Pub Date : 2024-06-01DOI: 10.1007/978-3-031-43085-5_36
Marcos Faúndez-Zanuy, Moisés Díaz
{"title":"On the Use of First and Second Derivative Approximations for Biometric Online Signature Recognition","authors":"Marcos Faúndez-Zanuy, Moisés Díaz","doi":"10.1007/978-3-031-43085-5_36","DOIUrl":"https://doi.org/10.1007/978-3-031-43085-5_36","url":null,"abstract":"","PeriodicalId":103356,"journal":{"name":"International Work-Conference on Artificial and Natural Neural Networks","volume":"44 11","pages":"461-472"},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141275693","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-25DOI: 10.48550/arXiv.2306.06107
Paul Stahlhofen, André Artelt, L. Hermes, Barbara Hammer
Many Machine Learning models are vulnerable to adversarial attacks: There exist methodologies that add a small (imperceptible) perturbation to an input such that the model comes up with a wrong prediction. Better understanding of such attacks is crucial in particular for models used in security-critical domains, such as monitoring of water distribution networks, in order to devise counter-measures enhancing model robustness and trustworthiness. We propose a taxonomy for adversarial attacks against machine learning based leakage detectors in water distribution networks. Following up on this, we focus on a particular type of attack: an adversary searching the least sensitive point, that is, the location in the water network where the largest possible undetected leak could occur. Based on a mathematical formalization of the least sensitive point problem, we use three different algorithmic approaches to find a solution. Results are evaluated on two benchmark water distribution networks.
{"title":"Adversarial Attacks on Leakage Detectors in Water Distribution Networks","authors":"Paul Stahlhofen, André Artelt, L. Hermes, Barbara Hammer","doi":"10.48550/arXiv.2306.06107","DOIUrl":"https://doi.org/10.48550/arXiv.2306.06107","url":null,"abstract":"Many Machine Learning models are vulnerable to adversarial attacks: There exist methodologies that add a small (imperceptible) perturbation to an input such that the model comes up with a wrong prediction. Better understanding of such attacks is crucial in particular for models used in security-critical domains, such as monitoring of water distribution networks, in order to devise counter-measures enhancing model robustness and trustworthiness. We propose a taxonomy for adversarial attacks against machine learning based leakage detectors in water distribution networks. Following up on this, we focus on a particular type of attack: an adversary searching the least sensitive point, that is, the location in the water network where the largest possible undetected leak could occur. Based on a mathematical formalization of the least sensitive point problem, we use three different algorithmic approaches to find a solution. Results are evaluated on two benchmark water distribution networks.","PeriodicalId":103356,"journal":{"name":"International Work-Conference on Artificial and Natural Neural Networks","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132566923","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-31DOI: 10.48550/arXiv.2209.01191
Ivan Lukyanenko, Mikhail Mozikov, Yury Maximov, Ilya Makarov Moscow Institute of Physics, Technologies, Skolkovo Institute of Science, Technology, Los Alamos National Laboratory, A. I. R. Institute
Hail risk assessment is necessary to estimate and reduce damage to crops, orchards, and infrastructure. Also, it helps to estimate and reduce consequent losses for businesses and, particularly, insurance companies. But hail forecasting is challenging. Data used for designing models for this purpose are tree-dimensional geospatial time series. Hail is a very local event with respect to the resolution of available datasets. Also, hail events are rare - only 1% of targets in observations are marked as"hail". Models for nowcasting and short-term hail forecasts are improving. Introducing machine learning models to the meteorology field is not new. There are also various climate models reflecting possible scenarios of climate change in the future. But there are no machine learning models for data-driven forecasting of changes in hail frequency for a given area. The first possible approach for the latter task is to ignore spatial and temporal structure and develop a model capable of classifying a given vertical profile of meteorological variables as favorable to hail formation or not. Although such an approach certainly neglects important information, it is very light weighted and easily scalable because it treats observations as independent from each other. The more advanced approach is to design a neural network capable to process geospatial data. Our idea here is to combine convolutional layers responsible for the processing of spatial data with recurrent neural network blocks capable to work with temporal structure. This study compares two approaches and introduces a model suitable for the task of forecasting changes in hail frequency for ongoing decades.
{"title":"Long-term hail risk assessment with deep neural networks","authors":"Ivan Lukyanenko, Mikhail Mozikov, Yury Maximov, Ilya Makarov Moscow Institute of Physics, Technologies, Skolkovo Institute of Science, Technology, Los Alamos National Laboratory, A. I. R. Institute","doi":"10.48550/arXiv.2209.01191","DOIUrl":"https://doi.org/10.48550/arXiv.2209.01191","url":null,"abstract":"Hail risk assessment is necessary to estimate and reduce damage to crops, orchards, and infrastructure. Also, it helps to estimate and reduce consequent losses for businesses and, particularly, insurance companies. But hail forecasting is challenging. Data used for designing models for this purpose are tree-dimensional geospatial time series. Hail is a very local event with respect to the resolution of available datasets. Also, hail events are rare - only 1% of targets in observations are marked as\"hail\". Models for nowcasting and short-term hail forecasts are improving. Introducing machine learning models to the meteorology field is not new. There are also various climate models reflecting possible scenarios of climate change in the future. But there are no machine learning models for data-driven forecasting of changes in hail frequency for a given area. The first possible approach for the latter task is to ignore spatial and temporal structure and develop a model capable of classifying a given vertical profile of meteorological variables as favorable to hail formation or not. Although such an approach certainly neglects important information, it is very light weighted and easily scalable because it treats observations as independent from each other. The more advanced approach is to design a neural network capable to process geospatial data. Our idea here is to combine convolutional layers responsible for the processing of spatial data with recurrent neural network blocks capable to work with temporal structure. This study compares two approaches and introduces a model suitable for the task of forecasting changes in hail frequency for ongoing decades.","PeriodicalId":103356,"journal":{"name":"International Work-Conference on Artificial and Natural Neural Networks","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127944383","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-27DOI: 10.1007/978-3-030-85030-2_40
T. Chowdhury, Mahira Jalisha, A. Cheraghian, Shafin Rahman
{"title":"Learning without Forgetting for 3D Point Cloud Objects","authors":"T. Chowdhury, Mahira Jalisha, A. Cheraghian, Shafin Rahman","doi":"10.1007/978-3-030-85030-2_40","DOIUrl":"https://doi.org/10.1007/978-3-030-85030-2_40","url":null,"abstract":"","PeriodicalId":103356,"journal":{"name":"International Work-Conference on Artificial and Natural Neural Networks","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116944871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-17DOI: 10.1007/978-3-030-85099-9_13
A. Rosato, M. Panella, Evgeny Osipov, D. Kleyko
{"title":"On Effects of Compression with Hyperdimensional Computing in Distributed Randomized Neural Networks","authors":"A. Rosato, M. Panella, Evgeny Osipov, D. Kleyko","doi":"10.1007/978-3-030-85099-9_13","DOIUrl":"https://doi.org/10.1007/978-3-030-85099-9_13","url":null,"abstract":"","PeriodicalId":103356,"journal":{"name":"International Work-Conference on Artificial and Natural Neural Networks","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125740577","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-06-10DOI: 10.1007/978-3-030-85030-2_4
W. Zamora-Cardenas, Mauro Mendez, S. C. Ramírez, Martin Vargas, Gerardo Monge, S. Quirós, D. Elizondo, Miguel A. Molina-Cabello
{"title":"Enforcing Morphological Information in Fully Convolutional Networks to Improve Cell Instance Segmentation in Fluorescence Microscopy Images","authors":"W. Zamora-Cardenas, Mauro Mendez, S. C. Ramírez, Martin Vargas, Gerardo Monge, S. Quirós, D. Elizondo, Miguel A. Molina-Cabello","doi":"10.1007/978-3-030-85030-2_4","DOIUrl":"https://doi.org/10.1007/978-3-030-85030-2_4","url":null,"abstract":"","PeriodicalId":103356,"journal":{"name":"International Work-Conference on Artificial and Natural Neural Networks","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129804752","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-04-13DOI: 10.1007/978-3-030-85099-9_4
N. Gallego-Molina, M. Formoso, A. Ortiz, Francisco J. Mart'inez-Murcia, J. Luque
{"title":"Temporal EigenPAC for dyslexia diagnosis","authors":"N. Gallego-Molina, M. Formoso, A. Ortiz, Francisco J. Mart'inez-Murcia, J. Luque","doi":"10.1007/978-3-030-85099-9_4","DOIUrl":"https://doi.org/10.1007/978-3-030-85099-9_4","url":null,"abstract":"","PeriodicalId":103356,"journal":{"name":"International Work-Conference on Artificial and Natural Neural Networks","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116045104","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-04-06DOI: 10.1007/978-3-030-85030-2_9
André Artelt, Fabian Hinder, Valerie Vaquet, Robert Feldhans, B. Hammer
{"title":"Contrastive Explanations for Explaining Model Adaptations","authors":"André Artelt, Fabian Hinder, Valerie Vaquet, Robert Feldhans, B. Hammer","doi":"10.1007/978-3-030-85030-2_9","DOIUrl":"https://doi.org/10.1007/978-3-030-85030-2_9","url":null,"abstract":"","PeriodicalId":103356,"journal":{"name":"International Work-Conference on Artificial and Natural Neural Networks","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132620395","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-06-12DOI: 10.1007/978-3-030-20518-8_14
Miguel A. Molina-Cabello, Cristian Accino, Ezequiel López-Rubio, Karl Thurnhofer-Hemsi
{"title":"Optimization of Convolutional Neural Network Ensemble Classifiers by Genetic Algorithms","authors":"Miguel A. Molina-Cabello, Cristian Accino, Ezequiel López-Rubio, Karl Thurnhofer-Hemsi","doi":"10.1007/978-3-030-20518-8_14","DOIUrl":"https://doi.org/10.1007/978-3-030-20518-8_14","url":null,"abstract":"","PeriodicalId":103356,"journal":{"name":"International Work-Conference on Artificial and Natural Neural Networks","volume":"200 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115289464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：