Causal discovery of drivers of surface ozone variability in Antarctica using a deep learning algorithm

Kumar, Pankaj; Kuttippurath, J.; Mitra, Adway

doi:10.1039/d1em00383f

Cited by 6 publications

(4 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The input type of the reduced function must match the output type of the map function: the Text type and the IntWritable type. In this case, the output type of reduce function is Text and IntWritable, the former type of time stamp, and the latter type of the highest feature data, where all feature data are traversed during the design and construction of Hadoop-based intrusion detection big data analysis, and each record is compared until the best feature data match is found [21].…”

Section: Big Data Storage For Intrusion Detection Based On Hadoopmentioning

confidence: 99%

Intrusion Detection Method Based on Deep Learning

Tian

Zhang

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

In today’s information age, the scale of the Internet is growing, the information capacity is also expanding explosively, and network security is becoming more and more important. Intrusion detection is regarded as a traditional security protection technology and is a key means to ensure the security of the network environment. Among them, the deep belief network performs well, and it can automatically learn abstract features for classification. In order to further improve the detection rate and reduce the false positive rate, it is necessary to improve the detection rate of small sample data. This paper builds an intelligent deep learning model and analysis model for intrusion detection data based on TensorFlow. By learning to identify network intrusion characteristic data, the characteristic data and model are stored in the big data storage system built by Hadoop. This algorithm has achieved good experiment result. Build a model knowledge base and an intrusion feature behavior library, use the decision tree model to automatically match the security control strategy, realize a highly intelligent security control model with self-learning ability, and solve the rapid identification of unknown intrusion behaviors. Experiments show that the algorithm can effectively improve the detection rate.

show abstract

Section: Big Data Storage For Intrusion Detection Based On Hadoopmentioning

confidence: 99%

Intrusion Detection Method Based on Deep Learning

Tian

Zhang

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…The input type of the reduce function must match the output type of the map function: the Text type and the IntWritable type. In this case, the output type of reduce function is Text and IntWritable, the former type of time stamp and the latter type of highest feature data, where all feature data are traversed during the design and construction of hadoop-based intrusion detection big data analysis, and each record is compared until a best feature data match is found until [20].…”

Section: Big Data Storage For Intrusion Detection Based On Hadoopmentioning

confidence: 99%

Research on Intrusion Detection Method Based on Deep Learning

Tian

Zhang

et al. 2023

Preprint

View full text Add to dashboard Cite

In today's information age, the scale of the Internet is growing, the information capacity is also expanding explosively, and network security is becoming more and more important. Intrusion detection is regarded as a traditional security protection technology and is a key means to ensure the security of the network environment. Among them, the deep belief network performs well, and it can automatically learn abstract features for classification. In order to further improve the detection rate and reduce the false positive rate, it is necessary to improve the detection rate of small sample data. This paper builds an intelligent deep learning model and analysis model for intrusion detection data based on TensorFlow. By learning to identify network intrusion characteristic data, the characteristic data and model are stored in the big data storage system built by Hadoop. This algorithm has achieved good experiments. result. Build a model knowledge base and an intrusion feature behavior library, use the decision tree model to automatically match the security control strategy, realize a highly intelligent security control model with self-learning ability, and solve the rapid identification of unknown intrusion behaviors. Experiments show that the algorithm can effectively improve the detection rate.

show abstract

“…Kumar et al [KKM22] used TCDF to analyse the surface ozone variability in Antarctica. They concluded that most of the discovered relationships were in line with domain knowledge.…”

Section: Impact and Applications Of Tcdfmentioning

confidence: 99%

“…They concluded that most of the discovered relationships were in line with domain knowledge. Compared to other causality methods, they "prefer links identified by TCDF as it can identify the directions and lags in all those cases apart from accounting for hidden confounders and non-linearity of the processes involved in the analysis" [KKM22]. Causal models constructed by causal discovery methods have also proved useful for feature selection to remove irrelevant or redundant input features [SLL+15].…”

Section: Impact and Applications Of Tcdfmentioning

confidence: 99%

Explainable AI and interpretable computer vision : from oversight to insight

Nauta¹

View full text Add to dashboard Cite

The last decades have seen rapid development of advanced machine learning (ML) models, considered a subarea of Artificial Intelligence (AI). Massive computing power and growing data availability have allowed the training of deep artificial neural networks, which learn themselves by finding task-relevant patterns in data. The size and complexity of these deep learning models grew over the years in pursuit of predictive performance. However, such black boxes prevent users from assessing whether the learned behaviour is in line with expectations and intentions. We argue in this thesis that the sole focus on predictive performance is an unsustainable trajectory, as a model can make right predictions for the wrong reasons. The research field of Explainable AI (XAI) addresses the black-box nature of ML models by generating explanations that present (aspects of) a model's behaviour in human-understandable terms. This thesis shows that explainability can be used to open up the whole machine learning pipeline: from understanding the underlying data, to assessing the quality of explanations and designing models that are interpretable by design. As such, we support the transition from oversight to insight. in-model uitlegbaarheid, zoals onze part-prototype modellen uit deel II, kunnen modellen worden 'heropgevoed' met onze gewenste normen, waarden en redeneringen. Op die manier kan kunstmatige intelligentie worden aangepast en aangevuld met menselijke intelligentie. Mensen in staat te stellen om ongewenst gedrag van een model te detecteren en te corrigeren draagt bij aan een effectief maar ook betrouwbaar en verantwoord gebruik van AI. v 12 Discussion and Reflection 12.

show abstract

Causal discovery of drivers of surface ozone variability in Antarctica using a deep learning algorithm

Abstract: The discovery of causal structures behind a phenomenon under investigation has been at the heart of scientific inquiry since the beginning. Randomized control trials, the gold standard for causal analysis,...

Cited by 6 publications

References 67 publications

Intrusion Detection Method Based on Deep Learning

Intrusion Detection Method Based on Deep Learning

Research on Intrusion Detection Method Based on Deep Learning

Explainable AI and interpretable computer vision : from oversight to insight

Contact Info

Product

Resources

About