检索结果-内蒙古大学图书馆

SCArFF: A scalable framework for streaming credit card fraud detection with spark

INFOrMATION FUSION 2018年 41卷 182-194页

作者： Carcillo, Fabrizio dal Pozzolo, Andrea Le Borgne, Yann-Ael Caelen, Olivier Mazzer, Yannis Bontempi, Gianluca ULB Fac Sci Comp Sci Dept Machine Learning Grp Brussels Belgium Worldline R&D High Proc & Volume Team Brussels Belgium

The expansion of the electronic commerce, together with an increasing confidence of customers in electronic payments, makes of fraud detection a critical factor. detecting frauds in (nearly) real time setting demands the design and the implementation of scalable learning techniques able to ingest and analyse massive amounts of streaming data. recent advances in analytics and the availability of open source solutions for Big data storage and processing open new perspectives to the fraud detection field. In this paper we present a Scalable real-time Fraud Finder (SCArFF) which integrates Big data tools (Kafka, Spark and Cassandra) with a machine learning approach which deals with imbalance, nonstationarity and feedback latency. Experimental results on a massive dataset of real credit card transactions show that this framework is scalable, efficient and accurate over a big stream of transactions. (C) 2017 Elsevier B.V. All rights reserved.

关键词： Big data Fraud detection Streaming analytics machine learning Scalable software Kafka Spark Cassandra

来源：评论

学校读者我要写书评

暂无评论

Conformal efficiency as a metric for comparative model assessment befitting federated learning

引用

ArTIFICIAL INTELLIGENCE IN THE LIFE SCIENCES 2023年 3卷

作者： Heyndrickx, Wouter Arany, Adam Simm, Jaak Pentina, Anastasia Sturm, Noe Humbeck, Lina Mervin, Lewis Zalewski, Adam Oldenhof, Martijn Schmidtke, Peter Friedrich, Lukas Loeb, regis Afanasyeva, Arina Schuffenhauer, Ansgar Moreau, Yves Ceulemans, Hugo Janssen Pharmaceut NV Turnhoutseweg 30 B-2340 Beerse Belgium Katholieke Univ Leuven ESAT STADIUS Kasteelpk Arenberg 10 B-3001 Heverlee Belgium Bayer AG Machine Learning Res Res & Dev Pharmaceut D-10117 Berlin Germany Novartis Inst Biomed Res Novartis Campus CH-4002 Basel Switzerland Boehringer Ingelheim Pharm GmbH & Co KG Med Chem Dept Birkendorfer Str 65 D-88397 Biberach Germany AstraZeneca Mol AI Discovery Sci R&D Cambridge England Amgen Res Munich GmbH Staffelseestr 2 D-81477 Munich Germany Discngine 79 Ave Ledru Rollin F-75012 Paris France Merck KGaA Global Res & Dev Frankfurter Str 250 D-64293 Darmstadt Germany Astellas Pharma Inc Modal Informat Grp Digital Res Solut Adv Informat & Analyt 21 Miyukigaoka Tsukuba Ibaraki 3058585 Japan

In a drug discovery setting, pharmaceutical companies own substantial but confidential datasets. The MELLOddY project developed a privacy-preserving federated machine learning solution and deployed it at an unprecedented scale. Each partner built models for their own private assays that benefitted from a shared representation. Established predictive performance metrics such as AUC rOC or AUC Pr are constrained to unseen labeled chemical space and cannot gage performance gains in unlabeled chemical space. Federated learning indirectly extends labeled space, but in a privacy-preserving context, a partner cannot use this label extension for performance assessment. Metrics that estimate uncertainty on a prediction can be calculated even where no label is known. Practically, the chemical space covered with predictions above an uncertainty threshold, reflects the applicability domain of a model. After establishing a link to established performance metrics, we propose the efficiency from the conformal prediction framework ('conformal efficiency') as a proxy to the applicability domain size. A documented extension of the applicability domain would qualify as a tangible benefit from federated learning. In interim assessments, MELLOddY partners reported a median increase in conformal efficiency of the federated over the single-partner model of 5.5% (with increases up to 9.7%). Subject to distributional conditions, that efficiency increase can be directly interpreted as the expected increase in conformal i.e. low uncertainty predictions. In conclusion, we present the first indication that privacy-preserving federated machine learning across massive drug-discovery datasets from ten pharma partners indeed extends the applicability domain of property prediction models.

关键词： Small molecule drug discovery MELLOddY QSAr Federated multitask learning Applicability domain Uncertainty

来源：评论

学校读者我要写书评

暂无评论

machine learning for Toxicity Prediction Using Chemical Structures: Pillars for Success in the real World

引用

CHEMICAL research IN TOXICOLOGY 2025年第5期38卷 759-807页

作者： Seal, Srijit Mahale, Manas Garcia-Ortegon, Miguel Joshi, Chaitanya K. Hosseini-Gerami, Layla Beatson, Alex Greenig, Matthew Shekhar, Mrinal Patra, Arijit Weis, Caroline Mehrjou, Arash Badre, Adrien Paisley, Brianna Lowe, rhiannon Singh, Shantanu Shah, Falgun Johannesson, Bjarki Williams, dominic rouquie, david Clevert, djork-Arne Schwab, Patrick richmond, Nicola Nicolaou, Christos A. Gonzalez, raymond J. Naven, russell Schramm, Carolin Vidler, Lewis r. Mansouri, Kamel Walters, W. Patrick Wilk, deidre dalmas Spjuth, Ola Carpenter, Anne E. Bender, Andreas Broad Inst MIT & Harvard Cambridge MA 02142 USA Univ Cambridge Dept Chem Cambridge CB2 1EW England Bombay Coll Pharm Dept Pharmaceut Chem Mumbai 400098 India Univ Cambridge Dept Comp Sci & Technol Cambridge CB3 0FD England IgnotaLabs Cambridge CB4 0GA England Axiom Bio San Francisco CA 94107 USA UCB Pharma Slough SL1 3WE England GSK London WC1A 1DG England Novartis Biomed Res Cambridge MA 02139 USA Eli Lilly & Co Indianapolis IN 46285 USA Relat Therapeut London NW1 3BG England Merck Inc Nonclin Drug Safety West Point PA 19486 USA AstraZeneca S-43183 Molndal Sweden Bayer SAS Crop Sci Div Toxicol Data Sci F-06906 Sophia Antipolis France Pfizer Machine Learning Res Worldwide Res Dev & Med D-10785 Berlin Germany Recursion London N1C 4AG England Novo Nordisk US R&D Computat Drug Design Digital Sci & Innovat Lexington MA 02421 USA Sanofi Babraham Res Campus Cambridge CB22 3AT England Eli Lilly & Co Bracknell RG12 1PU England NIH NIEHS DTT NICEATM Res Triangle Pk NC USA Relay Therapeut Cambridge MA 02141 USA Nonclin Safety Cambridge MA 19426 USA Uppsala Univ Dept Pharmaceut Biosci Sci Life Lab S-751 24 Uppsala Sweden Phenaros Pharmaceut AB S-75239 Uppsala Sweden Khalifa Univ Sci & Technol Coll Med & Hlth Sci Abu Dhabi 127788 U Arab Emirates

machine learning (ML) is increasingly valuable for predicting molecular properties and toxicity in drug discovery. However, toxicity-related end points have always been challenging to evaluate experimentally with respect to in vivo translation due to the required resources for human and animal studies;this has impacted data availability in the field. ML can augment or even potentially replace traditional experimental processes depending on the project phase and specific goals of the prediction. For instance, models can be used to select promising compounds for on-target effects or to deselect those with undesirable characteristics (e.g., off-target or ineffective due to unfavorable pharmacokinetics). However, reliance on ML is not without risks, due to biases stemming from nonrepresentative training data, incompatible choice of algorithm to represent the underlying data, or poor model building and validation approaches. This might lead to inaccurate predictions, misinterpretation of the confidence in ML predictions, and ultimately suboptimal decision-making. Hence, understanding the predictive validity of ML models is of utmost importance to enable faster drug development timelines while improving the quality of decisions. This perspective emphasizes the need to enhance the understanding and application of machine learning models in drug discovery, focusing on well-defined data sets for toxicity prediction based on small molecule structures. We focus on five crucial pillars for success with ML-driven molecular property and toxicity prediction: (1) data set selection, (2) structural representations, (3) model algorithm, (4) model validation, and (5) translation of predictions to decision-making. Understanding these key pillars will foster collaboration and coordination between ML researchers and toxicologists, which will help to advance drug discovery and development.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Streaming active learning strategies for real-life credit card fraud detection: assessment and visualization

引用

INTErNATIONAL JOUrNAL OF dATA SCIENCE ANd ANALYTICS 2018年第4期5卷 285-300页

作者： Carcillo, Fabrizio Le Borgne, Yann-Ael Caelen, Olivier Bontempi, Gianluca Univ Libre Bruxelles ULB Fac Sci Comp Sci Dept Machine Learning Grp Brussels Belgium Worldline R&D Brussels Belgium

Credit card fraud detection is a very challenging problem because of the specific nature of transaction data and the labeling process. The transaction data are peculiar because they are obtained in a streaming fashion, and they are strongly imbalanced and prone to non-stationarity. The labeling is the outcome of an active learning process, as every day human investigators contact only a small number of cardholders (associated with the riskiest transactions) and obtain the class (fraud or genuine) of the related transactions. An adequate selection of the set of cardholders is therefore crucial for an efficient fraud detection process. In this paper, we present a number of active learning strategies and we investigate their fraud detection accuracies. We compare different criteria (supervised, semi-supervised and unsupervised) to query unlabeled transactions. Finally, we highlight the existence of an exploitation/exploration trade-off for active learning in the context of fraud detection, which has so far been overlooked in the literature.

关键词： Active learning Fraud detection Selection bias Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Industry-scale application and evaluation of deep learning for drug target prediction

引用

JOUrNAL OF CHEMINFOrMATICS 2020年第1期12卷 26-26页

作者： Sturm, Noe Mayr, Andreas Thanh Le Van Chupakhin, Vladimir Ceulemans, Hugo Wegner, Joerg Golib-dzib, Jose-Felipe Jeliazkova, Nina Vandriessche, Yves Bohm, Stanislav Cima, Vojtech Martinovic, Jan Greene, Nigel Vander Aa, Tom Ashby, Thomas J. Hochreiter, Sepp Engkvist, Ola Klambauer, Guenter Chen, Hongming AstraZeneca R&D Biopharmaceut Clin Pharmacol & Safety Sci Pepparedsleden 1 S-43183 Molndal Sweden Johannes Kepler Univ Linz LIT AI Lab Altenberger Str 69 A-4040 Linz Austria Johannes Kepler Univ Linz Inst Machine Learning Altenberger Str 69 A-4040 Linz Austria Janssen Pharmaceut High Dimens Biol & Discovery Data Sci Discovery S Turnhoutseweg 30 B-2349 Beerse Belgium Janssen R&D High Dimens Biol & Discovery Data Sci Discovery S 1400 McKean Rd Spring House PA 19002 USA Janssen Cilag SA High Dimens Biol & Discovery Data Sci Discovery S Calle Rio Jarama75A Toledo 45007 Spain Idea Consult Ltd Veldkant 31 Sofia 1000 Bulgaria Intel Corp Data Ctr Grp Veldkant 31 B-2550 Kontich Belgium VSB Tech Univ Ostrava IT4Innovat 17 Listopadu 2172-15 Ostrava 70800 Czech Republic IMEC Exasci Lab Kapeldreef 75 B-3001 Louvain Belgium AstraZeneca R&D Biopharmaceut Hit Discovery Discovery Sci Pepparedsleden 1 S-43183 Molndal Sweden

Artificial intelligence (AI) is undergoing a revolution thanks to the breakthroughs of machine learning algorithms in computer vision, speech recognition, natural language processing and generative modelling. recent works on publicly available pharmaceutical data showed that AI methods are highly promising for drug Target prediction. However, the quality of public data might be different than that of industry data due to different labs reporting measurements, different measurement techniques, fewer samples and less diverse and specialized assays. As part of a European funded project (ExCAPE), that brought together expertise from pharmaceutical industry, machine learning, and high-performance computing, we investigated how well machine learning models obtained from public data can be transferred to internal pharmaceutical industry data. Our results show that machine learning models trained on public data can indeed maintain their predictive power to a large degree when applied to industry data. Moreover, we observed that deep learning derived machine learning models outperformed comparable models, which were trained by other machine learning algorithms, when applied to internal pharmaceutical company datasets. To our knowledge, this is the first large-scale study evaluating the potential of machine learning and especially deep learning directly at the level of industry-scale settings and moreover investigating the transferability of publicly learned target prediction models towards industrial bioactivity prediction pipelines.

关键词： QSAr deep learning machine learning Structure-based virtual screening Cheminformatics Big data ChEMBL PubChem Prospective evaluation retrospective evaluation

来源：评论

学校读者我要写书评

暂无评论

An improved approach for estimating social POI boundaries with textual attributes on social media

arXiv

引用

arXiv 2020年

作者： Tran, Cong Vu, dung d. Shin, Won-Yong Department of Computer Science and Engineering Dankook University Yongin16890 Korea Republic of Machine Learning R&D Korbit AI MontrealQCH2T 2A3 Canada Machine Intelligence & Data Science Laboratory Yonsei University Seoul03722 Korea Republic of Yonsei University Seoul03722 Korea Republic of

It has been insufficiently explored how to perform density-based clustering by exploiting textual attributes on social media. In this paper, we aim at discovering a social point-of-interest (POI) boundary, formed as a convex polygon. More specifically, we present a new approach and algorithm, built upon our earlier work on social POI boundary estimation (SoBEst). This SoBEst approach takes into account both relevant and irrelevant records within a geographic area, where relevant records contain a POI name or its variations in their text field. Our study is motivated by the following empirical observation: a fixed representative coordinate of each POI that SoBEst basically assumes may be far away from the centroid of the estimated social POI boundary for certain POIs. Thus, using SoBEst in such cases may possibly result in unsatisfactory performance on the boundary estimation quality (BEQ), which is expressed as a function of the F-measure. To solve this problem, we formulate a joint optimization problem of simultaneously finding the radius of a circle and the POI’s representative coordinate c by allowing to update c. Subsequently, we design an iterative SoBEst (I-SoBEst) algorithm, which enables us to achieve a higher degree of BEQ for some POIs. The computational complexity of the proposed I-SoBEst algorithm is shown to scale linearly with the number of records. We demonstrate the superiority of our algorithm over competing clustering methods including the original SoBEst. © 2020, CC BY.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Adaptive distributed honeypot detection network for enhanced cybersecurity against doS and ddoS attacks

Results in Engineering

引用

results in Engineering 2025年 26卷

作者： V. Selva Kumar K.r. Mohan raj S. Gopalakrishnan G. Vennila d. dhinakaran P. Kavitha Department of Computer Science and Engineering P.S.R. Engineering College Sivakasi India Department of Information Technology Velammal Engineering College Chennai India Department of Computer Science & Engineering (Data Science) Madanapalle Institute of Technology & Science Andhra Pradesh India Department of Artificial Intelligence and Machine Learning School of Computing Mohan Babu University Tirupati India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Department of Computer Science and Engineering R.M.K. Engineering college Chennai India

The increasing prevalence and sophistication of denial of Service (doS) and distributed denial of Service (ddoS) attacks present significant challenges in ensuring the security and stability of modern networked systems. These attacks, characterized by their ability to disrupt services and compromise resources, require innovative and robust detection mechanisms to safeguard highly interactive environments such as honeypot systems. Traditional detection techniques often fall short in addressing the complexities posed by dynamic traffic patterns, diverse attack types, and real-time processing demands. This study introduces the Adaptive distributed Honeypot detection Network (AdHdN), a novel framework that leverages deep learning and probabilistic modeling to address the limitations of existing solutions. AdHdN employs a combination of deep Generative Adversarial Networks (dGANs) and discrete Hidden Markov Models (dHMMs) to achieve superior detection precision across various doS attack types, including application-level, protocol-level, and data volume attacks. Implemented in a highly interactive honeypot environment with distributed server and virtual machine configurations, AdHdN demonstrates remarkable adaptability and resilience. Performance evaluation using the IoTId20 dataset reveals that AdHdN consistently outperforms contemporary models, such as rBMd, BNdH, and AHdL. AdHdN achieves a true positive rate of 99.7% for protocol-level attacks, 99.4% for application-level attacks, and 97.5% for data volume attacks under low attack volumes, maintaining robust performance even as attack intensity scales. These results underscore AdHdN’s potential to redefine doS detection in dynamic and high-interaction environments, offering a scalable and efficient solution to contemporary cybersecurity challenges.

关键词： denial of service distributed denial of service Intrusion detection systems Generative adversarial networks real-time attack detection deep learning

来源：评论

学校读者我要写书评

暂无评论

A study on deformation of friction stir welded aluminum battery housing using inherent strain method 29th

A study on deformation of friction stir welded aluminum batt...

引用

29th International Ocean and Polar Engineering Conference, ISOPE 2019

作者： Kang, Sung Wook Kim, Sung Hwan Kim, Hwan Jin Kim, Jae Woong ryu, Hyun Su Jang, Young Jae Transport Machine Components R&D Group Korea Institute of Industrial Technology JinjuGyeongsangnam-do Korea Republic of Energy Plant R&D Group Korea Institute of Industrial Technology Busan Korea Republic of Smart Manufacturing Process R&D Group Korea Institute of Industrial Technology Gwangju Korea Republic of Dept. of Naval Architecture and Ocean Engineering Changwon National University ChangwonGyeongsangnam-do Korea Republic of Ship Structure Research Department Hyundai Heavy Industries Ulsan Korea Republic of

ISBN: (纸本)9781880653852

Friction stir welding (FSW) was invented in 1991 at The Welding Institute, and nowadays is widely utilized in the shipbuilding, automobile, aerospace, construction, electrical, machinery and equipment industries. FSW is applied to various structures due to its many advantages like high quality or no need for protective gas. Furthermore, the welding temperature is not over the melting point. Thus, the deformation and residual stress of FSW is less than fusion welding. recently, consumption of aluminum is increasing in order to reduce vehicle weight which can influence carrying capacity and velocity. However, when the size of the applied structure increases, deformation must be considered. Particularly, in the case of the thin plate, there is almost no temperature gradient at the top surface and the bottom surface, so that the shrinkage occurs after cooling to room temperature. In this study, 10 plates of 2.5 mm thickness used in aluminum battery housing were welded by friction stir welding. If the deformation is not taken into consideration, the problem arises that the tool cannot be positioned at the welding center line from the second welding line. In addition, the analysis is performed using the inherent strain method because thermal elasto-plastic analysis takes a long time to calculate the welding deformation. Finally, the welding deformation calculated by using the inherent strain method was verified by comparing with the thermal elasto-plastic analysis and experimental results. © 2019 by the International Society of Offshore and Polar Engineers (ISOPE).

关键词： residual stresses

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised learning with declaratively Specified Entropy Constraints 32

Semi-Supervised Learning with Declaratively Specified Entrop...

引用

32nd Conference on Neural Information Processing Systems (NIPS)

作者： Sun, Haitian Bing, Lidong Cohen, William W. Carnegie Mellon Univ Machine Learning Dept Pittsburgh PA 15213 USA Alibaba DAMO Acad Machine Intelligence Technol R&D Ctr Singapore Hangzhou Zhejiang Peoples R China

We propose a technique for declaratively specifying strategies for semi-supervised learning (SSL). SSL methods based on different assumptions perform differently on different tasks, which leads to difficulties applying them in practice. In this paper, we propose to use entropy to unify many types of constraints. Our method can be used to easily specify ensembles of semi-supervised learners, as well as agreement constraints and entropic regularization constraints between these learners, and can be used to model both well-known heuristics such as co-training, and novel domain-specific heuristics. Besides, our model is flexible as to the underlying learning mechanism. Compared to prior frameworks for specifying SSL techniques, our technique achieves consistent improvements on a suite of well-studied SSL benchmarks, and obtains a new state-of-the-art result on a difficult relation extraction task.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Application of CBr for Intelligent Process Control of a WWTP 22

Application of CBR for Intelligent Process Control of a WWTP

引用

22nd International Conference of the Catalan-Association-for-Artificial-Intelligence (CCIA)

作者： Pascual-Panach, Josep Angel Cuguero-Escofet, Miguel Sanchez-Marre, Miguel Aguilo-Martos, Pere CCB Serv Mediambientals SAU Barcelona Spain Consorci Besos Tordera Barcelona Spain Univ Politecn Cataluna Knowledge Engn & Machine Learning Grp KEMLG Intelligent Data Sci & Artificial Intelligence Re BarcelonaTech Barcelona Spain Consorci Besos Tordera R&D Dept 241 St Julia Ave Granollers 08103 Barcelona Spain

ISBN: (纸本)9781643680156;9781643680149

This paper proposes the use of a Case-Based reasoning (CBr) system for the control and the supervision of a real wastewater treatment plant (WWTP). A WWTP is a critical system which aims to ensure the quality of the water discharged to the receiving bodies, stablished by applicable regulations. At the current stage the proposed methodology has been tested off-line on a real system for the control of the aeration process in the biological treatment of a WWTP within the ambit of Consorci Besos Tordera (CBT), a local water administration in the area of Barcelona. For this purpose, data mining methods are considered to extract the available knowledge from historical data to find a useful case base to be able to generate set-points for the local controllers in the WWTP. The results presented in this work are evaluated taking into account the performance of the CBr method e.g. case base size, CBr cycle time or number of cases resolved satisfactorily (forthcoming steps will include on-line tests). For this purpose, some Key Performance Indicators (KPI) are designed together with the plant manager and process experts, in order to monitor key parameters of the WWTP which are representative of the performance of the control and supervision system. Hence, these KPI are related with water quality regulations -e.g. ammonia concentration in the WWTP effluent- and the economic cost efficiency -e.g. electrical consumption of the installation. In order to evaluate the results, different flat-based memory organizations (i.e. cases are stored sequentially in a list) for the case base are considered. First, a unique case base is used. At the current stage and for the results shown in this work, this case base is divided in multiple libraries depending on a case classification. Finally, the combination of this approach with rule-Based reasoning (rBr) methods is proposed for the next stages of the work.

关键词： Case-Based reasoning Intelligent Process Control Wastewater Treatment Plant data Mining

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：