Filters








62,128 Hits in 5.4 sec

Using Artificial Intelligence in Source Code Summarization: A Review [chapter]

Shraddha Birari, Sukhada Bhingarkar
2021 Advances in Parallel Computing  
Thus, this paper presents a critical review of various NLP and ML techniques implemented so far for generating summaries from the source code and points out research challenges in this field.  ...  Artificial Intelligence is a very popular branch in the field of computer science that demonstrates machine intelligence and covers a wide range of applications.  ...  Introduction Summarization can be viewed as transformation of data into a concise yet meaningful representation which could be used further for analysis or storage.  ... 
doi:10.3233/apc210203 fatcat:ntpkh7z74vgffkpyloqeog4k7y

Biases in Data Science Lifecycle [article]

Dinh-An Ho, Oya Beyan
2020 arXiv   pre-print
However, a typical data scientist has not enough knowledge for identifying these challenges and it is not always possible to include an ethics expert during data science production.  ...  The aim of early publishing is to collect community feedback and improve the curated knowledge base for bias types and solutions.  ...  Best Practices: In [3] , novel data Representation bias Removal (REPAIR) technique is introduced to resolve the generalization issues present in training datasets by employing Repair-Algorithm.  ... 
arXiv:2009.09795v2 fatcat:rdo67rpt7bd3hecegejk7kv3oe

Analytical methods used in estimating the prevalence of HIV/AIDS from demographic and cross-sectional surveys with missing data: a systematic review

Neema R. Mosha, Omololu S. Aluko, Jim Todd, Rhoderick Machekano, Taryn Young
2020 BMC Medical Research Methodology  
Missing data in survey studies is still a problem in disease estimation.  ...  A piloted data extraction tool was used to extract data and assess the risk of bias of the eligible studies.  ...  Acknowledgements We acknowledge Anel Schoonees for helping with searching of the studies, and Traci Naidoo for the logistic support.  ... 
doi:10.1186/s12874-020-00944-w pmid:32171240 fatcat:prmm7aiq5jb7tejrsf6yb23kty

Photometric redshift estimation with convolutional neural networks and galaxy images: Case study of resolving biases in data-driven methods

Q. Lin, D. Fouchez, J. Pasquet, M. Treyer, R. Ait Ouahmed, S. Arnouts, O. Ilbert
2022 Astronomy and Astrophysics  
We focus on point estimates and propose a set of consecutive steps for resolving the two biases based on CNN models, involving representation learning with multichannel outputs, balancing the training  ...  We suggest that a prerequisite for resolving biases in photometric space is resolving biases in spectroscopic space.  ...  This project has received funding from the European Union's Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No713750.  ... 
doi:10.1051/0004-6361/202142751 fatcat:ovfdynhhg5flhf32yvnkkibjwe

Responsible Data Integration: Next-generation Challenges

Fatemeh Nargesian, Abolfazl Asudeh, H. V. Jagadish
2022 Proceedings of the 2022 International Conference on Management of Data  
We focus on three critical aspects: (1) the requirements to be considered for evaluating and auditing data integration tasks for quality and bias; (2) the data integration tasks that elicit attention to  ...  We present a tutorial on data integration and responsibility, highlighting the existing efforts in responsible data integration along with research opportunities and challenges.  ...  Jagadish was supported in part by the National Science Foundation under grants 1741022 and 1934565.  ... 
doi:10.1145/3514221.3522567 fatcat:edej7kctuzfulndxordhfpnliq

When (ish) is My Bus?

Matthew Kay, Tara Kola, Jessica R. Hullman, Sean A. Munson
2016 Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems - CHI '16  
To develop it, we identified domain specific design requirements for visualizing uncertainty in transit prediction through: 1) a literature review, 2) a large survey of users of a popular realtime transit  ...  We present several candidate visualizations of uncertainty for realtime transit predictions in a mobile context, and we propose a novel discrete representation of continuous outcomes designed for small  ...  Full priors and posterior estimates are available with our data. 6 Bias in respondent probability estimates Consistent with Figure 6A , our regression found that estimates were slightly biased on average  ... 
doi:10.1145/2858036.2858558 dblp:conf/chi/KayKHM16 fatcat:wfdjgl35gvhjzjis6aif5eivni

Photometric Redshift Estimation with Convolutional Neural Networks and Galaxy Images: A Case Study of Resolving Biases in Data-Driven Methods [article]

Q. Lin, D. Fouchez, J. Pasquet, M. Treyer, R. Ait Ouahmed, S. Arnouts, O. Ilbert
2022 arXiv   pre-print
We focus on point estimates and propose a set of consecutive steps for resolving the two biases based on CNN models, involving representation learning with multi-channel outputs, balancing the training  ...  We suggest that resolving biases in the spectroscopic space is a prerequisite for resolving biases in the photometric space.  ...  This project has received funding from the European Union's Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No713750.  ... 
arXiv:2202.09964v1 fatcat:xk3bgxwjxfd53n6p4kq4mt5d2q

Language (Technology) is Power: A Critical Survey of "Bias" in NLP [article]

Su Lin Blodgett and Solon Barocas and Hal Daumé III and Hanna Wallach
2020 arXiv   pre-print
We survey 146 papers analyzing "bias" in NLP systems, finding that their motivations are often vague, inconsistent, and lacking in normative reasoning, despite the fact that analyzing "bias" is an inherently  ...  Based on these findings, we describe the beginnings of a path forward by proposing three recommendations that should guide work analyzing "bias" in NLP systems.  ...  As a result, we excluded them from our counts for techniques as well.  ... 
arXiv:2005.14050v2 fatcat:nyzr4fj5gne55jzhzm2fy5xeqa

Comparison of Shear-velocity Profiles of Unconsolidated Sediments Near the Coyote Borehole (CCOC) Measured with Fourteen Invasive and Non-invasive Methods Editorial

M. Asten, D. Boore
2005 Journal of Environmental & Engineering Geophysics  
(Bill) Stephenson and Rob Williams for many suggestions and corrections to the draft of this paper. One of us (MWA) is supported by the U.S.  ...  The views and conclusions contained in this document are those of the authors and should not be interpreted as necessarily representing the official policies, either express or implied, of the U.S.  ...  The plotted Vs shows no obvious bias relative to CCOC-Vsm, and successfully resolves a thin LVL at 7-16 m depth. However it does not detect the lower LVL identified on Figure 4b (55-75 m).  ... 
doi:10.2113/jeeg10.2.85 fatcat:rxrgx7l4ljgy5gdy3aqadjl4em

The Delphi Process in Dental Research

Carl K. Cramer, Gary D. Klasser, Joel B. Epstein, Samuel B. Sheps
2008 Journal of Evidence-Based Dental Practice  
The Delphi technique has been used to achieve consensus of opinion on a variety of issues including those related to oral health. Guidelines for the use of Delphi are presented.  ...  Objective: To explore how Delphi formal consensus procedures may augment decision making in oral health care in the absence of high-quality clinical and epidemiological data.  ...  ACKNOWLEDGMENTS The authors thank Penelope Mullen MSc(Eng), DIC, ACGI, for her helpful critique of an earlier draft, and Susanne Sunell EdD, RDH, for her wide-ranging editorial input.  ... 
doi:10.1016/j.jebdp.2008.09.002 pmid:19027655 fatcat:5llklyp4rzfodjrtb7fc2houea

What they really think: Resolving methodological issues in supply chain ethics research

K. Chipp, M. Goldman, N. Kleyn
2007 Acta Commercii  
The method selected was saturation surveying, a process whereby all identifiable target respondents are surveyed.  ...  Furthermore, in terms of the little-studied nature of buyer-seller relations, the verification of the scale developed by Bendixon and Abratt (2007) affirms the robustness of this measure for ethics research  ...  Self-selection and non-response bias is a common problem in any survey.  ... 
doi:10.4102/ac.v7i1.18 fatcat:pkyvh7trcjayxe36f6dovv6huy

A Survey on Bias and Fairness in Machine Learning [article]

Ninareh Mehrabi, Fred Morstatter, Nripsuta Saxena, Kristina Lerman, Aram Galstyan
2022 arXiv   pre-print
We then created a taxonomy for fairness definitions that machine learning researchers have defined in order to avoid the existing bias in AI systems.  ...  In this survey we investigated different real-world applications that have shown biases in various ways, and we listed different sources of biases that can affect AI applications.  ...  In this survey we identify two potential sources of unfairness in machine learning outcomesthose that arise from biases in the data and those that arise from the algorithms.  ... 
arXiv:1908.09635v3 fatcat:fygrqs3sing6zdsg53t7awhih4

Using sex and gender in survey adjustment [article]

Lauren Kennedy, Katharine Khanna, Daniel Simpson, Andrew Gelman, Yajun Jia, Julien Teitler
2022 arXiv   pre-print
Accounting for sex and gender is a challenge in social science research.  ...  Overall, we conclude not with a single best recommendation for all surveys but rather with an awareness of the complexity of the problem and the benefits and weaknesses of different approaches.  ...  What it does not do, however, is make broad recommendations for a one best way to measure sex or gender or a one best technique to account for measuring gender in a survey when the population measures  ... 
arXiv:2009.14401v2 fatcat:ydfssua5dvbnvcdr4skmyas5ky

Quality standards and training are important in the peer review process, but what about engagement?

Peter J. Jordan
2020 Industrial and Organizational Psychology  
In doing this, we acknowledge the substantial work that has been produced on this topic to date and, therefore, focus our contribution specifically on issues that affect research in applied and managerial  ...  A common factor that can stymie research rigour is common method bias.  ...  More specifically, Williams et al. (2010) propose a three-step CFA marker technique to identify and control for method biases.  ... 
doi:10.1017/iop.2020.10 fatcat:afnis7f3ejdd3lolmv3r4gpd5a

Identifying the Main Causes of Medical Data Incompleteness in the Smart Healthcare Era

Colin Wilcox, Soufiene Djahel, Vasileios Giagos
2021 2021 International Symposium on Networks, Computers and Communications (ISNCC)  
This paper aims to identify the main causes of data incompleteness in the medical domain, discuss some techniques currently used to build a complete medical picture and highlight how they may affect the  ...  Incomplete data due to discrepancies between medical data sources and their storage methods represents a serious concern as it may lead to the loss, or misrepresentation of important medical information  ...  In this technique, a data adapter for each type of data source is used to convert the original data into a standardised format.  ... 
doi:10.1109/isncc52172.2021.9615774 fatcat:lqoqyfueendojatr4ggpx5c65m
« Previous Showing results 1 — 15 out of 62,128 results