scholarly journals Technical Solution Discussion for Key Challenges of Operational Convolutional Neural Network-Based Building-Damage Assessment from Satellite Imagery: Perspective from Benchmark xBD Dataset

2020 ◽  
Vol 12 (22) ◽  
pp. 3808
Author(s):  
Jinhua Su ◽  
Yanbing Bai ◽  
Xingrui Wang ◽  
Dong Lu ◽  
Bo Zhao ◽  
...  
Keyword(s):  
Class Imbalance ◽  
Sampling Technique ◽  
Typical Feature ◽  
Technical Solution ◽  
Satellite Imaging ◽  
Imagery Perspective ◽  
Knowledge Distillation ◽  
Technical Details ◽  
Technical Solutions ◽  
Building Level

Earth Observation satellite imaging helps building diagnosis during a disaster. Several models are put forward on the xBD dataset, which can be divided into two levels: the building level and the pixel level. Models from two levels evolve into several versions that will be reviewed in this paper. There are four key challenges hindering researchers from moving forward on this task, and this paper tries to give technical solutions. First, metrics on different levels could not be compared directly. We put forward a fairer metric and give a method to convert between metrics of two levels. Secondly, drone images may be another important source, but drone data may have only a post-disaster image. This paper shows and compares methods of directly detecting and generating. Thirdly, the class imbalance is a typical feature of the xBD dataset and leads to a bad F1 score for minor damage and major damage. This paper provides four specific data resampling strategies, which are Main-Label Over-Sampling (MLOS), Discrimination After Cropping (DAC), Dilation of Area with Minority (DAM) and Synthetic Minority Over-Sampling Technique (SMOTE), as well as cost-sensitive re-weighting schemes. Fourthly, faster prediction meets the need for a real-time situation. This paper recommends three specific methods, feature-map subtraction, parameter sharing, and knowledge distillation. Finally, we developed our AI-driven Damage Diagnose Platform (ADDP). This paper introduces the structure of ADDP and technical details. Customized settings, interface preview, and upload and download satellite images are major services our platform provides.

scholarly journals Risk Assessment Framework to Avoid Serial Failure for New Technical Solutions Applied to the Construction of a CLT Structure Resilient to Climate

Buildings ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 247
Author(s):  
Charlotte Svensson Tengberg ◽  
Carl-Eric Hagentoft
Keyword(s):  
Risk Assessment ◽  
Success Factors ◽  
Real Life ◽  
Qualitative Assessment ◽  
Technical Solution ◽  
Functional Requirements ◽  
Assessment Framework ◽  
Construction Period ◽  
Design Build ◽  
Technical Solutions

Design-build contractors are challenged with the task of minimizing failure risks when introducing new technical solutions or adapting technical solutions to new conditions, e.g., climate change. They seem to have a disproportional trust in suppliers and their reference cases and might not have adequate resources or methodologies for sufficient evaluation. This creates the potential for serial failures to spread in the construction industry. To mitigate this, it was suggested that a predefined risk assessment framework should be introduced with the aim of providing a prequalification and requirements for the use of the technical solution. The objectives of this paper are to develop a comprehensive risk assessment framework and to explore the framework’s potential to adequately support the design-build contractor’s decisions. The framework uses qualitative assessment, relying on expert workshops and quantitative assessments, with a focus on simulation and probabilities. Tollgates are used to communicate risk assessments to the contractor. The framework is applied to a real-life case study of construction with a CLT-structure for a Swedish design-build contractor, where exposure to precipitation during construction is a key issue. In conclusion, the chosen framework was successful in a design-build contractor context, structuring the process and identifying difficulties in achieving the functional requirements concerning moisture. Three success factors were: documentation and communication, expert involvement, and the use of tollgates. Recommendations to the design-build contractor on construction of CLT structure are to keep construction period short and to use full weather protection on site.

Support for Collaborative Building of a Railway Technical Solution during Tendering

2013 ◽  
Vol 4 (3) ◽  
pp. 103-113 ◽  
Author(s):  
Diana Penciuc ◽  
Marie-Hélène Abel ◽  
Didier Van Den Abeele
Keyword(s):  
Support Needs ◽  
Technical Solution ◽  
Complex Processes ◽  
Collaboration Support ◽  
Technical Solutions ◽  
Background Context ◽  
Division Of Work

As systems become more and more complex, more complex processes, organization and division of work are needed to achieve their conception and realization. The growing difficulty consists in the number and distribution of collaborators in disparate regions on the globe, the multifaceted communities that need to be coordinated in order to assure integration and coherence of their work. It is also the case of building railway technical solutions. The heterogeneity of customer market adds a supplementary challenge: adapt the solution to the customer background, context and real needs. In this context the authors propose a workspace to support collaboration when building customer technical solutions. The authors think that adequate collaboration support needs to be provided for each community and that a common backbone is needed between these communities to assure integration and coherence of their work. This paper gives a model and implementation of a dedicated workspace that can handle collaboration during complex processes like the construction of a railway technical solution.

Organizational Requirements and the Introduction of Information Technology in Courtrooms: A Case Study

1996 ◽  
Vol 11 (1) ◽  
pp. 71-77 ◽  
Author(s):  
David Poulson ◽  
Neil Waddell
Keyword(s):  
Information Technology ◽  
Systems Design ◽  
Technical Solution ◽  
Functional Requirements ◽  
Requirements Definition ◽  
It Systems ◽  
Equal Importance ◽  
Technical Solutions ◽  
Organizational Requirements

Traditional methods of systems design have tended to concentrate on capturing functional requirements and from them develop a system that will provide users with a technical solution to a problem they may have. However, there is a growing understanding, with historical origins in sociotechnical systems theory, that technical solutions alone, regardless of how well designed, may not succeed fully unless there is a concomitant understanding of the organization into which the technical solution is to be introduced. Organizational requirements, therefore, should become considerations of equal importance to systems designers. The ESPRIT Project ORDIT (organizational requirements definition for information technology) has developed a methodology which identifies and operationalizes organizational requirements for IT systems. This paper presents a case study in which the ORDIT concepts are applied to the process of introducing an IT system into a courtroom.

Rainwater propeller pumps structural integrity

2019 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Sergiu Valentin Galatanu ◽  
Sebastian Muntean ◽  
Liviu Marsavina ◽  
Iulian Ionut Ailinei ◽  
Dan Micota
Keyword(s):  
Shear Stress ◽  
Structural Integrity ◽  
Maximum Shear Stress ◽  
Operating Time ◽  
Operation Time ◽  
Technical Solution ◽  
Catastrophic Events ◽  
Impeller Blade ◽  
Content Type ◽  
Technical Solutions

Purpose The purpose of this paper is to focus on the structural integrity of the rainwater propeller pumps installed in the municipal wastewater treatment plant (WTP). Design/methodology/approach A numerical analysis is performed to determine the maximum shear stress on the fasten bolts. The rainwater propeller pump is examined in operation at normal conditions and when one blade is progressively blocked. Findings The failure mechanism of the rainwater pump impeller is determined. Research limitations/implications The fibbers and wastes are discharged together with rainwater during storms with these types of pumps to avoid the flood of the WTP. Several catastrophic events have occurred in service due to the fibbers clog the gap between the impeller blades and the pump casing. The clogging process is partially understood so actual technical solutions deal with effects rather the main causes. Practical implications The operation time of all seven rainwater pumps installed in Timisoara’s WTP is investigated. Climate changes in Banat region and new waste properties found in the wastewater require appropriate technical solutions. A technical solution is proposed based on these investigations to extend the operation time and to diminish the operation and maintenance costs. Social implications These large pumps are installed in the urban sewage centralised system implemented in the most cities. The access to the sewerage network is a requirement of any community, regardless of the social status. Originality/value The fracture surfaces of both fastening bolts of the rainwater pump impellers produced in service are examined. As a result, it has been identified that the catastrophic events are due to the brittle fracture of both fasten bolts between the impeller blades and the pump hub, respectively. The catastrophic events of the rainwater propeller pumps are directly correlated to the clog level of the impeller. The numerical simulation is performed to determine the maximum shear stress on the fasten bolts. The case with pump operating at normal conditions is performed identifying its vulnerabilities to clog conditions. Next, one impeller blade is progressively blocked considering three time stop scenarios associated with different clog levels. Conclusively, the operating time of the rainwater pump up to the catastrophic failure is correlated to the clog level of the impeller.

scholarly journals Improving undersampling-based ensemble with rotation forest for imbalanced problem

2019 ◽  
pp. 1371-1386 ◽  
Author(s):  
Huaping GUO ◽  
Xiaoyu DIAO ◽  
Hongbing LIU
Keyword(s):  
High Performance ◽  
State Of The Art ◽  
Class Imbalance ◽  
Imbalanced Data ◽  
Ensemble Methods ◽  
Sampling Technique ◽  
Robust Methods ◽  
Limited Data ◽  
Minority Class ◽  
Rotation Forest

As one of the most challenging and attractive issues in pattern recognition and machine learning, the imbalanced problem has attracted increasing attention. For two-class data, imbalanced data are characterized by the size of one class (majority class) being much larger than that of the other class (minority class), which makes the constructed models focus more on the majority class and ignore or even misclassify the examples of the minority class. The undersampling-based ensemble, which learns individual classifiers from undersampled balanced data, is an effective method to cope with the class-imbalance data. The problem in this method is that the size of the dataset to train each classifier is notably small; thus, how to generate individual classifiers with high performance from the limited data is a key to the success of the method. In this paper, rotation forest (an ensemble method) is used to improve the performance of the undersampling-based ensemble on the imbalanced problem because rotation forest has higher performance than other ensemble methods such as bagging, boosting, and random forest, particularly for small-sized data. In addition, rotation forest is more sensitive to the sampling technique than some robust methods including SVM and neural networks; thus, it is easier to create individual classifiers with diversity using rotation forest. Two versions of the improved undersampling-based ensemble methods are implemented: 1) undersampling subsets from the majority class and learning each classifier using the rotation forest on the data obtained by combing each subset with the minority class and 2) similarly to the first method, with the exception of removing the majority class examples that are correctly classified with high confidence after learning each classifier for further consideration. The experimental results show that the proposed methods show significantly better performance on measures of recall, g-mean, f-measure, and AUC than other state-of-the-art methods on 30 datasets with various data distributions and different imbalance ratios.

scholarly journals Exploration of Obesity Status of Indonesia Basic Health Research 2013 With Synthetic Minority Over-Sampling Techniques

2021 ◽  
Vol 5 (1) ◽  
pp. 75-91
Author(s):  
Sri Astuti Thamrin ◽  
Dian Sidik ◽  
Hedi Kuswanto ◽  
Armin Lawi ◽  
Ansariadi Ansariadi
Keyword(s):  
Machine Learning ◽  
Health Research ◽  
Class Imbalance ◽  
Imbalanced Data ◽  
Sampling Technique ◽  
Data Sets ◽  
Data Set ◽  
Basic Health ◽  
Obesity Status ◽  
Obese Class

The accuracy of the data class is very important in classification with a machine learning approach. The more accurate the existing data sets and classes, the better the output generated by machine learning. In fact, classification can experience imbalance class data in which each class does not have the same portion of the data set it has. The existence of data imbalance will affect the classification accuracy. One of the easiest ways to correct imbalanced data classes is to balance it. This study aims to explore the problem of data class imbalance in the medium case dataset and to address the imbalance of data classes as well. The Synthetic Minority Over-Sampling Technique (SMOTE) method is used to overcome the problem of class imbalance in obesity status in Indonesia 2013 Basic Health Research (RISKESDAS). The results show that the number of obese class (13.9%) and non-obese class (84.6%). This means that there is an imbalance in the data class with moderate criteria. Moreover, SMOTE with over-sampling 600% can improve the level of minor classes (obesity). As consequence, the classes of obesity status balanced. Therefore, SMOTE technique was better compared to without SMOTE in exploring the obesity status of Indonesia RISKESDAS 2013.

scholarly journals Technical Solution for a Real-Time Air Quality Monitoring System

2020 ◽  
Vol 15 (4) ◽  
Author(s):  
Attila Simo ◽  
Simona Dzitac ◽  
Flaviu Mihai Frigura-Iliasa ◽  
Sorin Musuroi ◽  
Petru Andea ◽  
...  
Keyword(s):  
Air Quality ◽  
Real Time ◽  
Monitoring System ◽  
Quality Monitoring ◽  
Real Field ◽  
Technical Solution ◽  
Air Quality Monitoring ◽  
Single Chip ◽  
Communication Module ◽  
Technical Solutions

This article will present a simple technical solution for a low-power and real-time air quality monitoring system. The whole package of software and hardware technical solutions applied for recording, transmitting and analyzing data is briefly described. This original monitoring system integrates a single chip microcon-troller, several dedicated air pollution surveillance sensors (for PM10, PM2.5, SO2, NO2, CO, O3, VOC, CO2), a LoRaWAN communication module and an online platform. This system was tested and applied under real field conditions. Depending on the measured values, it provides alerts, or, it can lead to the re-placement of specific components in the exhaust equipment. This article will pre-sent some experimental results, validated also by official measurements of government operated air quality stations.

scholarly journals Research on Decision Methods for Technical Solutions Based on Grey-correlation degree to Vapor Recovery of Refined Oil Terminals

2021 ◽  
Vol 252 ◽  
pp. 03054
Author(s):  
Yuanming Jia ◽  
Yiying Zhou ◽  
Hongmei Deng ◽  
Jing li
Keyword(s):  
Decision Model ◽  
Technical Solution ◽  
Refined Oil ◽  
Grey Correlation ◽  
Decision Method ◽  
Correlation Degree ◽  
Decision Methods ◽  
Grey Correlation Analysis ◽  
Grey Correlation Degree ◽  
Technical Solutions

In the process of decision on technical solution to vapor recovery of refined oil terminals, the grey-correlation analysis (GCA) is introduced to optimise technical solutions by building a multi-target decision model and using the sequencing of weighted grey-correlation degree (GCD) of evaluation solution as judgment criteria, to determine the priorities of solutions, and the effectiveness of the decision method is verified by a practical example.

scholarly journals Enhancing Privacy Education with a Technical Emphasis in IT Curriculum

10.28945/2330 ◽  
2016 ◽  
Vol 15 ◽  
pp. 001-017
Author(s):  
Svetlana Peltsverger ◽  
Guangzhi Zheng
Keyword(s):  
Information Technology ◽  
Real World ◽  
Data Protection ◽  
Technical Approach ◽  
Learning Modules ◽  
Hands On ◽  
Privacy Breach ◽  
Hands On Learning ◽  
Technical Details ◽  
Technical Solutions

The paper describes the development of four learning modules that focus on technical details of how a person’s privacy might be compromised in real-world scenarios. The paper shows how students benefited from the addition of hands-on learning experiences of privacy and data protection to the existing information technology courses. These learning modules raised students’ awareness of potential breaches of privacy as a user as well as a developer. The demonstration of a privacy breach in action helped students to design, configure, and implement technical solutions to prevent privacy violations. The assessment results demonstrate the strength of the technical approach.

scholarly journals Arabic Authorship Attribution Using Synthetic Minority Over-sampling Technique and Principal Components Analysis for Imbalanced Documents

2021 ◽  
Vol 15 (4) ◽  
pp. 0-0
Keyword(s):  
Principal Components Analysis ◽  
Principal Components ◽  
Average Length ◽  
Hybrid Approach ◽  
Class Imbalance ◽  
Imbalanced Data ◽  
Sampling Technique ◽  
Authorship Attribution ◽  
Svm Classifier ◽  
Components Analysis

Nowadays, dealing with imbalanced data represents a great challenge in data mining as well as in machine learning task. In this investigation, we are interested in the problem of class imbalance in Authorship Attribution (AA) task, with specific application on Arabic text data. This article proposes a new hybrid approach based on Principal Components Analysis (PCA) and Synthetic Minority Over-sampling Technique (SMOTE), which considerably improve the performances of authorship attribution on imbalanced data. The used dataset contains 7 Arabic books written by 7 different scholars, which are segmented into text segments of the same size, with an average length of 2900 words per text. The obtained results of our experiments show that the proposed approach using the SMO-SVM classifier, presents high performance in terms of authorship attribution accuracy (100%), especially with starting character-bigrams. In addition, the proposed method appears quite interesting by improving the AA performances in imbalanced datasets, mainly with function words.

Sign in / Sign up

Export Citation Format

Share Document