Filters








7,472 Hits in 6.3 sec

Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety [article]

Sebastian Houben, Stephanie Abrecht, Maram Akila, Andreas Bär, Felix Brockherde, Patrick Feifel, Tim Fingscheidt, Sujan Sai Gannamaneni, Seyed Eghbal Ghobadi, Ahmed Hammam, Anselm Haselhoff, Felix Hauser (+29 others)
2021 arXiv   pre-print
Cyber-physical systems employing DNNs are therefore likely to suffer from safety concerns. In recent years, a zoo of state-of-the-art techniques aiming to address these safety concerns has emerged.  ...  Our paper addresses both machine learning experts and safety engineers: The former ones might profit from the broad range of machine learning topics covered and discussions on limitations of recent methods  ...  Acknowledgment The research leading to these results is funded by the German Federal Ministry for Economic Affairs and Energy within the project "KI Absicherung -Safe AI for Automated Driving".  ... 
arXiv:2104.14235v1 fatcat:f6sj3v2brza7thyzw7b7fkpo2m

Maritime Robotics and Autonomous Systems Operations: Exploring Pathways for Overcoming International Techno-Regulatory Data Barriers

Tafsir Matin Johansson, Dimitrios Dalaklis, Aspasia Pastra
2021 Journal of Marine Science and Engineering  
A safety net needs to be devised to protect non-personal data.  ...  When it comes to patents, there are multifarious considerations in relation to vessel survey, inspection, and maintenance processes under national and international law.  ...  For a clear understanding of the different stages involved in RAS in survey and inspection, a diagram (see Figure 1 ) is presented to familiarize the reader with a real live scenario. propeller type:  ... 
doi:10.3390/jmse9060594 fatcat:vtgr3lorhfgt7lj4i6fr24zc3q

Applications of Drone Technology in Construction Industry: A Study 2012-2021

Gayatri Mahajan, Assistant Professor, Allana College of Architecture, Pune. (Maharashtra). India.
2021 International Journal of Engineering and Advanced Technology  
The aim of this paper is to study the potential of DT in construction industry, extended it to understand the following issues in better way(i) benefits and impacts of drone in CI, (ii) record disadvantage  ...  This is basically a review paper.  ...  conventional methods for site survey, Manuscript received on September 21, 2021.  ... 
doi:10.35940/ijeat.a3165.1011121 fatcat:2sw75e2lufggzb2btybcqbh7bq

Detection and Identification of Expansion Joint Gap of Road Bridges by Machine Learning using Line-Scan Camera Images

In Bae Kim, Jun Sang Cho, Goang Seup Zi, Beom Seok Cho, Seon Min Lee, Hyoung Uk Kim
2021 Applied System Innovation  
As a result, the expansion gap identification accuracy was improved by 27.5%, from 67.5% to 95.0%, and the use of the system reduces the survey time by more than 95%, from an average of approximately 1  ...  h/bridge (existing manual inspection method) to approximately 3 min/bridge.  ...  Conflicts of Interest: The authors declare no conflict of interest. Appl. Syst. Innov. 2021, 4, 94  ... 
doi:10.3390/asi4040094 fatcat:njr4gyfvpja5ronfjeshzai5be

Operationalising AI ethics: barriers, enablers and next steps

Jessica Morley, Libby Kinsey, Anat Elhalal, Francesca Garcia, Marta Ziosi, Luciano Floridi
2021 AI & Society: The Journal of Human-Centred Systems and Machine Intelligence  
It is this limitation that we seek to overcome here by conducting a mixed-methods qualitative analysis to answer the following four questions: what do AI practitioners understand about the need to translate  ...  Our previous research sought to start closing this gap between the 'what' and the 'how' of AI ethics through the creation of a searchable typology of tools and methods designed to translate between the  ...  Acknowledgements We would like to thank the anonymous reviewer for their incredibly valuable comments, they added significant depth to the discussion and the paper is much better as a result.  ... 
doi:10.1007/s00146-021-01308-8 fatcat:fgafgip6h5djfaekmfm252hske

Opportunities and Adoption Challenges of AI in the Construction Industry: A PRISMA Review

Massimo Regona, Tan Yigitcanlar, Bo Xia, Rita Yi Man Li
2022 Journal of Open Innovation: Technology, Market and Complexity  
practices.  ...  Moreover, despite AI being a hot topic in built environment research, there are limited review studies that investigate the reasons for the low-level AI adoption in the construction industry.  ...  Acknowledgments: The authors thank the editor-in-chief and anonymous referees for their constructive comments. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/joitmc8010045 fatcat:imvh2nwiijei5l5udts4wjdcxa

An Evaluation of the California Injury and Illness Prevention Program

John Mendeloff, Wayne B Gray, Amelia M Haviland, Regan Main, Jing Xia
2012 Rand health quarterly  
Eighty percent of the citations of the IIPP by the California Division of Occupational Safety and Health program are for only a different section, the one that requires employers to have a written IIPP  ...  single-establishment firms, the evaluation team analyzed the impact of citations for violations of the IIPP on safety performance by (1) using the number of citations as a measure of effectiveness and  ...  • Does training result in increased understanding of hazards and safer work practices?  ... 
pmid:28083238 pmcid:PMC4945298 fatcat:qsy3yunrtjc63pxdnfuw7wto7q

Model Fooling Attacks Against Medical Imaging: A Short Survey

Tuomo Sipola, Samir Puuska, Tero Kokkonen
2020 Information & Security An International Journal  
Acknowledgements This research is partially funded by the Cyber Security Network of Competence Centres for Europe (CyberSec4Europe) project of the Horizon 2020 SU-ICT-03-2018 program.  ...  The results of this short survey should be useful for anyone trying to understand the vulnerabilities of neural networks in specific domains.  ...  The scientific studies this short survey inspected include all those attacks.  ... 
doi:10.11610/isij.4615 fatcat:vg5xo6wiwfgk5pnm66d2bfgi5u

Critical control points for avian influenza A H5N1 in live bird markets in low resource settings

Gina Samaan, Anita Gultom, Risa Indriani, Kamalini Lokuge, Paul M. Kelly
2011 Preventive Veterinary Medicine  
The CCPs were developed based on three surveys conducted in Indonesia: a crosssectional survey in 119 markets, a knowledge, attitudes and practice survey in 3 markets and a microbiological survey in 83  ...  Live bird markets can become contaminated with and become a source of transmission for avian influenza viruses including the highly pathogenic H5N1 strain.  ...  Acknowledgements We thank the markets' management teams and poultry vendors, CHF International and all the staff implementing the changes for their consent to participate in the study.  ... 
doi:10.1016/j.prevetmed.2011.03.003 pmid:21489646 fatcat:6zwdxhezrjdfheushy3iwii7gy

A Review of Underground Pipeline Leakage and Sinkhole Monitoring Methods Based on Wireless Sensor Networking

Haibat Ali, Jae-ho Choi
2019 Sustainability  
The aim of this work is to review the existing methods for monitoring leakage in underground pipelines, the sinkholes caused by these leakages, and the viability of wireless sensor networking (WSN) for  ...  Additionally, the authors have suggested prospects for future research by comparing, analyzing, and classifying the reviewed methods.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/su11154007 fatcat:vuwmuzkvgjhjxct5stgy5yblam

Taxonomy of Machine Learning Safety: A Survey and Primer

Sina Mohseni, Zhiding Yu, Chaowei Xiao, Jay Yadawa, Haotao Wang, Zhangyang Wang
2022 ACM Computing Surveys  
Our taxonomy of ML safety presents a safety-oriented categorization of ML techniques to provide guidance for improving dependability of the ML design and development.  ...  The proposed taxonomy can serve as a safety checklist to aid designers in improving coverage and diversity of safety strategies employed in any given ML system.  ...  Summary: We proposed a taxonomy for broad range of ML techniques that support algorithmic safety for open-world deployment of ML-based software.  ... 
doi:10.1145/3551385 fatcat:kzohkvb56fd57bwro4e7s7a3fu

Taxonomy of Machine Learning Safety: A Survey and Primer [article]

Sina Mohseni and Haotao Wang and Zhiding Yu and Chaowei Xiao and Zhangyang Wang and Jay Yadawa
2022 arXiv   pre-print
Our taxonomy of ML safety presents a safety-oriented categorization of ML techniques to provide guidance for improving dependability of the ML design and development.  ...  The proposed taxonomy can serve as a safety checklist to aid designers in improving coverage and diversity of safety strategies employed in any given ML system.  ...  DISCUSSION AND CONCLUSIONS In our survey, we presented a review of fundamental ML limitations in engineering safety methods; followed by a taxonomy of safety-related techniques in ML.  ... 
arXiv:2106.04823v2 fatcat:mpw6v2j5mnbvho4w6tfhu7umeu

Evaluate Safety Practices of Malaysian Public Universities by using Balanced Scorecard

Lingaswaran Arjunan, Nurul Fadly Habidin, Mohamad Suwardi Mohamad Yusof, Rasikumari Muniandy
2020 Journal of Cognitive Sciences and Human Development  
The aim of this paper is to debate the concept of the balanced scorecard (BSC) and the way it will be used for evaluating the performance of safety practice in Malaysia public universities.  ...  It translates the mission and strategy of a security practice into a system of performance indicators.  ...  Data Collection Technique This research conducts a survey and uses a mono-method quantitative approach for collecting the information.  ... 
doi:10.33736/jcshd.1560.2020 fatcat:uuqjiicyxbebdbhsagsixn6ljq

Integrating Construction 4.0 Technologies: A Four-Layer Implementation Plan

Mahmoud El Jazzar, Christian Schranz, Harald Urban, Hala Nassereddine
2021 Frontiers in Built Environment  
The research presents a comprehensive plan for integrating Construction 4.0 technologies into the industry and serves as a guideline to help construction companies better understand the implications of  ...  This research explores the current state of Construction 4.0 and discusses a four-layer implementation of Construction 4.0 in the industry.  ...  One of the main components of AI is machine learning, where a machine learns from a set of data using statistical methods.  ... 
doi:10.3389/fbuil.2021.671408 fatcat:kulskvtfljfvlpy6vfpnijxqsy

Trustworthy AI: A Computational Perspective [article]

Haochen Liu, Yiqi Wang, Wenqi Fan, Xiaorui Liu, Yaxin Li, Shaili Jain, Yunhao Liu, Anil K. Jain, Jiliang Tang
2021 arXiv   pre-print
In this survey, we present a comprehensive survey of trustworthy AI from a computational perspective, to help readers understand the latest technologies for achieving trustworthy AI.  ...  Recent years have witnessed a tremendous amount of research on trustworthy AI.  ...  The overall aim is for humans to enjoy the benefits and conveniences of AI with a reliable and guarantee of safety.  ... 
arXiv:2107.06641v3 fatcat:ymqaxvzsoncqrcosj5mxcvgsuy
« Previous Showing results 1 — 15 out of 7,472 results