Filters








994 Hits in 13.5 sec

Using Deep Learning Algorithms for CPAs' Going Concern Prediction

Chyan-Long Jan
2021 Information  
This study aims to construct going concern prediction models to help CPAs and auditors to make more effective/correct judgments on going concern opinion decisions by deep learning algorithms, and using  ...  Certified public accounts' (CPAs) audit opinions of going concern are the important basis for evaluating whether enterprises can achieve normal operations and sustainable development.  ...  The learning and prediction abilities of deep learning algorithms are quite powerful and suitable for going concern study. However, related research is quite rare in the past literature.  ... 
doi:10.3390/info12020073 fatcat:4n43ek3grvcrzhaml2ko3w3fzq

Artificial Intelligence in Corporate Sustainability: Using LSTM and GRU for Going Concern Prediction

Der-Jang Chi, Chien-Chou Chu
2021 Sustainability  
However, the use of deep learning algorithms in the prediction of going concern remains limited.  ...  In contrast to those in the literature, this study uses long short-term memory (LSTM) and gated recurrent unit (GRU) for learning and training, in order to construct effective and highly accurate going-concern  ...  machine learning or deep learning algorithms to predict the going concern.  ... 
doi:10.3390/su132111631 fatcat:5jsh7amtcjaofa764iudutmp6q

Using Hybrid Artificial Intelligence and Machine Learning Technologies for Sustainability in Going-Concern Prediction

Der-Jang Chi, Zong-De Shen
2022 Sustainability  
In order to embrace the era of big data, artificial intelligence (AI) and machine learning technologies have been used in recent studies to judge going concern doubts and reduce judgment errors.  ...  The going-concern opinions of certified public accountants (CPAs) and auditors are very critical, and due to misjudgments, the failure to discover the possibility of bankruptcy can cause great losses to  ...  Acknowledgments: The authors would like to express their gratitude toward Ministry of Science and Technology, Taiwan, for the subsidy (MOST 109-2410-H-034-035) on this research.  ... 
doi:10.3390/su14031810 fatcat:fxeoo73wlbge7nejvihpngrpya

Detection of Financial Statement Fraud Using Deep Learning for Sustainable Development of Capital Markets under Information Asymmetry

Chyan-Long Jan
2021 Sustainability  
Two powerful deep learning algorithms (i.e., recurrent neural network (RNN) and long short-term memory (LSTM)) are used to construct financial statement fraud detection models.  ...  In this era of big data and artificial intelligence, deep learning is being applied to many different domains.  ...  Deep learning algorithms can quickly and effectively handle large amounts of data and are powerful tools for modeling.  ... 
doi:10.3390/su13179879 fatcat:l55rcahntvdbfpki57ijg32ore

Financial Information Asymmetry: Using Deep Learning Algorithms to Predict Financial Distress

Chyan-long Jan
2021 Symmetry  
The purpose of this study is to build high-accuracy and effective financial distress prediction models by two representative deep learning algorithms: Deep neural networks (DNN) and convolutional neural  ...  and OTC sample companies are taken from the Taiwan Economic Journal (TEJ) database during the period from 2000 to 2019, including 86 companies in financial distress and 258 not in financial distress, for  ...  In the era of artificial intelligence (AI), deep learning algorithms are used in academic research. So far, quite a few studies have used deep learning algorithms to predict financial distress.  ... 
doi:10.3390/sym13030443 fatcat:wxtep3yu4rhkldmkumtanpca2e

Analysis of Risk-Based Operational Bird Strike Prevention

Isabel C. Metz, Joost Ellerbroek, Thorsten Mühlhausen, Dirk Kügler, Jacco M. Hoekstra
2021 Aerospace (Basel)  
As such, the collision avoidance algorithm is extended to a bird strike risk algorithm.  ...  Hence, in-depth studies of multi-year bird data to develop bird behavior models and reliable predictions are recommended for future research.  ...  Acknowledgments: We thank Robin Radar, the Royal Netherlands Air Force and the Royal Netherlands Meteorological Institute for providing us with radar data.  ... 
doi:10.3390/aerospace8020032 fatcat:66bu2aouxbcjvkd27iwiikqlpu

SoK: Privacy Preserving Machine Learning using Functional Encryption: Opportunities and Challenges [article]

Prajwal Panzade, Daniel Takabi
2022 arXiv   pre-print
Numerous efforts have been made in privacy-preserving machine learning (PPML) to address security and privacy concerns.  ...  We focus on Inner-product-FE and Quadratic-FE-based machine learning models for the PPML applications.  ...  Rouhani et al. in DeepSecure [46] proposed an approach for the scalable execution of deep learning models in the PPML setting that uses an optimized version of Yao's Garbled Circuit (GC) protocol.  ... 
arXiv:2204.05136v1 fatcat:sah3enwbqzfe5pjqbnyjbjpdx4

Multi-UAV Conflict Resolution with Graph Convolutional Reinforcement Learning

Ralvi Isufaj, Marsel Omeri, Miquel Angel Piera
2022 Applied Sciences  
Safety is the primary concern when it comes to air traffic.  ...  In this paper, we model multi-UAV conflict resolution as a multiagent reinforcement learning problem.  ...  Furthermore, existing deep learning algorithms largely assume the data to be independent, which does not hold for graph data.  ... 
doi:10.3390/app12020610 fatcat:zv74eywngfh53h2chyxk4y4vke

A Review of Confidentiality Threats Against Embedded Neural Network Models [article]

Raphaël Joud, Pierre-Alain Moellic, Rémi Bernhard, Jean-Baptiste Rigaud
2021 arXiv   pre-print
Utilization of Machine Learning (ML) algorithms, especially Deep Neural Network (DNN) models, becomes a widely accepted standard in many domains more particularly IoT-based systems.  ...  The threats concern the exploitation of algorithmic flaws as well as SCA techniques to extract model's information or exploit data leakage (red targets).  ...  Attacks on the Machine Learning pipeline Among the major obstacles of the deployment of ML models, security issues are notably critical and concern the whole ML pipeline.  ... 
arXiv:2105.01401v1 fatcat:fo6kowqg2rfvxeqcoxuroeeefe

Financial Distress Prediction Using Hybrid Machine Learning Techniques

Suduan Chen, Zong-De Shen
2020 Asian Journal of Economics Business and Accounting  
The purpose of this study is to establish an effective financial distress prediction model by applying hybrid machine learning techniques.  ...  This study deploys multiple machine learning techniques.  ...  These variables are then used for the construction of prediction models for financial distress with CART and RF algorithms, respectively.  ... 
doi:10.9734/ajeba/2020/v16i230231 fatcat:wgdhcgr355cmbacy5mejf2aa7m

Integrated Topic Modeling and Sentiment Analysis: A Review Rating Prediction Approach for Recommender Systems

2019 Turkish Journal of Electrical Engineering and Computer Sciences  
Therefore, this paper aims to build a review rating prediction model that simultaneously captures the topics and sentiments present in the reviews which are then used as features for the rating prediction  ...  A new sentiment-enriched and topic-modeling-based review rating prediction technique which can recognize modern review contents is proposed to facilitate this feature.  ...  The input matrix is then fed to a deep learning architecture for better optimization.  ... 
doi:10.3906/elk-1905-114 fatcat:atvei3vqp5dnraqmctz6mrfcoi

Cyber—Physical Attack Detection in Water Distribution Systems with Temporal Graph Convolutional Neural Networks

Lydia Tsiami, Christos Makropoulos
2021 Water  
We presented an online, one-stage, prediction-based algorithm that implements the temporal graph convolutional network and makes use of the Mahalanobis distance.  ...  creation of trustworthy AI algorithms for water applications.  ...  Based on the explainability and the good localization performance of the algorithm, we argue that the use of deep learning models that consider the graph structure of the water network is a promising research  ... 
doi:10.3390/w13091247 doaj:796a03ec8f3d4209b14d767c62348498 fatcat:lc5ei5jchvg3plktbzlun77hty

A New Automatic Tool for CME Detection and Tracking with Machine-learning Techniques

Pengyu Wang, Yan Zhang, Li Feng, Hanqing Yuan, Yuan Gan, Shuting Li, Lei Lu, Beili Ying, Weiqun Gan, Hui Li
2019 Astrophysical Journal Supplement Series  
Next, to identify the CME region in each CME-flagged image, we use deep descriptor transforming to localize the common object in an image set.  ...  We have developed a new tool for CME Automatic detection and tracking with MachinE Learning (CAMEL) techniques. The system is a three-module pipeline.  ...  This paper uses data from the CACTus CME catalog, generated and maintained by the SIDC at the Royal Observatory of Belgium. We also acknowledge using the CME catalogs of SEEDS and CORIMP.  ... 
doi:10.3847/1538-4365/ab340c fatcat:2att2eaqezfsjefszwhukyfpzi

An Anatomization of Language Detection and Translation using NLP Techniques

Bhagyashree P Pujeri, Jagadeesh Sai D
2020 VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE  
Language detection algorithm based on char n-gram based statistical detector and translation Yandex API is used.While translating, there should be encryption and decryption for that we are using AES Algorithm  ...  Algorithms for natural language processing must be updated according to language's grammar.This paper proposes a secure language detection and translation technique to solve the security in natural language  ...  Machine learning is a subset of Deep Learning and Neural Networks.  ... 
doi:10.35940/ijitee.b8265.1210220 fatcat:ympcf6nspbboldlzmmg66d2som

MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining [article]

Ahmed Imtiaz Humayun, Randall Balestriero, Richard Baraniuk
2022 arXiv   pre-print
In response, we develop MaGNET, a novel and theoretically motivated latent space sampler for any pre-trained DGN, that produces samples uniformly distributed on the learned manifold.  ...  ., for fairness or data augmentation.  ...  INTRODUCTION Deep Generative Networks (DGNs) are Deep Networks (DNs) trained to learn latent representations of datasets; such frameworks include Generative Adversarial Networks (GANs) (Goodfellow et  ... 
arXiv:2110.08009v3 fatcat:p2z7iisxgra7rb6w6svh555u2q
« Previous Showing results 1 — 15 out of 994 results