scholarly journals Hierarchical Classification of Urban ALS Data by Using Geometry and Intensity Information

Sensors ◽  
2019 ◽  
Vol 19 (20) ◽  
pp. 4583 ◽  
Author(s):  
Xiaoqiang Liu ◽  
Yanming Chen ◽  
Shuyi Li ◽  
Liang Cheng ◽  
Manchun Li
Keyword(s):  
Supervised Learning ◽  
Laser Scanning ◽  
Large Scale ◽  
Three Dimensional ◽  
Hierarchical Classification ◽  
Training Data ◽  
Classification Model ◽  
Learning Method ◽  
Intensity Information

Airborne laser scanning (ALS) can acquire both geometry and intensity information of geo-objects, which is important in mapping a large-scale three-dimensional (3D) urban environment. However, the intensity information recorded by ALS will be changed due to the flight height and atmospheric attenuation, which decreases the robustness of the trained supervised classifier. This paper proposes a hierarchical classification method by separately using geometry and intensity information of urban ALS data. The method uses supervised learning for stable geometry information and unsupervised learning for fluctuating intensity information. The experiment results show that the proposed method can utilize the intensity information effectively, based on three aspects, as below. (1) The proposed method improves the accuracy of classification result by using intensity. (2) When the ALS data to be classified are acquired under the same conditions as the training data, the performance of the proposed method is as good as the supervised learning method. (3) When the ALS data to be classified are acquired under different conditions from the training data, the performance of the proposed method is better than the supervised learning method. Therefore, the classification model derived from the proposed method can be transferred to other ALS data whose intensity is inconsistent with the training data. Furthermore, the proposed method can contribute to the hierarchical use of some other ALS information, such as multi-spectral information.

scholarly journals Automated Localization and Classification of Expressway Pole-Like Road Facilities from Mobile Laser Scanning Data

2020 ◽  
Vol 2020 ◽  
pp. 1-18
Author(s):  
Tran Thanh Ha ◽  
Taweep Chaisomphob
Keyword(s):  
Laser Scanning ◽  
Large Scale ◽  
Three Dimensional ◽  
Point Clouds ◽  
Advanced Technology ◽  
Promising Alternative ◽  
Knowledge Based ◽  
Road Mapping ◽  
Vertical Height

Mobile LiDAR is an emerging advanced technology for capturing three-dimensional road information at a large scale effectively and precisely. Pole-like road facilities are crucial street infrastructures as they provide valuable information for road mapping and road inventory. Thus, the automated localization and classification of road facilities are necessary. This paper proposes a voxel-based method to detect and classify pole-like objects in an expressway environment based on the spatially independent and vertical height continuity analysis. First, the ground points are eliminated, and the nonground points are merged into clusters. Second, the pole-like objects are extracted using horizontal cross section analysis and minimum vertical height criteria. Finally, a set of knowledge-based rules, which comprise height features and geometric shape, is constructed to classify the detected road poles into different types of road facilities. Two test sites of point clouds in an expressway environment, which are located in Bangkok, Thailand, are used to assess the proposed method. The proposed method extracts the pole-like road facilities from two datasets with a detection rate of 95.1% and 93.5% and an overall quality of 89.7% and 98.0% in the classification stage, respectively. This shows that the algorithm could be a promising alternative for the localization and classification of pole-like road facilities with acceptable accuracy.

scholarly journals A Classification Model of Legal Consulting Questions Based on Multi-Attention Prototypical Networks

2021 ◽  
Vol 14 (1) ◽  
Author(s):  
Jianzhou Feng ◽  
Jinman Cui ◽  
Qikai Wei ◽  
Zhengji Zhou ◽  
Yuxiong Wang
Keyword(s):  
Supervised Learning ◽  
Language Processing ◽  
Text Classification ◽  
Question Answering ◽  
Training Data ◽  
Classification Model ◽  
Great Progress ◽  
Public Datasets ◽  
The Cost

AbstractText classification is a research hotspot in the field of natural language processing. Existing text classification models based on supervised learning, especially deep learning models, have made great progress on public datasets. But most of these methods rely on a large amount of training data, and these datasets coverage is limited. In the legal intelligent question-answering system, accurate classification of legal consulting questions is a necessary prerequisite for the realization of intelligent question answering. However, due to lack of sufficient annotation data and the cost of labeling is high, which lead to the poor effect of traditional supervised learning methods under sparse labeling. In response to the above problems, we construct a few-shot legal consulting questions dataset, and propose a prototypical networks model based on multi-attention. For the same category of instances, this model first highlights the key features in the instances as much as possible through instance-dimension level attention. Then it realizes the classification of legal consulting questions by prototypical networks. Experimental results show that our model achieves state-of-the-art results compared with baseline models. The code and dataset are released on https://github.com/cjm0824/MAPN.

scholarly journals Uncertainty-Aware Deep Learning-Based Cardiac Arrhythmias Classification Model of Electrocardiogram Signals

Computers ◽  
2021 ◽  
Vol 10 (6) ◽  
pp. 82
Author(s):  
Ahmad O. Aseeri
Keyword(s):  
Deep Learning ◽  
Cardiac Arrhythmias ◽  
Large Scale ◽  
Clinical Decision Making ◽  
Probabilistic Approach ◽  
Classification Model ◽  
Gating Mechanism ◽  
Uncertainty Estimates ◽  
Wide Range

Deep Learning-based methods have emerged to be one of the most effective and practical solutions in a wide range of medical problems, including the diagnosis of cardiac arrhythmias. A critical step to a precocious diagnosis in many heart dysfunctions diseases starts with the accurate detection and classification of cardiac arrhythmias, which can be achieved via electrocardiograms (ECGs). Motivated by the desire to enhance conventional clinical methods in diagnosing cardiac arrhythmias, we introduce an uncertainty-aware deep learning-based predictive model design for accurate large-scale classification of cardiac arrhythmias successfully trained and evaluated using three benchmark medical datasets. In addition, considering that the quantification of uncertainty estimates is vital for clinical decision-making, our method incorporates a probabilistic approach to capture the model’s uncertainty using a Bayesian-based approximation method without introducing additional parameters or significant changes to the network’s architecture. Although many arrhythmias classification solutions with various ECG feature engineering techniques have been reported in the literature, the introduced AI-based probabilistic-enabled method in this paper outperforms the results of existing methods in outstanding multiclass classification results that manifest F1 scores of 98.62% and 96.73% with (MIT-BIH) dataset of 20 annotations, and 99.23% and 96.94% with (INCART) dataset of eight annotations, and 97.25% and 96.73% with (BIDMC) dataset of six annotations, for the deep ensemble and probabilistic mode, respectively. We demonstrate our method’s high-performing and statistical reliability results in numerical experiments on the language modeling using the gating mechanism of Recurrent Neural Networks.

Semi-Supervised Classification and its Application to Filtering IDS False Positives

2013 ◽  
Vol 427-429 ◽  
pp. 2309-2312
Author(s):  
Hai Bin Mei ◽  
Ming Hua Zhang
Keyword(s):  
Supervised Learning ◽  
Supervised Classification ◽  
Classification Performance ◽  
False Positives ◽  
Training Data ◽  
Classification Model ◽  
Classification Technique

Alert classifiers built with the supervised classification technique require large amounts of labeled training alerts. Preparing for such training data is very difficult and expensive. Thus accuracy and feasibility of current classifiers are greatly restricted. This paper employs semi-supervised learning to build alert classification model to reduce the number of needed labeled training alerts. Alert context properties are also introduced to improve the classification performance. Experiments have demonstrated the accuracy and feasibility of our approach.

scholarly journals Multi-Task Self-Supervised Learning for Disfluency Detection

2020 ◽  
Vol 34 (05) ◽  
pp. 9193-9200
Author(s):  
Shaolei Wang ◽  
Wangxiang Che ◽  
Qi Liu ◽  
Pengda Qin ◽  
Ting Liu ◽  
...  
Keyword(s):  
Supervised Learning ◽  
Large Scale ◽  
Experimental Results ◽  
Training Data ◽  
Competitive Performance ◽  
Test Set ◽  
Full Dataset ◽  
Sentence Classification ◽  
Trained Network

Most existing approaches to disfluency detection heavily rely on human-annotated data, which is expensive to obtain in practice. To tackle the training data bottleneck, we investigate methods for combining multiple self-supervised tasks-i.e., supervised tasks where data can be collected without manual labeling. First, we construct large-scale pseudo training data by randomly adding or deleting words from unlabeled news data, and propose two self-supervised pre-training tasks: (i) tagging task to detect the added noisy words. (ii) sentence classification to distinguish original sentences from grammatically-incorrect sentences. We then combine these two tasks to jointly train a network. The pre-trained network is then fine-tuned using human-annotated disfluency detection training data. Experimental results on the commonly used English Switchboard test set show that our approach can achieve competitive performance compared to the previous systems (trained using the full dataset) by using less than 1% (1000 sentences) of the training data. Our method trained on the full dataset significantly outperforms previous methods, reducing the error by 21% on English Switchboard.

scholarly journals Weighing trees with lasers: advances, challenges and opportunities

2018 ◽  
Vol 8 (2) ◽  
pp. 20170048 ◽  
Author(s):  
M. I. Disney ◽  
M. Boni Vicari ◽  
A. Burt ◽  
K. Calders ◽  
S. L. Lewis ◽  
...  
Keyword(s):  
Laser Scanning ◽  
Large Scale ◽  
Three Dimensional ◽  
Point Clouds ◽  
3D Models ◽  
Tree Form ◽  
Form And Function ◽  
Challenges And Opportunities ◽  
And Function ◽  
Non Destructive

Terrestrial laser scanning (TLS) is providing exciting new ways to quantify tree and forest structure, particularly above-ground biomass (AGB). We show how TLS can address some of the key uncertainties and limitations of current approaches to estimating AGB based on empirical allometric scaling equations (ASEs) that underpin all large-scale estimates of AGB. TLS provides extremely detailed non-destructive measurements of tree form independent of tree size and shape. We show examples of three-dimensional (3D) TLS measurements from various tropical and temperate forests and describe how the resulting TLS point clouds can be used to produce quantitative 3D models of branch and trunk size, shape and distribution. These models can drastically improve estimates of AGB, provide new, improved large-scale ASEs, and deliver insights into a range of fundamental tree properties related to structure. Large quantities of detailed measurements of individual 3D tree structure also have the potential to open new and exciting avenues of research in areas where difficulties of measurement have until now prevented statistical approaches to detecting and understanding underlying patterns of scaling, form and function. We discuss these opportunities and some of the challenges that remain to be overcome to enable wider adoption of TLS methods.

scholarly journals On the utilization of novel spectral laser scanning for three-dimensional classification of vegetation elements

2018 ◽  
Vol 8 (2) ◽  
pp. 20170039 ◽  
Author(s):  
Zhan Li ◽  
Michael Schaefer ◽  
Alan Strahler ◽  
Crystal Schaaf ◽  
David Jupp
Keyword(s):  
Laser Scanning ◽  
Spatial Information ◽  
Information Source ◽  
Three Dimensional ◽  
Laser Scanner ◽  
Biochemical Properties ◽  
Dual Wavelength ◽  
Wavelength Scanning ◽  
Spatial Attributes

The Dual-Wavelength Echidna Lidar (DWEL), a full waveform terrestrial laser scanner (TLS), has been used to scan a variety of forested and agricultural environments. From these scanning campaigns, we summarize the benefits and challenges given by DWEL's novel coaxial dual-wavelength scanning technology, particularly for the three-dimensional (3D) classification of vegetation elements. Simultaneous scanning at both 1064 nm and 1548 nm by DWEL instruments provides a new spectral dimension to TLS data that joins the 3D spatial dimension of lidar as an information source. Our point cloud classification algorithm explores the utilization of both spectral and spatial attributes of individual points from DWEL scans and highlights the strengths and weaknesses of each attribute domain. The spectral and spatial attributes for vegetation element classification each perform better in different parts of vegetation (canopy interior, fine branches, coarse trunks, etc.) and under different vegetation conditions (dead or live, leaf-on or leaf-off, water content, etc.). These environmental characteristics of vegetation, convolved with the lidar instrument specifications and lidar data quality, result in the actual capabilities of spectral and spatial attributes to classify vegetation elements in 3D space. The spectral and spatial information domains thus complement each other in the classification process. The joint use of both not only enhances the classification accuracy but also reduces its variance across the multiple vegetation types we have examined, highlighting the value of the DWEL as a new source of 3D spectral information. Wider deployment of the DWEL instruments is in practice currently held back by challenges in instrument development and the demands of data processing required by coaxial dual- or multi-wavelength scanning. But the simultaneous 3D acquisition of both spectral and spatial features, offered by new multispectral scanning instruments such as the DWEL, opens doors to study biophysical and biochemical properties of forested and agricultural ecosystems at more detailed scales.

Combining Self-supervised Learning and Active Learning for Disfluency Detection

2022 ◽  
Vol 21 (3) ◽  
pp. 1-25
Author(s):  
Shaolei Wang ◽  
Zhongyuan Wang ◽  
Wanxiang Che ◽  
Sendong Zhao ◽  
Ting Liu
Keyword(s):  
Neural Network ◽  
Active Learning ◽  
Supervised Learning ◽  
Large Scale ◽  
Training Data ◽  
Fine Tuning ◽  
Training Dataset ◽  
Performance Gap ◽  
Annotation Costs ◽  
Trained Neural Network

Spoken language is fundamentally different from the written language in that it contains frequent disfluencies or parts of an utterance that are corrected by the speaker. Disfluency detection (removing these disfluencies) is desirable to clean the input for use in downstream NLP tasks. Most existing approaches to disfluency detection heavily rely on human-annotated data, which is scarce and expensive to obtain in practice. To tackle the training data bottleneck, in this work, we investigate methods for combining self-supervised learning and active learning for disfluency detection. First, we construct large-scale pseudo training data by randomly adding or deleting words from unlabeled data and propose two self-supervised pre-training tasks: (i) a tagging task to detect the added noisy words and (ii) sentence classification to distinguish original sentences from grammatically incorrect sentences. We then combine these two tasks to jointly pre-train a neural network. The pre-trained neural network is then fine-tuned using human-annotated disfluency detection training data. The self-supervised learning method can capture task-special knowledge for disfluency detection and achieve better performance when fine-tuning on a small annotated dataset compared to other supervised methods. However, limited in that the pseudo training data are generated based on simple heuristics and cannot fully cover all the disfluency patterns, there is still a performance gap compared to the supervised models trained on the full training dataset. We further explore how to bridge the performance gap by integrating active learning during the fine-tuning process. Active learning strives to reduce annotation costs by choosing the most critical examples to label and can address the weakness of self-supervised learning with a small annotated dataset. We show that by combining self-supervised learning with active learning, our model is able to match state-of-the-art performance with just about 10% of the original training data on both the commonly used English Switchboard test set and a set of in-house annotated Chinese data.

Classification Methods

2011 ◽  
pp. 196-201 ◽  
Author(s):  
Aijun An
Keyword(s):  
Unsupervised Learning ◽  
Supervised Learning ◽  
Credit Card ◽  
A Priori ◽  
Training Data ◽  
Classification Model ◽  
Highly Active ◽  
Data Object ◽  
Patient Database ◽  
Data Objects

Generally speaking, classification is the action of assigning an object to a category according to the characteristics of the object. In data mining, classification refers to the task of analyzing a set of pre-classified data objects to learn a model (or a function) that can be used to classify an unseen data object into one of several predefined classes. A data object, referred to as an example, is described by a set of attributes or variables. One of the attributes describes the class that an example belongs to and is thus called the class attribute or class variable. Other attributes are often called independent or predictor attributes (or variables). The set of examples used to learn the classification model is called the training data set. Tasks related to classification include regression, which builds a model from training data to predict numerical values, and clustering, which groups examples to form categories. Classification belongs to the category of supervised learning, distinguished from unsupervised learning. In supervised learning, the training data consists of pairs of input data (typically vectors), and desired outputs, while in unsupervised learning there is no a priori output. Classification has various applications, such as learning from a patient database to diagnose a disease based on the symptoms of a patient, analyzing credit card transactions to identify fraudulent transactions, automatic recognition of letters or digits based on handwriting samples, and distinguishing highly active compounds from inactive ones based on the structures of compounds for drug discovery.

Sign in / Sign up

Export Citation Format

Share Document