GSS-RiskAsser: A Multi-Modal Deep-Learning Framework for Urban Gas Supply System Risk Assessment on Business Users

Gas supply system risk assessment is a serious and important problem in cities. Existing methods tend to manually build mathematical models to predict risk value from single-modal information, i.e., pipeline parameters. In this paper, we attempt to consider this problem from a deep-learning perspective and define a novel task, Urban Gas Supply System Risk Assessment (GSS-RA). To drive deep-learning techniques into this task, we collect and build a domain-specific dataset GSS-20K containing multi-modal data. Accompanying the dataset, we design a new deep-learning framework named GSS-RiskAsser to learn risk prediction. In our method, we design a parallel-transformers Vision Embedding Transformer (VET) and Score Matrix Transformer (SMT) to process multi-modal information, and then propose a Multi-Modal Fusion (MMF) module to fuse the features with a cross-attention mechanism. Experiments show that GSS-RiskAsser could work well on GSS-RA task and facilitate practical applications. Our data and code will be made publicly available.

Download Full-text

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

10.1101/336719 ◽

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.

Download Full-text

Mol-BERT: An Effective Molecular Representation with BERT for Molecular Property Prediction

Wireless Communications and Mobile Computing ◽

10.1155/2021/7181815 ◽

2021 ◽

Vol 2021 ◽

pp. 1-7

Author(s):

Juncai Li ◽

Xiaofei Jiang

Keyword(s):

Deep Learning ◽

Language Processing ◽

Large Scale ◽

Molecular Data ◽

Molecular Property ◽

Property Prediction ◽

Learning Framework ◽

Learning Techniques ◽

Potential Benefits ◽

Current Sequence

Molecular property prediction is an essential task in drug discovery. Most computational approaches with deep learning techniques either focus on designing novel molecular representation or combining with some advanced models together. However, researchers pay fewer attention to the potential benefits in massive unlabeled molecular data (e.g., ZINC). This task becomes increasingly challenging owing to the limitation of the scale of labeled data. Motivated by the recent advancements of pretrained models in natural language processing, the drug molecule can be naturally viewed as language to some extent. In this paper, we investigate how to develop the pretrained model BERT to extract useful molecular substructure information for molecular property prediction. We present a novel end-to-end deep learning framework, named Mol-BERT, that combines an effective molecular representation with pretrained BERT model tailored for molecular property prediction. Specifically, a large-scale prediction BERT model is pretrained to generate the embedding of molecular substructures, by using four million unlabeled drug SMILES (i.e., ZINC 15 and ChEMBL 27). Then, the pretrained BERT model can be fine-tuned on various molecular property prediction tasks. To examine the performance of our proposed Mol-BERT, we conduct several experiments on 4 widely used molecular datasets. In comparison to the traditional and state-of-the-art baselines, the results illustrate that our proposed Mol-BERT can outperform the current sequence-based methods and achieve at least 2% improvement on ROC-AUC score on Tox21, SIDER, and ClinTox dataset.

Download Full-text

TableNN: Deep Learning Framework for Learning Domain Specific Tabular Data

10.1109/bigdata52589.2021.9671972 ◽

2021 ◽

Author(s):

Pranav Sankhe ◽

Elham Khabiri ◽

Bhavna Agrawal ◽

Yingjie Li

Keyword(s):

Deep Learning ◽

Tabular Data ◽

Learning Framework ◽

Domain Specific

Download Full-text

Minimal Linear Networks for Magnetic Resonance Image Reconstruction

Scientific Reports ◽

10.1038/s41598-019-55763-x ◽

2019 ◽

Vol 9 (1) ◽

Cited By ~ 1

Author(s):

Gilad Liberman ◽

Benedikt A. Poser

Keyword(s):

Deep Learning ◽

Magnetic Resonance ◽

Image Reconstruction ◽

Simulated Data ◽

Linear Networks ◽

Learning Framework ◽

Scan Time ◽

Learning Techniques ◽

Ill Posed ◽

Magnetic Resonance Imaging Mri

AbstractModern sequences for Magnetic Resonance Imaging (MRI) trade off scan time with computational challenges, resulting in ill-posed inverse problems and the requirement to account for more elaborated signal models. Various deep learning techniques have shown potential for image reconstruction from reduced data, outperforming compressed sensing, dictionary learning and other advanced techniques based on regularization, by characterization of the image manifold. In this work we suggest a framework for reducing a “neural” network to the bare minimum required by the MR physics, reducing the network depth and removing all non-linearities. The networks performed well both on benchmark simulated data and on arterial spin labeling perfusion imaging, showing clear images while preserving sensitivity to the minute signal changes. The results indicate that the deep learning framework plays a major role in MR image reconstruction, and suggest a concrete approach for probing into the contribution of additional elements.

Download Full-text

A Robust Deep Learning-Based Fault Diagnosis Method for Rotating Machinery

10.20944/preprints202005.0349.v1 ◽

2020 ◽

Author(s):

Greg Smith ◽

John Lundberg ◽

Masayoshi Shibatani

Keyword(s):

Deep Learning ◽

Domain Adaptation ◽

Operating Conditions ◽

Machine Learning Techniques ◽

The Real ◽

Practical Applications ◽

Promising Tool ◽

Cross Domain ◽

Learning Techniques ◽

Diagnosis Method

In the recent years, intelligent data-driven faultdiagnosis methods on gearboxes have been successfully developedand popularly applied in the industries. Currently, most ofthe machine learning techniques require that the training andtesting data are from the same distribution. However, thisassumption is difficult to be met in the real industries, sincethe gearbox operating conditions usually change in practice,which results in significant data distribution gap and diagnosticperformance deteriorations in applying the learned knowledgeon the new conditions. This paper proposes a deep learning-based domain adaptation method to address this issue. Theraw current signals are directly used as the model inputs fordiagnostics, which are easy to collect in the real industries andfacilitate practical applications. The maximum mean discrepancymetric is introduced to the deep neural network, the optimizationof which guarantees the extraction of generalized machineryhealth condition features across different operating conditions.The experiments on a real-world gearbox condition monitoringdataset validate the effectiveness of the proposed method, whichoffers a promising tool for cross-domain diagnosis in the realindustries.

Download Full-text

FiberNET: An ensemble deep learning framework for clustering white matter fibers

10.1101/141036 ◽

2017 ◽

Author(s):

Vikash Gupta ◽

Sophia I. Thomopoulos ◽

Faisal M. Rashid ◽

Paul M. Thompson

Keyword(s):

Deep Learning ◽

White Matter ◽

Structural Integrity ◽

Region Of Interest ◽

Fiber Bundles ◽

Anatomical Connectivity ◽

Learning Framework ◽

Fiber Clustering ◽

Learning Techniques ◽

The Brain

AbstractWhite matter tracts are commonly analyzed in studies of micro-structural integrity and anatomical connectivity in the brain. Over the last decade, it has been an open problem as to how best to cluster white matter fibers, extracted from whole-brain tractography, into anatomically meaningful groups. Some existing techniques use region of interest (ROI) based clustering, atlas-based labeling, or unsupervised spectral clustering. ROI-based clustering is popular for analyzing anatomical connectivity among a set of ROIs, but it does not always partition the brain into recognizable fiber bundles. Here we propose an approach using convolutional neural networks (CNNs) to learn shape features of the fiber bundles, which are then exploited to cluster white matter fibers. To achieve such clustering, we first need to re-parameterize the fibers in an intrinsic space. The clustering is performed in induced parameterized coordinates. To our knowledge, this is one of the first approaches for fiber clustering using deep learning techniques. The results show strong accuracy - on a par with or better than other state-of-the-art methods.

Download Full-text

Deep Learning Techniques Revolutionize E&P – Two practical applications

10.3997/2214-4609.202130009 ◽

2021 ◽

Author(s):

C. Jaikla ◽

E. Alkan ◽

C. Sutton ◽

Y. Cai ◽

S. Mannava ◽

...

Keyword(s):

Deep Learning ◽

Practical Applications ◽

Learning Techniques

Download Full-text

Emotional sounds of crowds: spectrogram-based analysis using deep learning

Multimedia Tools and Applications ◽

10.1007/s11042-020-09428-x ◽

2020 ◽

Vol 79 (47-48) ◽

pp. 36063-36075 ◽

Cited By ~ 1

Author(s):

Valentina Franzoni ◽

Giulio Biondi ◽

Alfredo Milani

Keyword(s):

Neural Network ◽

Deep Learning ◽

Convolutional Neural Network ◽

Critical Question ◽

Domain Specific ◽

Visual Knowledge ◽

Learning Techniques ◽

Proposed Model ◽

Political Demonstrations ◽

Fine Tune

AbstractCrowds express emotions as a collective individual, which is evident from the sounds that a crowd produces in particular events, e.g., collective booing, laughing or cheering in sports matches, movies, theaters, concerts, political demonstrations, and riots. A critical question concerning the innovative concept of crowd emotions is whether the emotional content of crowd sounds can be characterized by frequency-amplitude features, using analysis techniques similar to those applied on individual voices, where deep learning classification is applied to spectrogram images derived by sound transformations. In this work, we present a technique based on the generation of sound spectrograms from fragments of fixed length, extracted from original audio clips recorded in high-attendance events, where the crowd acts as a collective individual. Transfer learning techniques are used on a convolutional neural network, pre-trained on low-level features using the well-known ImageNet extensive dataset of visual knowledge. The original sound clips are filtered and normalized in amplitude for a correct spectrogram generation, on which we fine-tune the domain-specific features. Experiments held on the finally trained Convolutional Neural Network show promising performances of the proposed model to classify the emotions of the crowd.

Download Full-text

AgriPest: A Large-Scale Domain-Specific Benchmark Dataset for Practical Agricultural Pest Detection in the Wild

Sensors ◽

10.3390/s21051601 ◽

2021 ◽

Vol 21 (5) ◽

pp. 1601

Author(s):

Rujing Wang ◽

Liu Liu ◽

Chengjun Xie ◽

Po Yang ◽

Rui Li ◽

...

Keyword(s):

Deep Learning ◽

Large Scale ◽

Benchmark Dataset ◽

Domain Specific ◽

Pest Monitoring ◽

Field Environment ◽

Learning Techniques ◽

Monitoring Applications ◽

In The Wild ◽

Bounding Boxes

The recent explosion of large volume of standard dataset of annotated images has offered promising opportunities for deep learning techniques in effective and efficient object detection applications. However, due to a huge difference of quality between these standardized dataset and practical raw data, it is still a critical problem on how to maximize utilization of deep learning techniques in practical agriculture applications. Here, we introduce a domain-specific benchmark dataset, called AgriPest, in tiny wild pest recognition and detection, providing the researchers and communities with a standard large-scale dataset of practically wild pest images and annotations, as well as evaluation procedures. During the past seven years, AgriPest captures 49.7K images of four crops containing 14 species of pests by our designed image collection equipment in the field environment. All of the images are manually annotated by agricultural experts with up to 264.7K bounding boxes of locating pests. This paper also offers a detailed analysis of AgriPest where the validation set is split into four types of scenes that are common in practical pest monitoring applications. We explore and evaluate the performance of state-of-the-art deep learning techniques over AgriPest. We believe that the scale, accuracy, and diversity of AgriPest can offer great opportunities to researchers in computer vision as well as pest monitoring applications.

Download Full-text

Parallel Deep Learning Framework for Video Surveillance System

10.3233/apc210191 ◽

2021 ◽

Author(s):

Mayuri Karvande ◽

Apoorv Katkar ◽

Nikhil Koli ◽

Amit Joshi ◽

Suraj Sawant

Keyword(s):

Deep Learning ◽

Video Surveillance ◽

System Performance ◽

System Stability ◽

Camera System ◽

Public Places ◽

Dynamic Selection ◽

Learning Framework ◽

Learning Techniques ◽

The Right

In today’s world, the security of every individual has become an important aspect. There is a need for constant monitoring in public places. A Manual operating camera system is an unreliable and very basic and poor method for this purpose. Intelligent Video Surveillance is an approach where multiple CCTVs constantly record the scenes and proper algorithms are deployed in order to detect and monitor activities. Deep Learning frameworks and algorithms like Kera’s, YOLO, Convolutional Neural Networks or backbones for image detection like VGG16, Mobile net, Resnet101 have been used for human and weapon detection. The paper focuses on deep learning techniques and threading to collectively develop a Parallel Deep Learning Framework for Video Surveillance that aims at striking the right balance between accuracy and system performance or stability. Threading is used in terms of implementation of a uniquely proposed Dynamic Selection Algorithm that uses two backbones for object detection and switches between them based on the queue status for achieving system stability. A uniquely designed logistic regression filter is also implemented that boosts the system performance.

Download Full-text