检索结果-内蒙古大学图书馆

Uncovering the Benefits of Machine Learning for Automating Financial Regulatory Tasks

学校读者我要写书评

暂无评论

Uncovering the Benefits of Machine Learning for Automating F...

E-mobility, Power Control and Smart Systems (ICEMPS), International Conference on

作者： Sagar Varma Samanthapudi Piyush Rohella Sheetal Temara Ketan Gupta S. Dhanasekaran Applied Data Science The Polis Center at Indiana University Purdue University Indianapolis Indianapolis Indiana USA Principal Product Manager Payments & Commerce GoDaddy Edmonds Washington USA Dept of Computer & Information Sciences University of the Cumberlands Williamsburg KY USA Dept. of Information Technology University of The Cumberlands Williamsburg KY USA Department of ECE Sri Eshwar College of Engineering Coimbatore Tamil Nadu INDIA

ISBN: (数字)9798350394399

ISBN: (纸本)9798350394405

Machine Learning (ML) gives the ability to automate economic regulatory responsibilities in terms of price savings and more green process control. Current advances in ML have enabled the improvement of models that may interpret complicated sets of facts and automate the technique of extracting the preferred facts from these records. The development of such models gives a price-effective and efficient opportunity to greater luxurious and time-consuming guide labor. Moreover, these fashions are capable of perceiving and correctly categorizing data to ensure information accuracy and compliance with regulatory policies. It allows the company to adhere to policies without human oversight, lowering each value and time constraints. It will be further prolonged to other factors of the enterprise by making use of unsupervised fashions and fashions advanced on switch learning, together with deep learning. Those models allow the automation of responsibilities inclusive of assessing the threat associated with investments or transactions, facilitating the development of quicker and more knowledgeable techniques. Ordinary, the usage of ML fashions for financial law automatization processes is precious for decreasing price and time constraints and making sure of compliance. Through leveraging the ability of ML, financial institutions can take advantage of extra internal manner efficiency and statistics accuracy with fewer risks.

关键词： Accuracy Regulators Biological system modeling Machine learning Switches Time factors Stakeholders

Investigating the Role of AI in Personalized Consumer Banking Experiences

学校读者我要写书评

暂无评论

Investigating the Role of AI in Personalized Consumer Bankin...

E-mobility, Power Control and Smart Systems (ICEMPS), International Conference on

作者： Piyush Rohella Sheetal Temara Sagar Varma Samanthapudi Ketan Gupta K. Suganyadevi Principal Product Manager Payments & Commerce GoDaddy Edmonds Washington USA Dept of Computer & Information Sciences University of the Cumberlands Williamsburg KY USA Applied Data Science The Polis Center at Indiana University Purdue University Indianapolis Indianapolis Indiana USA Dept. of Information Technology University of The Cumberlands Williamsburg KY USA Department of ECE Sri Eshwar College of Engineering Coimbatore Tamil Nadu INDIA

ISBN: (数字)9798350394399

ISBN: (纸本)9798350394405

This research examines the function of synthetic Intelligence in developing customized purchaser banking reviews. Artificial Intelligent -based total gear is increasingly being followed to offer consumers customized banking reports. Studies into the use of AI in this context will tell the layout of future banking products and services. The primary intention of this research is to understand the modern technological and personal adoption developments related to Artificial Intelligent and customized banking reviews. Particularly, this study will identify the modern use cases of Artificial Intelligent in personalized banking, look into clients' attitudes and motivations towards Artificial Intelligent -enabled banking experiences, and discover the ability possibilities and challenges related to utilizing Artificial Intelligent in growing individualized banking studies for purchasers. Additionally, the role of ethical issues in implementing and the use of Artificial Intelligent in personalized consumer banking experiences may be evaluated. This study is crucial for presenting a better understanding of the function of Artificial Intelligent in developing personalized and moral consumer banking experiences.

关键词： Ethics Reviews Shape Power control Layout Banking Fraud

Research of Association Rules Mining based on Fuzzy Alarm Extraction 2020

学校读者我要写书评

暂无评论

Research of Association Rules Mining based on Fuzzy Alarm Ex...

4th International Conference on Digital Signal Processing, ICDSP 2020

作者： Tongyan, Li Dong, Lei Zhiguang, Qin Chengdu University of Information Technology Dept. of Communication Engineering China Data Security Key Laboratory of Sichuan Province University of Electronic Science and Technology of China China

ISBN: (纸本)9781450376877

In communication alarm correlation analysis, original alarm data often have problems about information redundancy, data incompleteness, time synchronization and "sharp boundary". This paper proposed a novel alarm extraction algorithm in order to resolve above problems. We first fuzzy the original alarms to avoid "sharp boundary"during the alarm preprocessing process, and then we proposed a novel double constraint based sliding time window method to improve the efficiency on extracting data. Performance tests of the algorithm indicate that this method has higher extracting efficiency than traditional methods, which is suitable for alarm data in telecommunication networks. © 2020 ACM.

关键词： Efficiency

Bridging the technology gap between industry and semantic web: Generating databases and server code from RDF

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Schröder, Markus Schulze, Michael Jilek, Christian Dengel, Andreas Smart Data & Knowledge Services Dept. DFKI GmbH Kaiserslautern Germany Computer Science Dept. TU Kaiserslautern Germany

Despite great advances in the area of Semantic Web, industry rather seldom adopts Semantic Web technologies and their storage and query concepts. Instead, relational databases (RDB) are often deployed to store business-critical data, which are accessed via REST interfaces. Yet, some enterprises would greatly benefit from Semantic Web related datasets which are usually represented with the Resource Description Framework (RDF). To bridge this technology gap, we propose a fully automatic approach that generates suitable RDB models with REST APIs to access them. In our evaluation, generated databases from different RDF datasets are examined and compared. Our findings show that the databases sufficiently reflect their counterparts while the API is able to reproduce rather simple SPARQL queries. Potentials for improvements are identified, for example, the reduction of data redundancies in generated databases. Copyright © 2020, The Authors. All rights reserved.

关键词： Digital storage

A Dual Self-supervised Deep Trajectory Clustering Method

学校读者我要写书评

暂无评论

A Dual Self-supervised Deep Trajectory Clustering Method

IEEE Symposium on Computers and Communications (ISCC)

作者： Junjun Si Yang Xiang Jin Yang Li Li Bo Tu Xiangqun Chen Rongqing Zhang School of Software & Microelectronics Peking University Beijing China Research & Development Dept. Hezhixin (Shandong) Big Data Technology Co. Ltd. Jinan China School of Information Management Beijing Information Science & Technology University Beijing China School of Software Engineering Tongji University Shanghai China

Trajectory clustering is a cornerstone task in trajectory mining. Sparse and noisy trajectories like Call Detail Records (CDR) have become popular with the rapid development of mobile applications. However, existing trajectory clustering methods' performance is limited on these trajectories. Therefore, we propose a dual Self-supervised Deep Trajectory Clustering (SDTC) method, to optimize trajectory representation and clustering jointly. First, we leverage the BERT model to learn spatial-temporal mobility patterns and incorporate them into the embeddings of location IDs. Second, we fine-tune the BERT model to learn cluster-friendly representations of trajectories by designing a dual self-supervised cluster layer, which improves the intra-cluster similarities and inter-cluster dissimilarities. Third, we conduct extensive experiments with two real-world datasets. Results show that SDTC improves the clustering accuracy by 12.1% (on a noisy and sparse dataset) and 3.8% (on a very sparse dataset) compared with SOTA deep clustering methods.

关键词：

The person index challenge: Extraction of persons from messy, short Texts

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Schröder, Markus Jilek, Christian Schulze, Michael Dengel, Andreas Smart Data & Knowledge Services Dept. DFKI GmbH Kaiserslautern Germany Computer Science Dept. TU Kaiserslautern Germany

When persons are mentioned in texts with their first name, last name and/or middle names, there can be a high variation which of their names are used, how their names are ordered and if their names are abbreviated. If multiple persons are mentioned consecutively in very different ways, especially short texts can be perceived as "messy". Once ambiguous names occur, associations to persons may not be inferred correctly. Despite these eventualities, in this paper we ask how well an unsupervised algorithm can build a person index from short texts. We define a person index as a structured table that distinctly catalogs individuals by their names. First, we give a formal definition of the problem and describe a procedure to generate ground truth data for future evaluations. To give a first solution to this challenge, a baseline approach is implemented. By using our proposed evaluation strategy, we test the performance of the baseline and suggest further improvements. For future research the source code is publicly available. Copyright © 2020, The Authors. All rights reserved.

关键词： Extraction

Usage of Computer Aided Methods for Detection and Evaluation of Breast Cancer in Mammograms

学校读者我要写书评

暂无评论

Usage of Computer Aided Methods for Detection and Evaluation...

Smart Electronics and Communication (ICOSEC), International Conference on

作者： M. Nagabhushana Rao L. Venkateswara Reddy D. Ganesh Lakkireddy. Udanth Reddy R Madana Mohana CSE Marri Laxman reddy institute of Technology & Management Hyderabad Department of CSE Joginapally B. R. Engineering College Yenkepally RR Dist Hyderabad Telangana India CSE Mohan Babu University (Erstwhile Sree Vidyanikethan Engineering College(Autonomous) Tirupati Andhra Pradesh India Dept. of ECE VIT-AP University Amaravath Artificial Intelligence & Data Science Chaitanya Bharathi Institute of Technology Hyderabad Telangana India

ISBN: (数字)9798331504403

ISBN: (纸本)9798331504410

Breast cancer accounts for an extremely high annual death rate. Many tools have been created to facilitate earlier diagnosis of breast cancer, which is the most common cancer among females. According to the research, cancer of the breast is also regarded as the second most deadly form of the disease. It is the most prominent kind of the disease and the top reason for death among females worldwide. Any progress made in the early detection and identification of cancer is crucial to maintaining good health. Therefore, it is essential to improve both the therapeutic aspect and the survival standard of patients by utilizing high precision in cancer prognosis. A reliable, effective, and speedy reaction from medical professionals is provided by an automatic disease identification system, which also reduces the danger of death. Recently, breast cancer screening methods that utilise deep learning have shown promising results, allowing for earlier identification and thereby enhancing patients’ chances of survival thanks to the introduction of artificial intelligence (AI). Deep learning reduces the need for manual intervention while extracting features, in comparison to traditional machine learning methods. We provide a brief overview of deep learning techniques, data availability, and the many breast cancer screening options, such as mammography, thermography, ultrasound, and MRI. Using demographic, laboratory, & mammographic data, this investigation sought to forecast breast cancer using various Deep learning algorithms. Ultimately, we apply artificial intelligence to breast cancer clinical trials and compare the proposed approach to current algorithms.

关键词： Deep learning Ultrasonic imaging Manuals Feature extraction Breast cancer Mammography Reliability Prognostics and health management Standards Medical diagnostic imaging

Observer study-based evaluation of TGAN architecture used to generate oncological PET images

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Fedrigo, Roberto Yousefirizi, Fereshteh Liu, Ziping Jha, Abhinav K. Bergen, Robert V. Rajotte, Jean-Francois Ng, Raymond T. Bloise, Ingrid Harsini, Sara Kadrmas, Dan J. Uribe, Carlos Rahmim, Arman Dept. of Integrative Oncology BC Cancer Research Institute VancouverBC Canada Dept. of Physics and Astronomy Univ. of British Columbia VancouverBC Canada Dept. of Biomedical Engineering Washington Univ. in St. Louis St. LouisMO United States Mallinckrodt Institute of Radiology Washington Univ. School of Med. St. LouisMO United States Univ. of British Columbia Data Science Institute 6339 Stores Road VancouverBC Canada Dept. of Functional Imaging BC Cancer VancouverBC Canada Dept. Of Radiology and Imaging Sciences University of Utah Salt Lake CityUT United States Dept. of Radiology Univ. of British Columbia VancouverBC Canada

The application of computer-vision algorithms in medical imaging has increased rapidly in recent years. However, algorithm training is challenging due to limited sample sizes, lack of labeled samples, as well as privacy concerns regarding data sharing. To address these issues, we previously developed (Bergen et al. 2022) a synthetic PET dataset for Head & Neck (H&N) cancer using the temporal generative adversarial network (TGAN) architecture and evaluated its performance segmenting lesions and identifying radiomics features in synthesized images. In this work, a two-alternative forced-choice (2AFC) observer study was performed to quantitatively evaluate the ability of human observers to distinguish between real and synthesized oncological PET images. In the study eight trained readers, including two board-certified nuclear medicine physicians, read 170 real/synthetic image pairs presented as 2D-transaxial using a dedicated web app. For each image pair, the observer was asked to identify the "real" image and input their confidence level with a 5-point Likert scale. P-values were computed using the binomial test and Wilcoxon signed-rank test. A heat map was used to compare the response accuracy distribution for the signed-rank test. Response accuracy for all observers ranged from 36.2% [27.9-44.4] to 63.1% [54.8-71.3]. Six out of eight observers did not identify the real image with statistical significance, indicating that the synthetic dataset was reasonably representative of oncological PET images. Overall, this study adds validity to the realism of our simulated H&N cancer dataset, which may be implemented in the future to train AI algorithms while favoring patient confidentiality and privacy protection. Copyright © 2023, The Authors. All rights reserved.

关键词： Network architecture

Turbulent burning velocity and thermo-diffusive instability of premixed flames

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Lee, Hsu Chew Wu, BuChen Dai, Peng Wan, Minping Lipatnikov, Andrei N. Guangdong Provincial Key Laboratory of Turbulence Research and Applications Department of Mechanics and Aerospace Engineering Southern University of Science and Technology Shenzhen518055 China Guangdong-Hong Kong-Macao Joint Laboratory for Data-Driven Fluid Mechanics and Engineering Applications Southern University of Science and Technology Shenzhen518055 China Jiaxing Research Institute Southern University of Science and Technology Zhejiang Jiaxing314031 China Dept. of Mechanics and Maritime Sciences Chalmers University of Technology Göteborg412 96 Sweden

Reported in the paper are results of unsteady three-dimensional direct numerical simulations of laminar and turbulent, lean hydrogen-air, complex-chemistry flames propagating in forced turbulence in a box. To explore the eventual influence of thermo-diffusive instability of laminar flames on turbulent burning velocity, (i) a critical length scale Λn that bounds regimes of unstable and stable laminar combustion is numerically determined by gradually decreasing the width Λ of computational domain until a stable laminar flame is obtained and (ii) simulations of turbulent flames are performed by varying the width from Λ n (in this case, the instability is suppressed) to Λ > Λn (in this case, the instability may grow). Moreover, simulations are performed either using mixture-averaged transport properties (low Lewis number flames) or setting diffusivities of all species equal to heat diffusivity of the mixture (equidiffusive flames), with all other things being equal. Obtained results show a significant increase in turbulent burning velocity UT when the boundary Λ = Λn is crossed in weak turbulence, but almost equal values of UT are computed at Λ n and Λ > Λn in moderately turbulent flames characterized by Karlovitz number equal to 3.4 or larger. These results imply that thermo-diffusive instability of laminar premixed flames substantially affects burning velocity in weak turbulence only, in line with a simple criterion proposed by Chomiak and Lipatnikov (Phys. Rev. E 107, 015102, 2023). Copyright © 2023, The Authors. All rights reserved.

关键词： Stability