scholarly journals Emotion Classification of Song Lyrics using Bidirectional LSTM Method with GloVe Word Representation Weighting

2020 ◽  
Vol 4 (4) ◽  
pp. 723-729
Author(s):  
Jiddy Abdillah ◽  
Ibnu Asror ◽  
Yanuar Firdaus Arie Wibowo
Keyword(s):  
Short Term Memory ◽  
Rapid Change ◽  
Data Sets ◽  
Emotion Classification ◽  
Analog To Digital ◽  
Word Representation ◽  
Song Lyrics ◽  
The Difference ◽  
Decay Parameters

The rapid change of the music market from analog to digital has caused a rapid increase in the amount of music that is spread throughout the world as well because music is easier to make and sell. The amount of music available has changed the way people find music, one of which is based on the emotion of the song. The existence of music emotion recognition and recommendation helps music listeners find songs in accordance with their emotions. Therefore, the classification of emotions is needed to determine the emotions of a song. The emotional classification of a song is largely based on feature extraction and learning from the available data sets. Various learning algorithms have been used to classify song emotions and produce different accuracy. In this study, the Bidirectional Long-short Term Memory (Bi-LSTM) deep learning method with weighting words using GloVe is used to classify the song's emotions using the lyrics of the song. The result shows that the Bi-LSTM model with dropout layer and activity regularization can produce an accuracy of 91.08%. Dropout, activity regularization and learning rate decay parameters can reduce the difference between training loss and validation loss by 0.15.

Classification of Twitter Vaping Discourse Using BERTweet: Comparative Deep Learning Study (Preprint)

2021 ◽  
Author(s):  
Alycia Noel Carey ◽  
William Baker ◽  
Jason B. Colditz ◽  
Huy Mai ◽  
Shyam Visweswaran ◽  
...  
Keyword(s):  
Deep Learning ◽  
Language Processing ◽  
Short Term Memory ◽  
Characteristic Curve ◽  
Data Sets ◽  
Learning Approaches ◽  
Sensitive Data ◽  
Twitter Data ◽  
Traditional Natural

BACKGROUND Twitter provides a valuable platform for the surveillance and monitoring of public health topics; however, manually categorizing large quantities of Twitter data is labor intensive and presents barriers to identify major trends and sentiments. Additionally, while machine and deep learning approaches have been proposed with high accuracy, they require large, annotated data sets. Public pre-trained deep learning classification models, such as BERTweet, produce higher quality models while using smaller annotated training sets. OBJECTIVE This study aims to derive and evaluate a pre-trained deep learning model based on BERTweet that can identify tweets relevant to vaping, tweets (related to vaping) of commercial nature, and tweets with pro-vape sentiment. Additionally, the performance of the BERTweet classifier will be compared against a long short-term memory (LSTM) model to show the improvements a pre-trained model has over traditional deep learning approaches. METHODS Twitter data were collected from August – October 2019 using vaping related search terms. From this set, a random subsample of 2,401 English tweets was manually annotated for relevance (vaping related or not), commercial nature (commercial or not), and sentiment (positive, negative, neutral). Using the annotated data, three separate classifiers were built using BERTweet with the default parameters defined by the Simple Transformer API. Each model was trained for 20 iterations and evaluated with a random split of the annotate tweets, reserving 10% of tweets for evaluations. RESULTS The relevance, commercial, and sentiment classifiers achieved an area under the receiver operating characteristic curve (AUROC) of 94.5%, 99.3%, and 81.7%, respectively. Additionally, the weighted F1 scores of each were 97.6%, 99.0%, and 86.1%. We found that BERTweet outperformed the LSTM model in classification of all categories. CONCLUSIONS Large, open-source deep learning classifiers, such as BERTweet, can provide researchers the ability to reliably determine if tweets are relevant to vaping, include commercial content, and include positive, negative, or neutral content about vaping with a higher accuracy than traditional Natural Language Processing deep learning models. Such enhancement to the utilization of Twitter data can allow for faster exploration and dissemination of time-sensitive data than traditional methodologies (e.g., surveys, polling research).

scholarly journals Neogene Siwalik mammalian lineages: species longevities, rates of change, and modes of speciation

1992 ◽  
Vol 6 ◽  
pp. 101-101
Author(s):  
Lawrence J. Flynn ◽  
John C. Barry ◽  
Michele E. Morgan ◽  
David Pilbeam ◽  
Louis L. Jacobs ◽  
...  
Keyword(s):  
Mammalian Species ◽  
Rapid Change ◽  
Temporal Distribution ◽  
Dominant Mode ◽  
Data Sets ◽  
Data Set ◽  
Rate Of Increase ◽  
Biogeographic Provinces ◽  
Average Longevity ◽  
The Difference

The Siwalik sequence, particularly the interval from 18 to 7 Ma, provides one of the few terrestrial data sets that allows direct measurement of temporal durations of mammalian species. Its data are drawn from a single biogeographic subprovince and superposed collections likely represent successive samples of single lineages. Observed temporal ranges underestimate total species longevities if (1) species existed in other biogeographic provinces before or after the temporal ranges recorded in the Siwaliks, or (2) the fossil record inadequately samples species durations in the Siwalik subprovince. Some data, notably from Afghanistan, China, and Thailand, bear on the first variable. The second can be controlled by considering data quality, in this case the temporal distribution of good data sets, to assess the scale of accuracy available for defining range endpoints. In general, range endpoints can be estimated to the nearest 0.1 million years.The diverse Rodentia give a mean species longevity of 2.2 million years for the Miocene Siwaliks. This includes single records, but of course ignores unretrieved rare or short-lived taxa. The diverse Artiodactyla yield 3.1 million years. The difference may reflect greater body size and longer generation time; large Perissodactyla and Proboscidea have longer temporal ranges. Carnivorous mammals also show about 3 million year durations. Given these data, the average longevity for Sivapithecus species (1.6 million years) is modest. The deposits of the Clarks Fork Basin, Wyoming, offer a Paleogene data set comparable to that of the Neogene Siwaliks. Paleocene-Eocene mammals of North America yield shorter longevities (most less than one million years).Extinction is the dominant mode of species termination for Siwalik mammals. Most taxa originated by immigration (as at about 13.5 Ma) or abrupt speciation. There are some cases for insitu transformation of lineages, for example in the genera Punjabemys, Antemus, Percrocuta, Dorcatherium, Giraffokeryx, and Selenoportax. The rodent Kanisamys shows a rate of increase in tooth size of 0.5 darwins. This overall rate is moderate by Paleogene standards, but includes an interval of more rapid change between 9.0 and 8.5 Ma.

scholarly journals Sentiment classification of user's reviews on drugs based on global vectors for word representation and bidirectional long short-term memory recurrent neural network

2021 ◽  
Vol 23 (1) ◽  
pp. 345
Author(s):  
Hadab Khalid Obayed ◽  
Firas Sabah Al-Turaihi ◽  
Khaldoon H. Alhussayni
Keyword(s):  
Neural Network ◽  
Short Term Memory ◽  
Human Life ◽  
Health Sector ◽  
Ground Truth ◽  
Second Stage ◽  
The Social ◽  
Word Representation ◽  
Two Phases

<p>The process of product development in the health sector, especially pharmaceuticals, goes through a series of precise procedures due to its directrelevance to human life. The opinion of patients or users of a particular drugcan be relied upon in this development process, as the patients convey their experience with the drugs through their opinion. The social media field provides many datasets related to drugs through knowing the user's ratingand opinion on a drug after using it. In this work, a dataset is used that includes the user’s rating and review on the drug, for the purpose of classifying the user’s opinions (reviews) whether they are positive ornegative. The proposed method in this article includes two phases. The first phase is to use the Global vectors for word representation model for converting texts into the vector of embedded words. As for the second stage, the deep neural network (Bidirectional longshort-termmemory) is employedin the classification of reviews. The user's rating is used as a ground truth inevaluating the classification results. The proposed method present sencouraging results, as the classification results are evaluated through threecriteria, namely Precision, Recall and F-score, whose obtained values equal(0.9543, 0.9597and0.9558), respectively. The classification results of theproposed method are compared to a number of classifiers, and it was noticed that the results of the proposed method exceed those of the alternative classifiers.</p>

Depression, pain, and site:

1999 ◽  
Vol 15 (1) ◽  
pp. 10-17
Author(s):  
Molina Omar Franklin ◽  
Tavares Gimenes Pablo ◽  
Aquilino Raphael ◽  
Rank Rise ◽  
Coelho Santos Zeila ◽  
...  
Keyword(s):  
Visual Analogue Scale ◽  
Beck Depression Inventory ◽  
Temporomandibular Disorders ◽  
Analogue Scale ◽  
Epidemiological Data ◽  
Depression Severity ◽  
Internal Joint ◽  
The Difference ◽  
Biomechanical Tests

Objective: To assess the level of depression, severity of pain and pain in single/multiple sites in patients with different severity of bruxing behavior and Temporomandibular Disorders (TMDs). Methods: We evaluated 131 patients with bruxism and TMDs: 20 patients with mild bruxism, 42 patients with moderate bruxism, 45 patients with severe bruxism and 24 patients with extreme bruxism. We used the Beck Depression Inventory (BDI), clinical examination, a questionnaire of clinical epidemiological data, criteria for TMDs and bruxism, palpation of muscles and joints, the Visual Analogue Scale for pain, classification of the occlusion and biomechanical tests to assess for internal joint derangements. Results: The level of depression increased from the mild, to the moderate, severe and extreme bruxing behavior groups, but the difference was significant only from the mild to the extreme group (p<0.001). Pain levels increased from the mild and moderate to the severe and extreme subgroups, but were not statistically significant. Mean number of pain sites increased from the mild, to the moderate, severe and extreme subgroup and the difference was extremely significant (p<0.0001). Conclusion: Levels of depression, severity of pain and pain sites increased with severity of bruxing behavior. A higher number of pain sites with more severe bruxism indicates somatization in bruxers, but a further study using the same protocol and a psychological test for somatization would be indicated to further substantiate these findings.

Human Activity Recognition using Fourier Transform Inspired Deep Learning Combination Model

2019 ◽  
Vol 9 (1) ◽  
pp. 16-31
Author(s):  
Kyungkoo Jun
Keyword(s):  
Fourier Transform ◽  
Deep Learning ◽  
Short Term Memory ◽  
Window Size ◽  
Sensor Data ◽  
Data Sets ◽  
Data Set ◽  
Proposed Model ◽  
Testing Data ◽  
Labeling Scheme

Background & Objective: This paper proposes a Fourier transform inspired method to classify human activities from time series sensor data. Methods: Our method begins by decomposing 1D input signal into 2D patterns, which is motivated by the Fourier conversion. The decomposition is helped by Long Short-Term Memory (LSTM) which captures the temporal dependency from the signal and then produces encoded sequences. The sequences, once arranged into the 2D array, can represent the fingerprints of the signals. The benefit of such transformation is that we can exploit the recent advances of the deep learning models for the image classification such as Convolutional Neural Network (CNN). Results: The proposed model, as a result, is the combination of LSTM and CNN. We evaluate the model over two data sets. For the first data set, which is more standardized than the other, our model outperforms previous works or at least equal. In the case of the second data set, we devise the schemes to generate training and testing data by changing the parameters of the window size, the sliding size, and the labeling scheme. Conclusion: The evaluation results show that the accuracy is over 95% for some cases. We also analyze the effect of the parameters on the performance.

scholarly journals Classification of jujube defects in small data sets based on transfer learning

2021 ◽  
Author(s):  
Jianping Ju ◽  
Hong Zheng ◽  
Xiaohang Xu ◽  
Zhongyuan Guo ◽  
Zhaohui Zheng ◽  
...  
Keyword(s):  
Transfer Learning ◽  
Loss Function ◽  
Training Model ◽  
Parameter Distribution ◽  
Test Accuracy ◽  
Small Data ◽  
Data Sets ◽  
Data Set ◽  
Small Data Sets

AbstractAlthough convolutional neural networks have achieved success in the field of image classification, there are still challenges in the field of agricultural product quality sorting such as machine vision-based jujube defects detection. The performance of jujube defect detection mainly depends on the feature extraction and the classifier used. Due to the diversity of the jujube materials and the variability of the testing environment, the traditional method of manually extracting the features often fails to meet the requirements of practical application. In this paper, a jujube sorting model in small data sets based on convolutional neural network and transfer learning is proposed to meet the actual demand of jujube defects detection. Firstly, the original images collected from the actual jujube sorting production line were pre-processed, and the data were augmented to establish a data set of five categories of jujube defects. The original CNN model is then improved by embedding the SE module and using the triplet loss function and the center loss function to replace the softmax loss function. Finally, the depth pre-training model on the ImageNet image data set was used to conduct training on the jujube defects data set, so that the parameters of the pre-training model could fit the parameter distribution of the jujube defects image, and the parameter distribution was transferred to the jujube defects data set to complete the transfer of the model and realize the detection and classification of the jujube defects. The classification results are visualized by heatmap through the analysis of classification accuracy and confusion matrix compared with the comparison models. The experimental results show that the SE-ResNet50-CL model optimizes the fine-grained classification problem of jujube defect recognition, and the test accuracy reaches 94.15%. The model has good stability and high recognition accuracy in complex environments.

scholarly journals Time–frequency time–space LSTM for robust classification of physiological signals

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Tuan D. Pham
Keyword(s):  
Time Series ◽  
Network Architecture ◽  
Time Series Data ◽  
Short Term Memory ◽  
Physiological Signals ◽  
Series Data ◽  
Time Frequency ◽  
Time Space ◽  
Deep Recurrent Neural Network

AbstractAutomated analysis of physiological time series is utilized for many clinical applications in medicine and life sciences. Long short-term memory (LSTM) is a deep recurrent neural network architecture used for classification of time-series data. Here time–frequency and time–space properties of time series are introduced as a robust tool for LSTM processing of long sequential data in physiology. Based on classification results obtained from two databases of sensor-induced physiological signals, the proposed approach has the potential for (1) achieving very high classification accuracy, (2) saving tremendous time for data learning, and (3) being cost-effective and user-comfortable for clinical trials by reducing multiple wearable sensors for data recording.

Detection and Classification of Anomalies in Large Data Sets on the Basis of Information Granules

2021 ◽  
pp. 1-1
Author(s):  
Adam Kiersztyn ◽  
Pawe Karczmarek ◽  
Krystyna Kiersztyn ◽  
Witold Pedrycz
Keyword(s):  
Large Data ◽  
Large Data Sets ◽  
Data Sets ◽  
Information Granules
Sign in / Sign up

Export Citation Format

Share Document