scholarly journals Spatial Context-Based Local Toponym Extraction and Chinese Textual Address Segmentation from Urban POI Data

2020 ◽  
Vol 9 (3) ◽  
pp. 147 ◽  
Author(s):  
Xi Kuai ◽  
Renzhong Guo ◽  
Zhijun Zhang ◽  
Biao He ◽  
Zhigang Zhao ◽  
...  
Keyword(s):  
Input Data ◽  
Geographic Area ◽  
Spatial Context ◽  
Second Step ◽  
Chinese Word Segmentation ◽  
Textual Information ◽  
Points Of Interest ◽  
Data Source ◽  
Series Of Experiments ◽  
Segmentation Models

Georeferencing by place names (known as toponyms) is the most common way of associating textual information with geographic locations. While computers use numeric coordinates (such as longitude-latitude pairs) to represent places, people generally refer to places via their toponyms. Query by toponym is an effective way to find information about a geographic area. However, segmenting and parsing textual addresses to extract local toponyms is a difficult task in the geocoding field, especially in China. In this paper, a local spatial context-based framework is proposed to extract local toponyms and segment Chinese textual addresses. We collect urban points of interest (POIs) as an input data source; in this dataset, the textual address and geospatial position coordinates correspond at a one-to-one basis and can be easily used to explore the spatial distribution of local toponyms. The proposed framework involves two steps: address element identification and local toponym extraction. The first step identifies as many address element candidates as possible from a continuous string of textual addresses for each urban POI. The second step focuses on merging neighboring candidate pairs into local toponyms. A series of experiments are conducted to determine the thresholds for local toponym extraction based on precision-recall curves. Finally, we evaluate our framework by comparing its performance with three well-known Chinese word segmentation models. The comparative experimental results demonstrate that our framework achieves a better performance than do other models.

scholarly journals Inductive learning and local differential privacy for privacy-preserving offloading in mobile edge intelligent systems

2021 ◽  
Author(s):  
Jude TCHAYE-KONDI ◽  
Yanlong Zhai ◽  
Liehuang Zhu
Keyword(s):  
Intelligent Systems ◽  
Differential Privacy ◽  
Inductive Learning ◽  
Random Noise ◽  
Privacy Preserving ◽  
Sensitive Data ◽  
Privacy Concerns ◽  
Feature Extractor ◽  
Data Source ◽  
Series Of Experiments

<div>We address privacy and latency issues in the edge/cloud computing environment while training a centralized AI model. In our particular case, the edge devices are the only data source for the model to train on the central server. Current privacy-preserving and reducing network latency solutions rely on a pre-trained feature extractor deployed on the devices to help extract only important features from the sensitive dataset. However, finding a pre-trained model or pubic dataset to build a feature extractor for certain tasks may turn out to be very challenging. With the large amount of data generated by edge devices, the edge environment does not really lack data, but its improper access may lead to privacy concerns. In this paper, we present DeepGuess , a new privacy-preserving, and latency aware deeplearning framework. DeepGuess uses a new learning mechanism enabled by the AutoEncoder(AE) architecture called Inductive Learning, which makes it possible to train a central neural network using the data produced by end-devices while preserving their privacy. With inductive learning, sensitive data remains on devices and is not explicitly involved in any backpropagation process. The AE’s Encoder is deployed on devices to extracts and transfers important features to the server. To enhance privacy, we propose a new local deferentially private algorithm that allows the Edge devices to apply random noise to features extracted from their sensitive data before transferred to an untrusted server. The experimental evaluation of DeepGuess demonstrates its effectiveness and ability to converge on a series of experiments.</div>

scholarly journals A robust method to identify cyclone tracks from gridded data

2010 ◽  
Vol 4 (1) ◽  
pp. 105-114 ◽  
Author(s):  
F. Kreienkamp ◽  
A. Spekat ◽  
W. Enke
Keyword(s):  
Input Data ◽  
Grid Point ◽  
Storm Track ◽  
Atmospheric Dynamics ◽  
Storm Tracks ◽  
Second Step ◽  
Small Scale ◽  
Gridded Data ◽  
Robust Method ◽  
Space Order

Abstract. A system to derive tracks of barometric minima is presented. It is deliberately using coarse input data in space (order of 2°×2°) and time (6-hourly to daily) as well as information from just one geopotential level. It is argued that the results are, for one robust in the sense of an assumption of the IMILAST Project that the use of as simple as possible metrics should be strived for and for two tailored to the input from reanalyses and GCMs. The methodology presented is a necessary first step towards an automated storm track recognition scheme which will be employed in a second paper to study the future development of atmospheric dynamics in a changing climate. The process towards obtaining storm tracks is two-fold. In its first step cyclone centers are being identified. The performance of this step requires the existence of closed isolines, i.e., a topology in which a grid-point is surrounded by neighbours which all exhibit higher geopotential. The usage of this topology requirement as well as the constraint of coarse data may lead, though, to limitations in identifying centers in geopotential fields with shallow gradients that may occur in the summer months; moreover, some centers may potentially be missed in case of a configuration in which a small scale storm is located at the perimeter of a deep and very large low (a kind of "dent in a crater wall"). The second step of the process strings the identified cyclone centers together in a meaningful way to form tracks. By way of several examples the capability to identify known storm tracks is shown.

scholarly journals Partition Learning for Multiagent Planning

2012 ◽  
Vol 2012 ◽  
pp. 1-14 ◽  
Author(s):  
Jared Wood ◽  
J. Karl Hedrick
Keyword(s):  
Autonomous Agents ◽  
Geographic Area ◽  
Standard Approach ◽  
Second Step ◽  
Development Effort ◽  
New Approach ◽  
Target Track ◽  
Significant Research ◽  
Automated Surveillance ◽  
Multiagent Planning

Automated surveillance of large geographic areas and target tracking by a team of autonomous agents is a topic that has received significant research and development effort. The standard approach is to decompose this problem into two steps. The first step is target track estimation and the second step is path planning by optimizing directly over target track estimation. This standard approach works well in many scenarios. However, an improved approach is needed for the scenario when general, nonparametric estimation is required, and the number of targets is unknown. The focus of this paper is to present a new approach that inherently handles the task to search for and track anunknownnumber of targets within alargegeographic area. This approach is designed for the case when the search is performed by a team of autonomous agents and target estimation requires general, nonparametric methods. There are consequently very few assumptions made. The only assumption made is that a time-changing target track estimation is available and shared between the agents. This estimation is allowed to be general and nonparametric. Results are provided that compare the performance of this new approach with the standard approach. From these results it is concluded that this new approach improves search and tracking when the number of targets is unknown and target track estimation is general and nonparametric.

scholarly journals Deep Learning-Based Thermal Image Analysis for Pavement Defect Detection and Classification Considering Complex Pavement Conditions

2021 ◽  
Vol 14 (1) ◽  
pp. 106
Author(s):  
Cheng Chen ◽  
Sindhu Chandra ◽  
Yufan Han ◽  
Hyungjoon Seo
Keyword(s):  
Deep Learning ◽  
Damage Detection ◽  
Defect Detection ◽  
Input Data ◽  
Thermal Image ◽  
Detection Accuracy ◽  
Detection Model ◽  
Fused Image ◽  
Data Source ◽  
Pavement Damage

Automatic damage detection using deep learning warrants an extensive data source that captures complex pavement conditions. This paper proposes a thermal-RGB fusion image-based pavement damage detection model, wherein the fused RGB-thermal image is formed through multi-source sensor information to achieve fast and accurate defect detection including complex pavement conditions. The proposed method uses pre-trained EfficientNet B4 as the backbone architecture and generates an argument dataset (containing non-uniform illumination, camera noise, and scales of thermal images too) to achieve high pavement damage detection accuracy. This paper tests separately the performance of different input data (RGB, thermal, MSX, and fused image) to test the influence of input data and network on the detection results. The results proved that the fused image’s damage detection accuracy can be as high as 98.34% and by using the dataset after augmentation, the detection model deems to be more stable to achieve 98.35% precision, 98.34% recall, and 98.34% F1-score.

scholarly journals Effects of Spatial Transformer Location on Segmentation Performance of a Dense Transformer Network

2017 ◽  
Vol 3 (1) ◽  
Author(s):  
David Abou-Chacra ◽  
John Zelek
Keyword(s):  
Input Data ◽  
Spatial Information ◽  
Semantic Segmentation ◽  
Spatial Context ◽  
Class Label ◽  
Spatial Span ◽  
Almost All

Semantic segmentation solves the task of labelling every pixel inan image with its class label, and remains an important unsolvedproblem. While significant work has gone into using deep learningto solve this problem, almost all the existing research uses methodsthat do not make modifications on spatial context considered for thepixel being labelled. Spatial information is an important cue in taskssuch as segmentation, reusing the same spatial span for every pixeland every label may not be the best approach. Spatial TransformerNetworks have shown promising results in improving classificationperformance of existing networks by allowing networks to activelymanipulate their input data to achieve better performance. Our workshows the benefit of incorporating Spatial Transformer Networksand their corresponding decoders into networks tailored to semanticsegmentation. Our experiments show an improvement in performanceover baseline networks when using networks augmentedwith Spatial Transformers.

scholarly journals A Complete Method for Reconstructing an Elevation Surface of 3D Point Clouds

2015 ◽  
Vol 4 (3-4) ◽  
Author(s):  
Van Sinh Nguyen ◽  
Manh Ha Tran ◽  
Ba Cong Nhan
Keyword(s):  
Point Cloud ◽  
Input Data ◽  
Smooth Surface ◽  
Point Clouds ◽  
Triangular Mesh ◽  
Second Step ◽  
Discrete Point ◽  
The Third ◽  
Input Surface ◽  
3D Point Clouds

Reconstructing the surface of 3D point clouds is a reconstruction from a cloud of 3D points to a triangular mesh. This process approximates a discrete point cloud by a continuous/smooth surface depending on the input data and the applications of users. In this paper, we propose a complete method to reconstruct an elevation surface from 3D point clouds. The method consists of three steps. In the first step, we triangulate an elevation surface of 3D point cloud structured in a 3D grid. In the second step, we remove the outward triangles to deal with concave regions on the boundary of the triangular mesh. In the third step, we reconstruct this surface by filling the hole of triangular mesh. Our method could process very fast for triangulating the surface, preserve the topology and characteristic of the input surface after reconstruction.

Following the script: Optical Character Recognition Technology and the British Town and Trade Directory

1997 ◽  
Vol 9 (1-3) ◽  
pp. 1-16
Author(s):  
Tim Coles ◽  
Andrew Alexander ◽  
Gareth Shaw
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
Data Entry ◽  
Historical Research ◽  
Optical Character ◽  
Data Source ◽  
Series Of Experiments

Directories are a universal data source widely used in urban historical research. This paper reports on a series of experiments to explore the applicability of Optical Character Recognition (OCR) technology as a means of mass directory data entry.

Computer Simulated Demonstration of the Actions of Drugs on the Isolated Perfused Mammalian Heart (Langendorff Preparation)

1991 ◽  
Vol 19 (3) ◽  
pp. 316-322
Author(s):  
David G. Dewhurst ◽  
Richard T. Ullyott
Keyword(s):  
Undergraduate Teaching ◽  
Computer Assisted ◽  
Learning Program ◽  
Textual Information ◽  
Langendorff Preparation ◽  
Mammalian Heart ◽  
Teaching Objectives ◽  
Chart Recorder ◽  
Heart Preparation ◽  
Series Of Experiments

A computer-assisted learning program to demonstrate the pharmacological actions of drugs on the isolated, perfused mammalian heart is described. The program is based on a series of experiments (the action of a range of drugs/drug combinations; the action of ions; the effects of increasing preload) which may be performed on the Langendorff heart preparation. Simulated responses (contractile force, heart rate and coronary blood flow) are presented, in high-resolution graphics, for each experiment in a form comparable to a chart recorder display. The program is driven from an easy-to-use menu and contains textual information describing the preparation, the apparatus and the method. A HELP option, in the form of an editable text window, is also available. The potential for using this program in undergraduate teaching and its ability to meet the teaching objectives of laboratory-based practical sessions are discussed.

scholarly journals An accurate fingerprint reference point determination method based on curvature estimation of separated ridges

2018 ◽  
Vol 28 (1) ◽  
pp. 209-225 ◽  
Author(s):  
Rafal Doroz ◽  
Krzysztof Wrobel ◽  
Piotr Porwik
Keyword(s):  
Reference Point ◽  
Reference Points ◽  
Second Step ◽  
Multi Stage ◽  
Stage System ◽  
Series Of Experiments ◽  
Curvature Estimation ◽  
Point Determination ◽  
Point Detection

AbstractThis paper presents an effective method for the detection of a fingerprint’s reference point by analyzing fingerprint ridges’ curvatures. The proposed approach is a multi-stage system. The first step extracts the fingerprint ridges from an image and transforms them into chains of discrete points. In the second step, the obtained chains of points are processed by a dedicated algorithm to detect corners and other points of highest curvature on their planar surface. In a series of experiments we demonstrate that the proposed method based on this algorithm allows effective determination of fingerprint reference points. Furthermore, the proposed method is relatively simple and achieves better results when compared with the approaches known from the literature. The reference point detection experiments were conducted using publicly available fingerprint databases FVC2000, FVC2002, FVC2004 and NIST

Sign in / Sign up

Export Citation Format

Share Document