SHEDR: An End-to-End Deep Neural Event Detection and Recommendation Framework for Hyperlocal News Using Social Media

2021 ◽  
Author(s):  
Yuheng Hu ◽  
Yili Hong
Keyword(s):  
Neural Network ◽  
Social Media ◽  
Deep Learning ◽  
Event Detection ◽  
Large Scale ◽  
Short Term Memory ◽  
State Of The Art ◽  
Neural Network Models ◽  
Neural Event ◽  
End To End

Residents often rely on newspapers and television to gather hyperlocal news for community awareness and engagement. More recently, social media have emerged as an increasingly important source of hyperlocal news. Thus far, the literature on using social media to create desirable societal benefits, such as civic awareness and engagement, is still in its infancy. One key challenge in this research stream is to timely and accurately distill information from noisy social media data streams to community members. In this work, we develop SHEDR (social media–based hyperlocal event detection and recommendation), an end-to-end neural event detection and recommendation framework with a particular use case for Twitter to facilitate residents’ information seeking of hyperlocal events. The key model innovation in SHEDR lies in the design of the hyperlocal event detector and the event recommender. First, we harness the power of two popular deep neural network models, the convolutional neural network (CNN) and long short-term memory (LSTM), in a novel joint CNN-LSTM model to characterize spatiotemporal dependencies for capturing unusualness in a region of interest, which is classified as a hyperlocal event. Next, we develop a neural pairwise ranking algorithm for recommending detected hyperlocal events to residents based on their interests. To alleviate the sparsity issue and improve personalization, our algorithm incorporates several types of contextual information covering topic, social, and geographical proximities. We perform comprehensive evaluations based on two large-scale data sets comprising geotagged tweets covering Seattle and Chicago. We demonstrate the effectiveness of our framework in comparison with several state-of-the-art approaches. We show that our hyperlocal event detection and recommendation models consistently and significantly outperform other approaches in terms of precision, recall, and F-1 scores. Summary of Contribution: In this paper, we focus on a novel and important, yet largely underexplored application of computing—how to improve civic engagement in local neighborhoods via local news sharing and consumption based on social media feeds. To address this question, we propose two new computational and data-driven methods: (1) a deep learning–based hyperlocal event detection algorithm that scans spatially and temporally to detect hyperlocal events from geotagged Twitter feeds; and (2) A personalized deep learning–based hyperlocal event recommender system that systematically integrates several contextual cues such as topical, geographical, and social proximity to recommend the detected hyperlocal events to potential users. We conduct a series of experiments to examine our proposed models. The outcomes demonstrate that our algorithms are significantly better than the state-of-the-art models and can provide users with more relevant information about the local neighborhoods that they live in, which in turn may boost their community engagement.

scholarly journals Classification of Skin Disease Using Deep Learning Neural Networks with MobileNet V2 and LSTM

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2852
Author(s):  
Parvathaneni Naga Srinivasu ◽  
Jalluri Gnana SivaSai ◽  
Muhammad Fazal Ijaz ◽  
Akash Kumar Bhoi ◽  
Wonjoon Kim ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Skin Disease ◽  
Network Architecture ◽  
Large Scale ◽  
Short Term Memory ◽  
Convolutional Networks ◽  
Occurrence Matrix

Deep learning models are efficient in learning the features that assist in understanding complex patterns precisely. This study proposed a computerized process of classifying skin disease through deep learning based MobileNet V2 and Long Short Term Memory (LSTM). The MobileNet V2 model proved to be efficient with a better accuracy that can work on lightweight computational devices. The proposed model is efficient in maintaining stateful information for precise predictions. A grey-level co-occurrence matrix is used for assessing the progress of diseased growth. The performance has been compared against other state-of-the-art models such as Fine-Tuned Neural Networks (FTNN), Convolutional Neural Network (CNN), Very Deep Convolutional Networks for Large-Scale Image Recognition developed by Visual Geometry Group (VGG), and convolutional neural network architecture that expanded with few changes. The HAM10000 dataset is used and the proposed method has outperformed other methods with more than 85% accuracy. Its robustness in recognizing the affected region much faster with almost 2× lesser computations than the conventional MobileNet model results in minimal computational efforts. Furthermore, a mobile application is designed for instant and proper action. It helps the patient and dermatologists identify the type of disease from the affected region’s image at the initial stage of the skin disease. These findings suggest that the proposed system can help general practitioners efficiently and effectively diagnose skin conditions, thereby reducing further complications and morbidity.

scholarly journals Data-to-Text Generation with Content Selection and Planning

2019 ◽  
Vol 33 ◽  
pp. 6908-6915 ◽  
Author(s):  
Ratish Puduppully ◽  
Li Dong ◽  
Mirella Lapata
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Large Scale ◽  
Network Models ◽  
Text Generation ◽  
Neural Network Models ◽  
Generation Task ◽  
Content Selection ◽  
End To End ◽  
Two Stages

Recent advances in data-to-text generation have led to the use of large-scale datasets and neural network models which are trained end-to-end, without explicitly modeling what to say and in what order. In this work, we present a neural network architecture which incorporates content selection and planning without sacrificing end-to-end training. We decompose the generation task into two stages. Given a corpus of data records (paired with descriptive documents), we first generate a content plan highlighting which information should be mentioned and in which order and then generate the document while taking the content plan into account. Automatic and human-based evaluation experiments show that our model1 outperforms strong baselines improving the state-of-the-art on the recently released RotoWIRE dataset.

Application of Deep Learning for Characterization of Drivers’ Engagement in Secondary Tasks in In-Vehicle Systems

2020 ◽  
Vol 2674 (8) ◽  
pp. 429-440
Author(s):  
Osama A. Osman ◽  
Hesham Rakha
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Time Series Data ◽  
Short Term Memory ◽  
Network Models ◽  
Sensor Technology ◽  
Series Data ◽  
Neural Network Models ◽  
Secondary Tasks ◽  
Driving Assistance

Distracted driving (i.e., engaging in secondary tasks) is an epidemic that threatens the lives of thousands every year. Data collected from vehicular sensor technologies and through connectivity provide comprehensive information that, if used to detect driver engagement in secondary tasks, could save thousands of lives and millions of dollars. This study investigates the possibility of achieving this goal using promising deep learning tools. Specifically, two deep neural network models (a multilayer perceptron neural network model and a long short-term memory networks [LSTMN] model) were developed to identify three secondary tasks: cellphone calling, cellphone texting, and conversation with adjacent passengers. The Second Strategic Highway Research Program Naturalistic Driving Study (SHRP 2 NDS) time series data, collected using vehicle sensor technology, were used to train and test the model. The results show excellent performance for the developed models, with a slight improvement for the LSTMN model, with overall classification accuracies ranging between 95 and 96%. Specifically, the models are able to identify the different types of secondary tasks with high accuracies of 100% for calling, 96%–97% for texting, 90%–91% for conversation, and 95%–96% for the normal driving. Based on this performance, the developed models improve on the results of a previous model developed by the author to classify the same three secondary tasks, which had an accuracy of 82%. The model is promising for use in in-vehicle driving assistance technology to report engagement in unlawful tasks or alert drivers to take over control in level 1 and 2 automated vehicles.

scholarly journals Comparative Analysis of Deep Learning Techniques for the Classification of Hate Speech

2021 ◽  
Vol 4 (1) ◽  
pp. 121-128
Author(s):  
A Iorliam ◽  
S Agber ◽  
MP Dzungwe ◽  
DK Kwaghtyo ◽  
S Bum
Keyword(s):  
Neural Network ◽  
Social Media ◽  
Deep Learning ◽  
Hate Speech ◽  
Short Term Memory ◽  
Short Term ◽  
Term Memory ◽  
Learning Techniques ◽  
Or Groups ◽  
Long Short Term Memory

Social media provides opportunities for individuals to anonymously communicate and express hateful feelings and opinions at the comfort of their rooms. This anonymity has become a shield for many individuals or groups who use social media to express deep hatred for other individuals or groups, tribes or race, religion, gender, as well as belief systems. In this study, a comparative analysis is performed using Long Short-Term Memory and Convolutional Neural Network deep learning techniques for Hate Speech classification. This analysis demonstrates that the Long Short-Term Memory classifier achieved an accuracy of 92.47%, while the Convolutional Neural Network classifier achieved an accuracy of 92.74%. These results showed that deep learning techniques can effectively classify hate speech from normal speech.

Deep Learning in the Healthcare Industry

2020 ◽  
pp. 220-245 ◽  
Author(s):  
Zahra A. Shirazi ◽  
Camila P. E. de Souza ◽  
Rasha Kashef ◽  
Felipe F. Rodrigues
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Input Data ◽  
Time Series Data ◽  
Short Term Memory ◽  
Healthcare Industry ◽  
Neural Network Models ◽  
Input Layer ◽  
Hidden Layer

Artificial Neural networks (ANN) are composed of nodes that are joint to each other through weighted connections. Deep learning, as an extension of ANN, is a neural network model, but composed of different categories of layers: input layer, hidden layers, and output layers. Input data is fed into the first (input) layer. But the main process of the neural network models is done within the hidden layers, ranging from a single hidden layer to multiple ones. Depending on the type of model, the structure of the hidden layers is different. Depending on the type of input data, different models are applied. For example, for image data, convolutional neural networks are the most appropriate. On the other hand, for text or sequential and time series data, recurrent neural networks or long short-term memory models are the better choices. This chapter summarizes the state-of-the-art deep learning methods applied to the healthcare industry.

scholarly journals Anomaly Detection Using XGBoost Ensemble of Deep Neural Network Models

2021 ◽  
Vol 21 (3) ◽  
pp. 175-188
Author(s):  
Sumaiya Thaseen Ikram ◽  
Aswani Kumar Cherukuri ◽  
Babu Poorva ◽  
Pamidi Sai Ushasree ◽  
Yishuo Zhang ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Anomaly Detection ◽  
Deep Neural Network ◽  
Short Term Memory ◽  
Network Models ◽  
Neural Network Models ◽  
Detection Model ◽  
Detection Systems ◽  
Learning Techniques

Abstract Intrusion Detection Systems (IDSs) utilise deep learning techniques to identify intrusions with maximum accuracy and reduce false alarm rates. The feature extraction is also automated in these techniques. In this paper, an ensemble of different Deep Neural Network (DNN) models like MultiLayer Perceptron (MLP), BackPropagation Network (BPN) and Long Short Term Memory (LSTM) are stacked to build a robust anomaly detection model. The performance of the ensemble model is analysed on different datasets, namely UNSW-NB15 and a campus generated dataset named VIT_SPARC20. Other types of traffic, namely unencrypted normal traffic, normal encrypted traffic, encrypted and unencrypted malicious traffic, are captured in the VIT_SPARC20 dataset. Encrypted normal and malicious traffic of VIT_SPARC20 is categorised by the deep learning models without decrypting its contents, thus preserving the confidentiality and integrity of the data transmitted. XGBoost integrates the results of each deep learning model to achieve higher accuracy. From experimental analysis, it is inferred that UNSW_ NB results in a maximal accuracy of 99.5%. The performance of VIT_SPARC20 in terms of accuracy, precision and recall are 99.4%. 98% and 97%, respectively.

scholarly journals Repetitive Reprediction Deep Decipher for Semi-Supervised Learning

2020 ◽  
Vol 34 (04) ◽  
pp. 6170-6177
Author(s):  
Guo-Hua Wang ◽  
Jianxin Wu
Keyword(s):  
Deep Learning ◽  
Supervised Learning ◽  
Large Scale ◽  
State Of The Art ◽  
Link Function ◽  
Training Strategy ◽  
Network Parameters ◽  
Theoretical Support ◽  
Percentage Points ◽  
End To End

Most recent semi-supervised deep learning (deep SSL) methods used a similar paradigm: use network predictions to update pseudo-labels and use pseudo-labels to update network parameters iteratively. However, they lack theoretical support and cannot explain why predictions are good candidates for pseudo-labels. In this paper, we propose a principled end-to-end framework named deep decipher (D2) for SSL. Within the D2 framework, we prove that pseudo-labels are related to network predictions by an exponential link function, which gives a theoretical support for using predictions as pseudo-labels. Furthermore, we demonstrate that updating pseudo-labels by network predictions will make them uncertain. To mitigate this problem, we propose a training strategy called repetitive reprediction (R2). Finally, the proposed R2-D2 method is tested on the large-scale ImageNet dataset and outperforms state-of-the-art methods by 5 percentage points.

scholarly journals Deep learning for pharmacovigilance: recurrent neural network architectures for labeling adverse drug reactions in Twitter posts

2017 ◽  
Vol 24 (4) ◽  
pp. 813-821 ◽  
Author(s):  
Anne Cocos ◽  
Alexander G Fiks ◽  
Aaron J Masino
Keyword(s):  
Neural Network ◽  
Social Media ◽  
Deep Learning ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Recurrent Neural Network ◽  
State Of The Art ◽  
Detection Performance ◽  
Word Embeddings

Abstract Objective Social media is an important pharmacovigilance data source for adverse drug reaction (ADR) identification. Human review of social media data is infeasible due to data quantity, thus natural language processing techniques are necessary. Social media includes informal vocabulary and irregular grammar, which challenge natural language processing methods. Our objective is to develop a scalable, deep-learning approach that exceeds state-of-the-art ADR detection performance in social media. Materials and Methods We developed a recurrent neural network (RNN) model that labels words in an input sequence with ADR membership tags. The only input features are word-embedding vectors, which can be formed through task-independent pretraining or during ADR detection training. Results Our best-performing RNN model used pretrained word embeddings created from a large, non–domain-specific Twitter dataset. It achieved an approximate match F-measure of 0.755 for ADR identification on the dataset, compared to 0.631 for a baseline lexicon system and 0.65 for the state-of-the-art conditional random field model. Feature analysis indicated that semantic information in pretrained word embeddings boosted sensitivity and, combined with contextual awareness captured in the RNN, precision. Discussion Our model required no task-specific feature engineering, suggesting generalizability to additional sequence-labeling tasks. Learning curve analysis showed that our model reached optimal performance with fewer training examples than the other models. Conclusions ADR detection performance in social media is significantly improved by using a contextually aware model and word embeddings formed from large, unlabeled datasets. The approach reduces manual data-labeling requirements and is scalable to large social media datasets.

scholarly journals DeepADEMiner: A Deep Learning Pharmacovigilance Pipeline for Extraction and Normalization of Adverse Drug Effect Mentions on Twitter

2020 ◽  
Author(s):  
Arjun Magge ◽  
Elena Tutubalina ◽  
Zulfat Miftahutdinov ◽  
Ilseyar Alimova ◽  
Anne Dirkson ◽  
...  
Keyword(s):  
Social Media ◽  
Deep Learning ◽  
Large Scale ◽  
Named Entity Recognition ◽  
Drug Effects ◽  
Entity Recognition ◽  
Pipeline Architecture ◽  
Social Media Data ◽  
End To End ◽  
Media Data

Objective: Research on pharmacovigilance from social media data has focused on mining adverse drug effects (ADEs) using annotated datasets, with publications generally focusing on one of three tasks: (i) ADE classification, (ii) named entity recognition (NER) for identifying the span of an ADE mentions, and (iii) ADE mention normalization to standardized vocabularies. While the common goal of such systems is to detect ADE signals that can be used to inform public policy, it has been impeded largely by limited end-to-end solutions to the three tasks for large-scale analysis of social media reports for different drugs. Materials and Methods: We present a dataset for training and evaluation of ADE pipelines where the ADE distribution is closer to the average `natural balance' with ADEs present in about 7% of the Tweets. The deep learning architecture involves an ADE extraction pipeline with individual components for all three tasks. Results: The system presented achieved a classification performance of F1 = 0.63, span detection performance of F1 = 0.44 and an end-to-end entity resolution performance of F1 = 0.34 on the presented dataset. Discussion: The performance of the models continue to highlight multiple challenges when deploying pharmacovigilance systems that use social media data. We discuss the implications of such models in the downstream tasks of signal detection and suggest future enhancements. Conclusion: Mining ADEs from Twitter posts using a pipeline architecture requires the different components to be trained and tuned based on input data imbalance in order to ensure optimal performance on the end-to-end resolution task.

scholarly journals RNA-protein binding motifs mining with a new hybrid deep learning based cross-domain knowledge integration approach

2016 ◽  
Author(s):  
Xiaoyong Pan ◽  
Hong-Bin Shen
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Binding Sites ◽  
Domain Knowledge ◽  
Large Scale ◽  
Knowledge Integration ◽  
State Of The Art ◽  
Binding Motifs ◽  
Abstraction Level ◽  
Cross Domain

AbstractBackgroundRNAs play key roles in cells through the interactions with proteins known as the RNA-binding proteins (RBP) and their binding motifs enable crucial understanding of the post-transcriptional regulation of RNAs. How the RBPs correctly recognize the target RNAs and why they bind specific positions is still far from clear. Machine learning-based algorithms are widely acknowledged to be capable of speeding up this process. Although many automatic tools have been developed to predict the RNA-protein binding sites from the rapidly growing multi-resource data, e.g. sequence, structure, their domain specific features and formats have posed significant computational challenges. One of current difficulties is that the cross-source shared common knowledge is at a higher abstraction level beyond the observed data, resulting in a low efficiency of direct integration of observed data across domains. The other difficulty is how to interpret the prediction results. Existing approaches tend to terminate after outputting the potential discrete binding sites on the sequences, but how to assemble them into the meaningful binding motifs is a topic worth of further investigation.ResultsIn viewing of these challenges, we propose a deep learning-based framework (iDeep) by using a novel hybrid convolutional neural network and deep belief network to predict the RBP interaction sites and motifs on RNAs. This new protocol is featured by transforming the original observed data into a high-level abstraction feature space using multiple layers of learning blocks, where the shared representations across different domains are integrated. To validate our iDeep method, we performed experiments on 31 large-scale CLIP-seq datasets, and our results show that by integrating multiple sources of data, the average AUC can be improved by 8% compared to the best single-source-based predictor; and through cross-domain knowledge integration at an abstraction level, it outperforms the state-of-the-art predictors by 6%. Besides the overall enhanced prediction performance, the convolutional neural network module embedded in iDeep is also able to automatically capture the interpretable binding motifs for RBPs. Large-scale experiments demonstrate that these mined binding motifs agree well with the experimentally verified results, suggesting iDeep is a promising approach in the real-world applications.ConclusionThe iDeep framework not only can achieve promising performance than the state-of-the-art predictors, but also easily capture interpretable binding motifs. iDeep is available at http://www.csbio.sjtu.edu.cn/bioinf/iDeep

Sign in / Sign up

Export Citation Format

Share Document