scholarly journals A Systematic Review of Artificial Intelligence Public Datasets for Railway Applications

2021 ◽  
Vol 6 (10) ◽  
pp. 136
Author(s):  
Mauro José Pappaterra ◽  
Francesco Flammini ◽  
Valeria Vittorini ◽  
Nikola Bešinović
Keyword(s):  
Artificial Intelligence ◽  
Traffic Planning ◽  
Time Data ◽  
The Public ◽  
Government Organizations ◽  
Creative Commons ◽  
Railway Industry ◽  
Open Datasets ◽  
Maintenance And Inspection ◽  
Public Datasets

The aim of this paper is to review existing publicly available and open artificial intelligence (AI) oriented datasets in different domains and subdomains of the railway sector. The contribution of this paper is an overview of AI-oriented railway data published under Creative Commons (CC) or any other copyright type that entails public availability and freedom of use. These data are of great value for open research and publications related to the application of AI in the railway sector. This paper includes insights on the public railway data: we distinguish different subdomains, including maintenance and inspection, traffic planning and management, safety and security and type of data including numerical, string, image and other. The datasets reviewed cover the last three decades, from January 1990 to January 2021. The study revealed that the number of open datasets is very small in comparison with the available literature related to AI applications in the railway industry. Another shortcoming is the lack of documentation and metadata on public datasets, including information related to missing data, collection schemes and other limitations. This study also presents quantitative data, such as the number of available open datasets divided by railway application, type of data and year of publication. This review also reveals that there are openly available APIs—maintained by government organizations and train operating companies (TOCs)—that can be of great use for data harvesting and can facilitate the creation of large public datasets. These data are usually well-curated real-time data that can greatly contribute to the accuracy of AI models. Furthermore, we conclude that the extension of AI applications in the railway sector merits a centralized hub for publicly available datasets and open APIs.

scholarly journals PRIVACY PRESERVING ADVANCED SECURITY ON UNTRUSTED CLOUD WITH SELF BACKUP PROCESS

2017 ◽  
Vol 5 (4) ◽  
pp. 176-181
Author(s):  
Sadeer Dheyaa Abdulameer
Keyword(s):  
Cloud Storage ◽  
Service Providers ◽  
Time Data ◽  
The Public ◽  
Government Organizations ◽  
Data Owner ◽  
Cloud Storage Service ◽  
Storage Service ◽  
Problem Data ◽  
Data Consumer

Cloud Storage service are frequently required for many corporate and government organizations. Most of cloud storage service providers are un-trusted, so it is not safe to keep the data in cloud for long period. Many are using cloud storage for data sharing that means it is not possible to send a big file in email, maximum 25 GB are allowed, for big files, files are uploaded in cloud storage and link is given to the data consumer. After Data consumer download the file, Data owner has to delete the file from the cloud for the security reasons, but most of time Data Owner forget to delete the file. To overcome this problem data self-destruction is proposed in many papers and now proposed system has Self-Destruction cum Self-Backup Process, which help the file to stay in the public cloud for certain period of times and it will be removed from the cloud storage and securely stored in another storage.  To verify the integrity of the file HMAC is created while file is uploaded and Data Consumer can able to download the file and generate the HMAC, check the integrity of the file.

scholarly journals Lesion Detection and Classification techniques for Diabetic Retinopathy

2020 ◽  
Vol 9 (3) ◽  
pp. 3436-3441
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Diabetic Retinopathy ◽  
Vision Loss ◽  
Lesion Detection ◽  
Classification Techniques ◽  
The Public ◽  
Detection Systems ◽  
Regular Screening ◽  
Public Datasets

Diabetes is a worldwide spread disease which is increasing rapidly and found in all age people. Diabetic Retinopathy is a retinal abnormality caused by diabetes. Which can lead to permanent vision loss or blindness. As Diabetic Retinopathy pathology damages retina without any early symptoms, it is very important to do the regular screening of retina and detection of Retinopathy. Ophthalmologist does the identification of Retinopathy manually which is time consuming and error prone. Hence, there is a need for early and correct automatic detection of Diabetic Retinopathy. Many researches have done for detection using Image Processing, Artificial Intelligence, Neural Network and Machine Learning. This paper presents a review on Diabetic Retinopathy Detection systems. This review highlights the public datasets available for the evaluation of the detection systems with different segmentation and classification techniques. We have discussed the analysis of different classification and segmentation techniques used in DR detection.

scholarly journals IdeTo: Spreadsheets for Calculation and Analysis of Area Under the Disease Progress Over Time Data

2021 ◽  
pp. PHYTOFR-11-20-0
Author(s):  
Ivan Simko
Keyword(s):  
Correlation Coefficients ◽  
Copyright Law ◽  
Time Data ◽  
Experiment Data ◽  
The Public ◽  
Creative Commons ◽  
Disease Progress ◽  
Progress Curve ◽  
Progression Of Disease ◽  
Over Time

When disease ratings are obtained over time, area under the disease progress metrics such as area under the disease progress curve (AUDPC) and area under the disease progress stairs (AUDPS), which allow integration of these measures into a single value, have found use for both survey or replicated experiment data. IdeTo, an Excel-based calculator, computes AUDPC, AUDPS, and their standardized and relative values for up to 200 individuals evaluated at 200 timepoints. In addition to the areas, descriptive statistics are provided for the group of individuals (e.g., accessions and replicates), and both Pearson and Spearman correlation coefficients between the areas and other traits of interest. Graphs are provided to visualize the progression of disease scores over time, distribution of AUDPC and AUDPS values in the dataset, and their linear correlation with the traits of interest. [Formula: see text] The author(s) have dedicated the work to the public domain under the Creative Commons CC0 “No Rights Reserved” license by waiving all of his or her rights to the work worldwide under copyright law, including all related and neighboring rights, to the extent allowed by law. 2021

scholarly journals Etiology management and COVID-19 death forecast using artificial intelligent based Bayesian learning approach

2021 ◽  
Vol 8 (3) ◽  
pp. 1542
Author(s):  
Mohd Saqib ◽  
Saleem M. Khan ◽  
Danish Suhail
Keyword(s):  
Artificial Intelligence ◽  
Bayesian Learning ◽  
Good Accuracy ◽  
Learning Approach ◽  
Artificial Intelligent ◽  
The Public ◽  
Proposed Model ◽  
Public Datasets ◽  
Progression Prediction ◽  
Death Cases

In 2020, coronavirus disease 2019 (COVID-19), caused by the SARS-CoV-2 (severe acute respiratory syndrome corona virus 2) coronavirus, has become a worldwide natural disaster and has taken form of pandemic. Due to this unforeseen pandemic, humanity had faced many challenges and realized the capability of a human being is not enough to survive in such circumstances. Here, artificial intelligence (AI) comes into the picture which can perform beyond human abilities and enhance the capabilities of a human especially the doctors and health care system. The proposed work is a survey of the areas of COVID-19 where AI can play a big role. There are some areas: death cases prediction, virus progression prediction, disease detection, and drug discovery. In this study we have discussed above mentioned issues and presented a Bayesian learning model to forecast death cases in India. The proposed model predicted with good accuracy and also takes care of uncertainty of predictions. We have fitted Bayesian learning on n-polynomial. This is a completely mathematical model in which we have successfully incorporated with prior knowledge and posterior distribution enables us to incorporate more upcoming data without storing previous data. Our forecast in this study is based on the public datasets provided by John Hopkins University. We are concluding with further evolution and scope of the proposed model.

scholarly journals Using Social Media for the Development of Civic Engagement and Local Governance

2021 ◽  
Author(s):  
Sataporn Roengtam
Keyword(s):  
Social Media ◽  
Local Governance ◽  
Policy Formulation ◽  
Time Data ◽  
The Public ◽  
Government Organizations ◽  
The People ◽  
Use Of Social Media ◽  
Media Applications ◽  
The Impact

The main objective of this study is to propose guidelines for the development of the administration of local government organizations using digital technology, such as the use of social media in the administration. It will be used in the case of promoting public participation in public policy formulation. The information on the features needed to develop operating systems on social media applications would be collected and then trialed. At the same time, data was collected from the experiments. Then, the received information is made into a user manual. The study found that the municipality could use social media to enhance the communication efficiency between municipalities with the public at an efficiency level. At the effectiveness level, people were satisfied with using social media to raise complaints and recommend municipalities. Meanwhile, municipalities can obtain adequate information to use in making operational decisions in comparison with regular operations. And at the impact level, it was found that the municipality could encourage people to participate in the administration of local administrative organizations and support municipalities begin to take new approaches in response to the needs of the people even better.

Towards a Customized¬ Awareness Campaign to Educate the Public about COVID-19: Development and Validation of a Messaging Campaign to Promote Precautionary Behavior Using Geospatial Intelligence in Saudi Arabia (Preprint)

2020 ◽  
Author(s):  
Mayda Alrige ◽  
Hind Bitar Bitar ◽  
Maram Meccawi ◽  
Balakrishnan Mullachery
Keyword(s):  
Artificial Intelligence ◽  
Saudi Arabia ◽  
Content Validity ◽  
Awareness Campaign ◽  
Artificial Intelligence Technique ◽  
The Public ◽  
High Infection ◽  
Local Map ◽  
The City ◽  
Intelligence Technique

BACKGROUND Designing a health promotion campaign is never an easy task, especially during a pandemic of a highly infectious disease, such as Covid-19. In Saudi Arabia, many attempts have been made toward raising the public awareness about Covid-19 infection-level and its precautionary health measures that have to be taken. Although this is useful, most of the health information delivered through the national dashboard and the awareness campaign are very generic and not necessarily make the impact we like to see on individuals’ behavior. OBJECTIVE The objective of this study is to build and validate a customized awareness campaign to promote precautionary health behavior during the COVID-19 pandemic. The customization is realized by utilizing a geospatial artificial intelligence technique called Space-Time Cube (STC) technique. METHODS This research has been conducted in two sequential phases. In the first phase, an initial library of thirty-two messages was developed and validated to promote precautionary messages during the COVID-19 pandemic. This phase was guided by the Fogg Behavior Model (FBM) for behavior change. In phase 2, we applied STC as a Geospatial Artificial Intelligence technique to create a local map for one city representing three different profiles for the city districts. The model was built using COVID-19 clinical data. RESULTS Thirty-two messages were developed based on resources from the World Health Organization and the Ministry of Health in Saudi Arabia. The enumerated content validity of the messages was established through the utilization of Content Validity Index (CVI). Thirty-two messages were found to have acceptable content validity (I-CVI=.87). The geospatial intelligence technique that we used showed three profiles for the districts of Jeddah city: one for high infection, another for moderate infection, and the third for low infection. Combining the results from the first and second phases, a customized awareness campaign was created. This awareness campaign would be used to educate the public regarding the precautionary health behaviors that should be taken, and hence help in reducing the number of positive cases in the city of Jeddah. CONCLUSIONS This research delineates the two main phases to developing a health awareness messaging campaign. The messaging campaign, grounded in FBM, was customized by utilizing Geospatial Artificial Intelligence to create a local map with three district profiles: high-infection, moderate-infection, and low-infection. Locals of each district will be targeted by the campaign based on the level of infection in their district as well as other shared characteristics. Customizing health messages is very prominent in health communication research. This research provides a legitimate approach to customize health messages during the pandemic of COVID-19.

Living machines in our cultural imagination

2018 ◽  
Author(s):  
Michael Szollosy
Keyword(s):  
Artificial Intelligence ◽  
Science Fiction ◽  
Public Perceptions ◽  
Human Condition ◽  
Cultural Imagination ◽  
The Public ◽  
The Enlightenment ◽  
The Future ◽  
Public Imagination ◽  
The Human Condition

Public perceptions of robots and artificial intelligence (AI)—both positive and negative—are hopelessly misinformed, based far too much on science fiction rather than science fact. However, these fictions can be instructive, and reveal to us important anxieties that exist in the public imagination, both towards robots and AI and about the human condition more generally. These anxieties are based on little-understood processes (such as anthropomorphization and projection), but cannot be dismissed merely as inaccuracies in need of correction. Our demonization of robots and AI illustrate two-hundred-year-old fears about the consequences of the Enlightenment and industrialization. Idealistic hopes projected onto robots and AI, in contrast, reveal other anxieties, about our mortality—and the transhumanist desire to transcend the limitations of our physical bodies—and about the future of our species. This chapter reviews these issues and considers some of their broader implications for our future lives with living machines.

scholarly journals A Dynamic Mobility Traffic Model Based on Two Modes of Transport in Smart Cities

Smart Cities ◽  
2021 ◽  
Vol 4 (1) ◽  
pp. 253-270
Author(s):  
Mohammed Bin Hariz ◽  
Dhaou Said ◽  
Hussein T. Mouftah
Keyword(s):  
Data Exchange ◽  
Smart Cities ◽  
Time Data ◽  
School Bus ◽  
The Public ◽  
Ride Sharing ◽  
Dynamic Mobility ◽  
Proposed Model ◽  
Loading System ◽  
Suitable Combination

This paper focuses on transportation models in smart cities. We propose a new dynamic mobility traffic (DMT) scheme which combines public buses and car ride-sharing. The main objective is to improve transportation by maximizing the riders’ satisfaction based on real-time data exchange between the regional manager, the public buses, the car ride-sharing and the riders. OpenStreetMap and OMNET++ were used to implement a realistic scenario for the proposed model in a city like Ottawa. The DMT scheme was compared to a multi-loading system used for a school bus. Simulations showed that rider satisfaction was enhanced when a suitable combination of transportation modes was used. Additionally, compared to the other scheme, this DMT scheme can reduce the stress level of car ride-sharing and public buses during the day to the minimal level.

Research on the strategy of intelligent analysis to improve sports person psychological experience in the era of artificial intelligence

2021 ◽  
pp. 1-11
Author(s):  
Lei Wu ◽  
Juan Wang ◽  
Long Jin ◽  
P. Hemalatha ◽  
R Premalatha
Keyword(s):  
Artificial Intelligence ◽  
Vital Role ◽  
Performance Ratio ◽  
Psychological Experience ◽  
The Public ◽  
Usable Knowledge ◽  
Intelligent Analysis ◽  
Accuracy Ratio ◽  
Depression Level ◽  
Predictive Research

Artificial intelligence (AI) is an excellent potential technology that is evolving day-to-day and a critical avenue for exploration in the world of computer science & engineering. Owing to the vast volume of data and the eventual need to turn this data into usable knowledge and realistic solutions, artificial intelligence approaches and methods have gained substantial prominence in the knowledge economy and community world in general. AI revolutionizes and raises athletics to an entirely different level. Although it is clear that analytics and predictive research have long played a vital role in sports, AI has a massive effect on how games are played, structured, and engaged by the public. Apart from these, AI helps to analyze the mental stability of the athletes. This research proposes the Artificial Intelligence assisted Effective Monitoring System (AIEMS) for the specific intelligent analysis of sports people’s psychological experience. The comparative analysis suggests the best AI strategies for analyzing mental stability using different criteria and resource factors. It is observed that the growth in the present incarnation indicates a promising future concerning AI use in elite athletes. The study ends with the predictive efficiency of particular AI approaches and procedures for further predictive analysis focused on retrospective methods. The experimental results show that the proposed AIEMS model enhances the athlete performance ratio of 98.8%, emotion state prediction of 95.7%, accuracy ratio of 97.3%, perception level of 98.1%, and reduces the anxiety and depression level of 15.4% compared to other existing models.

scholarly journals Sustainable public health partnerships: Results from 41 European, Asian and American regions

2020 ◽  
Vol 30 (Supplement_5) ◽  
Author(s):  
J Ese ◽  
C Ihlebak
Keyword(s):  
Public Health ◽  
Public Sector ◽  
Social Contexts ◽  
Research Literature ◽  
Person Fit ◽  
Time Data ◽  
Incentive Schemes ◽  
The Public ◽  
Health Partnerships ◽  
Group Interviews

Abstract Background Public health problems often constitute so called “wicked problems”, and the importance of involving multiple stakeholders in order to address such problems is acknowledged, for instance through the SDG17 guidelines. Partnerships between academia and the public sector have been deemed especially promising. However, sustainable partnerships might be difficult due to divergent understandings and interests. Although there is a substantial research literature on academic-public partnerships in general, partnerships addressing public health specifically are less investigated. The aim of the project was therefore to identify enablers for sustainable public health partnerships between academia and the public sector. Methods A mixed methods design was used. A survey regarding partnerships was sent to 41 European, Asian and American regions, with a response rate of 72 %. Based on survey data, an interview guide was developed and four best cases (Canada, Bulgaria, the Netherlands and Norway) were identified. Site visits and group interviews with representatives from stakeholders of the partnerships were conducted. Interview data and answers to open ended questions from questionnaires were analysed. Results Three main findings became apparent through the analysis. Important enablers were: 1) person-to-person fit between individuals, 2) national incentive schemes for collaboration, and 3) formal partnership agreements that provided a framework that allowed for manoeuvring. The enablers identified are on a macro, miso and micro level. Furthermore, they can be categorised as political, organisational, and social. Conclusions The data support the notion that partnerships are complex social structures that need to be initiated and managed on different levels and with different measures. At the same time, data demonstrate that across different geographical, political, and social contexts the same enablers are reappearing as important for sustaining public health partnerships. Key messages Similar enablers for sustaining public health partnerships are found across geographical, political, and social contexts. Important enablers for partnerships are person-to-person fit, national incentive schemes, and formal agreements.

Sign in / Sign up

Export Citation Format

Share Document