Predicting Spatiotemporal Demand of Dockless E-Scooter Sharing Services with a Masked Fully Convolutional Network

2021 ◽  
Vol 10 (11) ◽  
pp. 773
Author(s):  
Santi Phithakkitnukooon ◽  
Karn Patanukhom ◽  
Merkebe Getachew Demissie
Keyword(s):  
Loss Function ◽  
Short Term Memory ◽  
Selection Process ◽  
Convolutional Network ◽  
Fully Convolutional Network ◽  
Demand Prediction ◽  
Learning Techniques ◽  
Last Mile ◽  
Long Short Term Memory ◽  
Highly Correlated

Dockless electric scooters (e-scooter) have emerged as a green alternative to automobiles and a solution to the first- and last-mile problems. Demand anticipation, or being able to accurately predict spatiotemporal demand of e-scooter usage, is one supply–demand balancing strategy. In this paper, we present a dockless e-scooter demand prediction model based on a fully convolutional network (FCN) coupled with a masking process and a weighted loss function, namely, masked FCN (or MFCN). The MFCN model handles the sparse e-scooter usage data with its masking process and weighted loss function. The model is trained with highly correlated features through our feature selection process. Next-hour and next 24-h prediction schemes have been tested for both pick-up and drop-off demands. Overall, the proposed MFCN outperforms other baseline models including a naïve forecasting, linear regression, and convolutional long short-term memory networks with mean absolute errors of 0.0434 and 0.0464 for the next-hour pick-up and drop-off demand prediction, respectively, and the errors of 0.0491 and 0.0501 for the next 24-h pick-up and drop-off demand prediction, respectively. The developed MFCN expands the collection of deep learning techniques that can be applied in the transportation domain, especially spatiotemporal demand prediction.

Using Machine Learning Algorithms on Prediction of Stock Price

2020 ◽  
Vol 12 (2) ◽  
pp. 84-99
Author(s):  
Li-Pang Chen
Keyword(s):  
Machine Learning ◽  
Stock Price ◽  
Short Term Memory ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Short Term ◽  
Learning Techniques ◽  
Historical Database ◽  
Long Short Term Memory

In this paper, we investigate analysis and prediction of the time-dependent data. We focus our attention on four different stocks are selected from Yahoo Finance historical database. To build up models and predict the future stock price, we consider three different machine learning techniques including Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN) and Support Vector Regression (SVR). By treating close price, open price, daily low, daily high, adjusted close price, and volume of trades as predictors in machine learning methods, it can be shown that the prediction accuracy is improved.

scholarly journals Change Detection in Hyperspectral Images Using Recurrent 3D Fully Convolutional Networks

2018 ◽  
Vol 10 (11) ◽  
pp. 1827 ◽  
Author(s):  
Ahram Song ◽  
Jaewan Choi ◽  
Youkyung Han ◽  
Yongil Kim
Keyword(s):  
Deep Learning ◽  
Change Detection ◽  
Spatial Information ◽  
Short Term Memory ◽  
Hyperspectral Images ◽  
Convolutional Network ◽  
Ground Truth Data ◽  
Fully Convolutional Network ◽  
Training Samples ◽  
Multi Temporal

Hyperspectral change detection (CD) can be effectively performed using deep-learning networks. Although these approaches require qualified training samples, it is difficult to obtain ground-truth data in the real world. Preserving spatial information during training is difficult due to structural limitations. To solve such problems, our study proposed a novel CD method for hyperspectral images (HSIs), including sample generation and a deep-learning network, called the recurrent three-dimensional (3D) fully convolutional network (Re3FCN), which merged the advantages of a 3D fully convolutional network (FCN) and a convolutional long short-term memory (ConvLSTM). Principal component analysis (PCA) and the spectral correlation angle (SCA) were used to generate training samples with high probabilities of being changed or unchanged. The strategy assisted in training fewer samples of representative feature expression. The Re3FCN was mainly comprised of spectral–spatial and temporal modules. Particularly, a spectral–spatial module with a 3D convolutional layer extracts the spectral–spatial features from the HSIs simultaneously, whilst a temporal module with ConvLSTM records and analyzes the multi-temporal HSI change information. The study first proposed a simple and effective method to generate samples for network training. This method can be applied effectively to cases with no training samples. Re3FCN can perform end-to-end detection for binary and multiple changes. Moreover, Re3FCN can receive multi-temporal HSIs directly as input without learning the characteristics of multiple changes. Finally, the network could extract joint spectral–spatial–temporal features and it preserved the spatial structure during the learning process through the fully convolutional structure. This study was the first to use a 3D FCN and a ConvLSTM for the remote-sensing CD. To demonstrate the effectiveness of the proposed CD method, we performed binary and multi-class CD experiments. Results revealed that the Re3FCN outperformed the other conventional methods, such as change vector analysis, iteratively reweighted multivariate alteration detection, PCA-SCA, FCN, and the combination of 2D convolutional layers-fully connected LSTM.

scholarly journals BO-LSTM: Classifying relations via long short-term memory networks along biomedical ontologies

2018 ◽  
Author(s):  
Andre Lamurias ◽  
Luka A. Clarke ◽  
Francisco M. Couto
Keyword(s):  
Deep Learning ◽  
Text Mining ◽  
Drug Interactions ◽  
Short Term Memory ◽  
Biomedical Ontologies ◽  
Short Term ◽  
Term Memory ◽  
Domain Specific ◽  
Learning Techniques ◽  
Long Short Term Memory

AbstractRecent studies have proposed deep learning techniques, namely recurrent neural networks, to improve biomedical text mining tasks. However, these techniques rarely take advantage of existing domain-specific resources, such as ontologies. In Life and Health Sciences there is a vast and valuable set of such resources publicly available, which are continuously being updated. Biomedical ontologies are nowadays a mainstream approach to formalize existing knowledge about entities, such as genes, chemicals, phenotypes, and disorders. These resources contain supplementary information that may not be yet encoded in training data, particularly in domains with limited labeled data.We propose a new model, BO-LSTM, that takes advantage of domain-specific ontologies, by representing each entity as the sequence of its ancestors in the ontology. We implemented BO-LSTM as a recurrent neural network with long short-term memory units and using an open biomedical ontology, which in our case-study was Chemical Entities of Biological Interest (ChEBI). We assessed the performance of BO-LSTM on detecting and classifying drug-drug interactions in a publicly available corpus from an international challenge, composed of 792 drug descriptions and 233 scientific abstracts. By using the domain-specific ontology in addition to word embeddings and WordNet, BO-LSTM improved both the F1-score of the detection and classification of drug-drug interactions, particularly in a document set with a limited number of annotations. Our findings demonstrate that besides the high performance of current deep learning techniques, domain-specific ontologies can still be useful to mitigate the lack of labeled data.Author summaryA high quantity of biomedical information is only available in documents such as scientific articles and patents. Due to the rate at which new documents are produced, we need automatic methods to extract useful information from them. Text mining is a subfield of information retrieval which aims at extracting relevant information from text. Scientific literature is a challenge to text mining because of the complexity and specificity of the topics approached. In recent years, deep learning has obtained promising results in various text mining tasks by exploring large datasets. On the other hand, ontologies provide a detailed and sound representation of a domain and have been developed to diverse biomedical domains. We propose a model that combines deep learning algorithms with biomedical ontologies to identify relations between concepts in text. We demonstrate the potential of this model to extract drug-drug interactions from abstracts and drug descriptions. This model can be applied to other biomedical domains using an annotated corpus of documents and an ontology related to that domain to train a new classifier.

scholarly journals Identifying vulgarity in Bengali social media textual content

2021 ◽  
Vol 7 ◽  
pp. e665
Author(s):  
Salim Sazzed
Keyword(s):  
Social Media ◽  
Gradient Descent ◽  
Short Term Memory ◽  
Stochastic Gradient Descent ◽  
Media Content ◽  
Short Term ◽  
Long Short Term Memory ◽  
Highly Correlated ◽  
Negative Sentiment ◽  
Textual Content

The presence of abusive and vulgar language in social media has become an issue of increasing concern in recent years. However, research pertaining to the prevalence and identification of vulgar language has remained largely unexplored in low-resource languages such as Bengali. In this paper, we provide the first comprehensive analysis on the presence of vulgarity in Bengali social media content. We develop two benchmark corpora consisting of 7,245 reviews collected from YouTube and manually annotate them into vulgar and non-vulgar categories. The manual annotation reveals the ubiquity of vulgar and swear words in Bengali social media content (i.e., in two corpora), ranging from 20% to 34%. To automatically identify vulgarity, we employ various approaches, such as classical machine learning (CML) classifiers, Stochastic Gradient Descent (SGD) optimizer, a deep learning (DL) based architecture, and lexicon-based methods. Although small in size, we find that the swear/vulgar lexicon is effective at identifying the vulgar language due to the high presence of some swear terms in Bengali social media. We observe that the performances of machine leanings (ML) classifiers are affected by the class distribution of the dataset. The DL-based BiLSTM (Bidirectional Long Short Term Memory) model yields the highest recall scores for identifying vulgarity in both datasets (i.e., in both original and class-balanced settings). Besides, the analysis reveals that vulgarity is highly correlated with negative sentiment in social media comments.

scholarly journals Prediction of Protein Secondary Structure Based on WS-BiLSTM Model

Symmetry ◽  
2022 ◽  
Vol 14 (1) ◽  
pp. 89
Author(s):  
Yang Gao ◽  
Yawu Zhao ◽  
Yuming Ma ◽  
Yihui Liu
Keyword(s):  
Secondary Structure ◽  
Structure Prediction ◽  
Short Term Memory ◽  
Secondary Structure Prediction ◽  
Protein Secondary Structure ◽  
Short Term ◽  
Convolutional Network ◽  
Term Memory ◽  
Memory Network ◽  
Long Short Term Memory

Protein secondary structure prediction is an important topic in bioinformatics. This paper proposed a novel model named WS-BiLSTM, which combined the wavelet scattering convolutional network and the long-short-term memory network for the first time to predict protein secondary structure. This model captures nonlocal interactions between amino acid sequences and remembers long-range interactions between amino acids. In our WS-BiLSTM model, the wavelet scattering convolutional network is used to extract protein features from the PSSM sliding window; the extracted features are combined with the original PSSM data as the input features of the long-short-term memory network to predict protein secondary structure. It is worth noting that the wavelet scattering convolutional network is asymmetric as a member of the continuous wavelet family. The Q3 accuracy on the test set CASP9, CASP10, CASP11, CASP12, CB513, and PDB25 reached 85.26%, 85.84%, 84.91%, 85.13%, 86.10%, and 85.52%, which were higher 2.15%, 2.16%, 3.5%, 3.19%, 4.22%, and 2.75%, respectively, than using the long-short-term memory network alone. Comparing our results with the state-of-art methods shows that our proposed model achieved better results on the CB513 and CASP12 data sets. The experimental results show that the features extracted from the wavelet scattering convolutional network can effectively improve the accuracy of protein secondary structure prediction.

scholarly journals Deep Learning-Based Sentiment Analysis of COVID-19 Vaccination Responses from Twitter Data

2021 ◽  
Vol 2021 ◽  
pp. 1-15
Author(s):  
Kazi Nabiul Alam ◽  
Md Shakib Khan ◽  
Abdur Rab Dhruba ◽  
Mohammad Monirujjaman Khan ◽  
Jehad F. Al-Amri ◽  
...  
Keyword(s):  
Deep Learning ◽  
Language Processing ◽  
Performance Metrics ◽  
Short Term Memory ◽  
Confusion Matrix ◽  
Short Term ◽  
Learning Techniques ◽  
The World ◽  
Long Short Term Memory ◽  
Severe Anxiety

The COVID-19 pandemic has had a devastating effect on many people, creating severe anxiety, fear, and complicated feelings or emotions. After the initiation of vaccinations against coronavirus, people’s feelings have become more diverse and complex. Our aim is to understand and unravel their sentiments in this research using deep learning techniques. Social media is currently the best way to express feelings and emotions, and with the help of Twitter, one can have a better idea of what is trending and going on in people’s minds. Our motivation for this research was to understand the diverse sentiments of people regarding the vaccination process. In this research, the timeline of the collected tweets was from December 21 to July21. The tweets contained information about the most common vaccines available recently from across the world. The sentiments of people regarding vaccines of all sorts were assessed using the natural language processing (NLP) tool, Valence Aware Dictionary for sEntiment Reasoner (VADER). Initializing the polarities of the obtained sentiments into three groups (positive, negative, and neutral) helped us visualize the overall scenario; our findings included 33.96% positive, 17.55% negative, and 48.49% neutral responses. In addition, we included our analysis of the timeline of the tweets in this research, as sentiments fluctuated over time. A recurrent neural network- (RNN-) oriented architecture, including long short-term memory (LSTM) and bidirectional LSTM (Bi-LSTM), was used to assess the performance of the predictive models, with LSTM achieving an accuracy of 90.59% and Bi-LSTM achieving 90.83%. Other performance metrics such as precision,, F1-score, and a confusion matrix were also used to validate our models and findings more effectively. This study improves understanding of the public’s opinion on COVID-19 vaccines and supports the aim of eradicating coronavirus from the world.

scholarly journals Convolutional Neural Network and Long Short-Term Memory Models for Ice-Jam Prediction

2021 ◽  
Author(s):  
Fatemehalsadat Madaeni ◽  
Karem Chokmani ◽  
Rachid Lhissou ◽  
Saeid Homayuni ◽  
Yves Gauthier ◽  
...  
Keyword(s):  
Time Series ◽  
Short Term Memory ◽  
Weather Forecasting ◽  
Multivariate Time Series ◽  
Water Levels ◽  
Time Series Classification ◽  
Ice Jams ◽  
Ice Jam ◽  
Learning Techniques ◽  
Long Short Term Memory

Abstract. In cold regions, ice-jam events result in severe flooding due to a rapid rise in water levels upstream of the jam. These floods threaten human safety and damage properties and infrastructures as the floods resulting from ice-jams are sudden. Hence, the ice-jam prediction tools can give an early warning to increase response time and minimize the possible corresponding damages. However, the ice-jam prediction has always been a challenging problem as there is no analytical method available for this purpose. Nonetheless, ice jams form when some hydro-meteorological conditions happen, a few hours to a few days before the event. The ice-jam prediction problem can be considered as a binary multivariate time-series classification. Deep learning techniques have been successfully applied for time-series classification in many fields such as finance, engineering, weather forecasting, and medicine. In this research, we successfully applied CNN, LSTM, and combined CN-LSTM networks for ice-jam prediction for all the rivers in Quebec. The results show that the CN-LSTM model yields the best results in the validation and generalization with F1 scores of 0.82 and 0.91, respectively. This demonstrates that CNN and LSTM models are complementary, and a combination of them further improves classification.

Sequence Model based Cloudburst Prediction for the Indian State of Uttarakhand

2021 ◽  
Vol 14 (7) ◽  
pp. 1-9
Author(s):  
M. Sivagami ◽  
P. Radha ◽  
A. Balasundaram
Keyword(s):  
Predictive Power ◽  
Short Term Memory ◽  
Geographic Location ◽  
Short Term ◽  
The Past ◽  
Learning Techniques ◽  
Indian State ◽  
Long Short Term Memory ◽  
Life Challenge ◽  
Gated Recurrent Unit

Predicting the phenomenon of cloudburst has been a larger than life challenge to many weather and rain scientists. The very nature of cloudburst occurrence itself complicates the prediction of cloudburst. Since, cloudburst downpour occurs over a short span of time and is confined to very narrow geographic location, it is highly difficult for weather scientists to make any cloudburst predictions. In this work, the authors propose a cloudburst prediction model that leverages deep learning techniques to predict the occurrence of cloudburst in a location. The authors have collected the data pertaining to the cloudburst events that have occurred in the Indian State of Uttarakhand over the past decade and developed the model. Experiments were conducted using time series sequence models namely Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU). Predictive Power Score (PPS) has been used to extract the essential features that are fed as input to these sequence models. The performance of sequence models has been discussed in terms of loss function and accuracy and the results are promising for GRU based model in comparison with other sequence models.

Sign in / Sign up

Export Citation Format

Share Document