Real-time prediction of gas leakage and diffusion for buried natural gas pipelines by deep learning and dimensionality reduction methods

Review of classical dimensionality reduction and sample selection methods for large-scale data processing

Experimental study on distributed optical-fiber cable for high-pressure buried natural gas pipeline leakage monitoring

Electronic mail, or email, is a method for com-municating using the internet which is inexpensive, effective, and fast. Spam is a type of email where unwanted messages, usually unwanted commercial messages, are distributed in large quantities by a spammer. The objective of such behavior is to harm email users; these messages need to be detected and prevented from being sent to users in the first place. In order to filter these emails, the developers have used machine learning methods. This paper discusses different methods which are used deep learning methods such as a Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) models with(out) a GloVe model in order to classify spam and non-spam messages. These models are only based on email data, and the extraction set of features is automatic. In addition, our work provides a comparison between traditional machine learning and deep learning algorithms on spam datasets to find out the best way to intrusion detection. The results indicate that deep learning offers improved performance of precision, recall, and accuracy. As far as we are aware, deep learning methods show great promise in being able to filter email spam, therefore we have performed a comparison of various deep learning methods with traditional machine learning methods. Using a benchmark dataset consisting of 5,243 spam and 16,872 not-spam and SMS messages, the highest achieved accuracy score is 96.52% using CNN with the GloVe model.

The pedestrian re-identification problem (i.e., re-id) is essential and pre-requisite in multi-camera video surveillance studies, provided the fact that pedestrian targets need to be accurately re-identified across a network of multiple cameras with non-overlapping fields of views before other post-hoc high-level utilizations (i.e., tracking, behaviors analyses, activities monitoring, etc.) can be carried out. Driven by recent developments in deep learning techniques, the important re-id problem is often tackled via either deep discriminant learning or deep generative learning techniques. However, most contemporary deep learning-based models with tremendously deep structures are not easy to be trained because of the notorious vanishings gradient problem. In this study, a novel full-scaled deep discriminant learning model is proposed. The novelty of the full-scale model is significant, as three crucial concepts in designing a deep learning model, including depth, width, and cardinality, are all taken into consideration, simultaneously. Therefore, the new model needs not to be tremendously deep but is more convenient to be trained. Moreover, based on the new model, a novel deep metric learning method is proposed to further solve the important re-id problem. Technically, two algorithms either based on the conventional SGD (stochastic gradient descent) or an alternative more efficient PGD (proximal gradient descent) are both derived. For experimental analyses, the newly introduced full-scaled deep metric learning method has been comprehensively compared with dozens of popular re-id methods proposed from either deep learning or shallow learning perspectives. Several well-known public re-id datasets have been incorporated and rigorous statistical analyses have been carried out to compare all methods regarding their re-id performance. The superiority of the novel full-scaled deep metric learning method has been substantiated, from the statistical point of view.

Deep learning methods have become popular among researchers in the field of fault detection. However, their performance depends on the availability of big datasets. To overcome this problem researchers started applying transfer learning to achieve good performance from small available datasets, by leveraging multiple prediction models over similar machines and working conditions. However, the influence of negative transfer limits their application. Negative transfer among prediction models increases when the environment and working conditions are changing continuously. To overcome the effect of negative transfer, we propose a novel deep transfer learning method, coined deep boosted transfer learning, for wind turbine gearbox fault detection that prevents negative transfer and only focuses on relevant information from the source machine. The proposed method is an instance-based deep transfer learning method that updates the weights of the source and the target machine training samples separately. The weights of different source training samples are gradually decreased to reduce the impact on the final model. The proposed method is verified by the Case Western Reserve University bearing and real field wind farm datasets. The results show that the proposed method ignores negative transfer and achieves higher accuracy compared to standard deep learning and deep transfer learning methods.

Speaker recognition is the process of identifying an individual from their voices, and it has been widely applied in many real-world applications. Recently, deep learning has instigated a revolutionary high success rate in speaker recognition. The major advantage of deep learning over conventional methods for speaker recognition is attributed to its representation ability, and the ability to produce highly abstract embedding features from utterances. Recent researches had revealed that deep learning method in learning speaker features from raw data, is strongly depending on a speaker's language. However, only minimal researches had done on deep learning over Vietnamese speaker recognition to present. Nevertheless, this paper has proposed a deep transfer learning method which integrates both transfer learning and deep learning to build models for Vietnamese speaker recognition. Our experimental results indicated that the proposed method is able to build accurate models for Vietnamese speaker recognition.

Machine learning for real-time prediction of complications in critical care: a retrospective study

Comparing ECG-Lead Subsets for Heart Arrhythmias/ECG Patterns Classification: Convolutional Neural Networks and Random Forest

The paper proposes a new method for classifying the LISS IV satellite images using deep learning method. Deep learning method is to automatically extract many features without any human intervention. The classification accuracy through deep learning is still improved by including object-based segmentation. The object-based deep feature learning method using CNN is used to accurately classify the remotely sensed images. The method is designed with the technique of extracting the deep features and using it for object-based classification. The proposed system extracts deep features using pre-defined filter values, thus increasing the overall performance of the process compared to randomly initialized filter values. The object-based classification method can preserve edge information in complex satellite images. To improve the classification accuracy and to reduce complexity, object-based deep learning technique is used. The proposed object-based deep learning approach is used to drastically increase the classification accuracy. Here, the remotely sensed images were used to classify the urban areas of Ahmadabad and Madurai cities. Experimental results show a better performance with the object-based classification.

Assessing Cancer Risk from Mammograms: Deep Learning Is Superior to Conventional Risk Models.

This paper presents an extended set of numerical fragility functions for the structural assessment of buried steel natural gas (NG) pipelines subjected to axial compression caused by transient seismic ground deformations. The study focuses on NG pipelines crossing sites with a vertical geotechnical discontinuity, where high compression straining of a buried pipeline is expected to occur under seismic transient ground deformations. A de-coupled numerical framework is developed for this purpose, which includes a 3D finite element model of the pipe–trench system employed to evaluate rigorously the soil–pipe interaction effects on the pipeline axial response in a quasi-static manner. One-dimensional soil response analyses are used to determine critical ground deformation patterns at the vicinity of the geotechnical discontinuity, caused by the ground shaking. A comprehensive parametric analysis is performed by implementing the proposed analytical framework for an ensemble of 40 recorded earthquake ground motions. Crucial parameters that affect the seismic response and therefore the seismic vulnerability of buried steel NG pipelines namely, the diameter, wall thickness, burial depth and internal pressure of the pipeline, the backfill compaction level, the pipe–soil interface friction characteristics, the soil deposits characteristics, as well as initial geometric imperfections of the walls of the pipeline, are systematically considered. The analytical fragility functions are developed in terms of peak ground velocity at the ground surface, for four performance limit states, considering all the associated uncertainties. The study contributes towards a reliable quantitative risk assessment of buried steel NG pipelines, crossing similar sites, subjected to seismically-induced transient ground deformations.

Optimization problem is an important challenge in two-dimensional (2D) target/anomaly detection as a real-world application. As manual time series drone image interpretation is time-consuming and expensive, deep learning methods are of high interest for 2D target/anomaly detection. Despite 2D target and anomaly detection from time series drone images based on deep learning models is an active field in remote sensing engineering, but annotating remote sensing time series data is costly for training step. To build robust machine learning methods in remote sensing, deep few-shot learning approaches have been developed from real-world and real-time datasets based on drone images in small training data as an optimized solution. In this chapter, we focus on two real-world applications of 2D target/anomaly detection based on a new deep few-shot learning method, which can be widely used in urban management and precision farming. The experiments are based on two time series multispectral datasets, including traffic monitoring (as a target) and weed detection (as an anomaly). Compared with the few-shot learning with different backbones, the proposed method, called SA-Net, demonstrates better performance and good generalization ability for 2D target/anomaly detection.

A practical evaluation of machine learning for classification of ultrasound images of ovarian development in channel catfish (Ictalurus punctatus)

The automatic segmentation of brain tumour from MRI medical images is mainly covered in this review. Recently, state-of-the-art performance is provided by deep learning-based approaches in the field of image classification, segmentation, object detection, and tracking tasks. The core feature deep learning approach is the hierarchical representation of features from images and thus avoiding domain-specific handcrafted features. In this review paper, we have dealt with a Review of Deep Learning Architecture and Methods for MRI Brain Tumour Segmentation. First, we have discussed basic architecture and approaches for deep learning methods. Secondly, we have discussed the literature survey of MRI brain tumour segmentation using deep learning methods and its multimodality fusion. Then, the advantages and disadvantages of each method analyzed and finally concluded the discussion with the merits and challenges of deep learning techniques. The review of brain tumour identification using deep learning Techniques may help the research to have a better focus on it.

Compression and reinforce variation with convolutional neural networks for hyperspectral image classification