrochloride, paroxetine hydrochloride, and citalopram hydrobromide), as reported by participants interviewed by NNHANES personnel, was the primary exposure, measured as a binary variable (taking an SSRI vs not taking an SSRI). MAIN OUTCOMES AND MEASURESThe primary outcome was the intensity of body movement as recorded by a piezoelectric accelerometer worn on the right hip for more than 1 week. RESULTSOf the 7162 participants included in the study, the mean (SD) age was 33.7 (22.6) years, 266 (3.7%) were taking an SSRI, 3706 (51.7%) were female, 1934 (27.0%) were Black, 1823 (25.5%) were Mexican American, 210 (2.9%) were other Hispanic, 336 (4.7%) were other or multiracial, and 2859 (39.9%) were White (per the NHANES data collection protocol). A cross-validated, deep learning classifier was constructed that achieved fair performance predicting SSRI use (area under the curve, 0.67 [95% CI, 0.64-0.71] for the validation set and 0.66 [95% CI, 0.64-0.68] for the test set). To account for possible confounding by indication, we constructed a parallel model incorporating depression severity, finding only marginal performance improvement. When averaged across individuals and across 7 days, the results show less overall movement in the SSRI group (mean, 120.1 vertical acceleration counts/min [95% CI, 115.7-124.6 vertical acceleration counts/min]) (continued) Key Points Question What can digital technologies and deep learning indicate about the association between the use of antidepressants and abnormal physical movement patterns? Findings This cross-sectional study found a significant association between antidepressant use and measured movement, even when accounting for depression. Individuals treated with antidepressants had an overal...

show abstract

Fractional-order multiscale attention feature pyramid network for time series classification

Pan

Zhang

2022

Appl Intell

View full text Add to dashboard Cite

A Sense Embedding of Deep Convolutional Neural Networks for Sentiment Classification

Abstract: Abstract

Cited by 3 publications

References 10 publications

Long-Short-Term Memory Based on Adaptive Convolutional Network for Time Series Classification

Long-Short-Term Memory Based on Adaptive Convolutional Network for Time Series Classification

Association of Selective Serotonin Reuptake Inhibitor Use With Abnormal Physical Movement Patterns as Detected Using a Piezoelectric Accelerometer and Deep Learning in a Nationally Representative Sample of Noninstitutionalized Persons in the US

Fractional-order multiscale attention feature pyramid network for time series classification

Contact Info

Product

Resources

About