检索结果-内蒙古大学图书馆

MELLOddY: Cross-pharma Federated learning at Unprecedented Scale Unlocks Benefits in QSAr without Compromising Proprietary Information

引用

JOUrNAL OF CHEMICAL INFOrMATION ANd MOdELING 2023年第7期64卷 2331-2344页

作者： Heyndrickx, Wouter Mervin, Lewis Morawietz, Tobias Sturm, Noe Friedrich, Lukas Zalewski, Adam Pentina, Anastasia Humbeck, Lina Oldenhof, Martijn Niwayama, ritsuya Schmidtke, Peter Fechner, Nikolas Simm, Jaak Arany, Adam drizard, Nicolas Jabal, rama Afanasyeva, Arina Loeb, regis Verma, Shlok Harnqvist, Simon Holmes, Matthew Pejo, Balazs Telenczuk, Maria Holway, Nicholas dieckmann, Arne rieke, Nicola Zumsande, Friederike Clevert, djork-Arne Krug, Michael Luscombe, Christopher Green, darren Ertl, Peter Antal, Peter Marcus, david do Huu, Nicolas Fuji, Hideyoshi Pickett, Stephen Acs, Gergely Boniface, Eric Beck, Bernd Sun, Yax Gohier, Arnaud rippmann, Friedrich Engkvist, Ola Goeller, Andreas H. Moreau, Yves Galtier, Mathieu N. Schuffenhauer, Ansgar Ceulemans, Hugo Janssen Pharmaceut NV B-2340 Beerse Belgium AstraZeneca R&D Cambridge CB2 0SL England Bayer Pharm AG Global Drug Discovery Chem Res Computat Chem D-42096 Wuppertal Germany Novartis Inst BioMed Res CH-4002 Basel Switzerland Merck KGaA Global Res & Dev D-64293 Darmstadt Germany Amgen Res Munich GmbH D-81477 Munich Germany Bayer AG Machine Learning Res Res & Dev Pharmaceut D-13353 Berlin Germany Boehringer Ingelheim Pharm GmbH & Co KG BI Med Chem Dept D-88397 Biberach Germany Katholieke Univ Leuven ESAT STADIUS B-3001 Heverlee Belgium Inst Rech Servier F-78290 Croissy Sur Seine Ile De France France Discngine F-75012 Paris France Iktos F-75017 Paris France Astellas Pharma Inc Modal Informat Grp Digital Res Solut Adv Informat & Analyt Tsukuba Ibaraki 3058585 Japan GlaxoSmithKline Computat Sci Brentford SG1 2NY Herts England Budapest Univ Technol & Econ Dept Networked Syst & Serv H-1111 Budapest Hungary Owkin F-75010 Paris France Bayer AG API Prod Prod Supply Pharmaceut D-59192 Bergkamen Germany NVIDIA GmbH D-81369 Munich Germany Budapest Univ Technol & Econ Dept Measurement & Informat Syst H-1111 Budapest Hungary Substra Fdn Labelia Labs F-44000 Nantes France Amgen Res Thousand Oaks CA 91320 USA AstraZeneca Mol AI Discovery Sci S-43150 Molndal Sweden Owkin F-44000 Nantes France

Federated multipartner machine learning has been touted as an appealing and efficient method to increase the effective training data volume and thereby the predictivity of models, particularly when the generation of training data is resource-intensive. In the landmark MELLOddY project, indeed, each of ten pharmaceutical companies realized aggregated improvements on its own classification or regression models through federated learning. To this end, they leveraged a novel implementation extending multitask learning across partners, on a platform audited for privacy and security. The experiments involved an unprecedented cross-pharma data set of 2.6+ billion confidential experimental activity data points, documenting 21+ million physical small molecules and 40+ thousand assays in on-target and secondary pharmacodynamics and pharmacokinetics. Appropriate complementary metrics were developed to evaluate the predictive performance in the federated setting. In addition to predictive performance increases in labeled space, the results point toward an extended applicability domain in federated learning. Increases in collective training data volume, including by means of auxiliary data resulting from single concentration high-throughput and imaging assays, continued to boost predictive performance, albeit with a saturating return. Markedly higher improvements were observed for the pharmacokinetics and safety panel assay-based task subsets.

关键词： Assays Bioinformatics and computational biology drug discovery machine learning Structure activity relationship

来源：评论

学校读者我要写书评

暂无评论

MANAGING NEXT-GENErATION NETWOrKS FOr INTELLIGENT SErVICES ANd APPLICATIONS

引用

IEEE NETWOrK 2022年第3期36卷 4-6页

作者： Aloqaily, Moayad Sedjelmac, Hichem Tseng, Lewis da Costa Cordeiro, Weverton Luis Zhang, Qian Amer Univ Middle East AUM Kuwait Kuwait Al Ain Univ Fac Engn Abu Dhabi U Arab Emirates Analytics Inc Ottawa ON Canada Mohamed Bin Zayed Univ Artificial Intelligence MB Machine Learning Dept Abu Dhabi U Arab Emirates Ericsson R&D France Paris France Orange Labs Cyber Secur & AI Paris France Orange Labs Paris France Univ Burgundy DRIVE Lab Dijon France Boston Coll Dept Comp Sci Chestnut Hill MA 02167 USA Toyota Info Technol Ctr Mountain View CA USA Fed Univ Rio Grande Sul FRGS Inst Informat INF Porto Alegre RS Brazil Hong Kong Univ Sci & Technol Hong Kong Peoples R China Hong Kong Univ Sci & Technol Engn Hong Kong Peoples R China Hong Kong Univ Sci & Technol Dept Comp Sci & Engn Hong Kong Peoples R China Huawei HKUST Innovat Lab Hong Kong Peoples R China HKUST Digital Life Res Ctr Hong Kong Peoples R China Microsoft Res Asia Beijing Peoples R China Microsoft Res Asia Wireless & Networking Grp Beijing Peoples R China

Next-generation networks (NGNs) integrate the functionalities of a plethora of established and emerging technologies such as 5G, artificial intelligence (AI), edge intelligence, network softwarization, and data plane programmability. NGNs promise to achieve ultra-fast data rates and minimal latency in wireless communication and networking. They enable smart and autonomous services and applications through AI and machine learning (ML). Coupled with advances in end-user devices, NGNs enable a plethora of smart services and user-defined applications. Given the rise in system complexity and the exponential increase in the amount of data exchanged through networks, new state-of-the-art NGN management solutions are needed. By adapting cooperative and distributed management solutions, more reliable and efficient services and applications are conveyed to end users. Moreover, with distributed learning solutions, NGNs could be optimized to support the dynamic nature of network configuration and enable end-to-end system automation. For instance, the integration of federated learning (FL), deep reinforcement learning (drL), and blockchain to NGNs can support scalable, secure, and diversified services and applications. Furthermore, through data plane programmability, network intelligence could be implemented directly on programmable devices in the network core. An intelligent forwarding plane would enable faster reaction to network events without depending on time-consuming exchange between the data and control planes.

关键词： Special issues and sections Next generation networking reinforcement learning distributed management Computer aided instruction Complexity theory Blockchains Collaborative work 5G mobile communication deep learning

来源：评论

学校读者我要写书评

暂无评论

Hybrid deep learning for International Trading: Integrating LSTM and Transformer Models

Hybrid Deep Learning for International Trading: Integrating ...

引用

Sentiment Analysis and deep learning (ICSAdL), International Conference on

作者： T. S. Akhila J. relin Francis raj d. Kani Jesintha r. Santhana Krishnan V. Vinoth Kumar P. Sundaravadivel Department of Electronics and Communication Engineering Dhanalakshmi College of Engineering Chennai India Department of Electronics and Communication Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Department of Computer Science and Engineering SCAD College of Engineering and Technology Cheranmahadevi India Department of Electronics and Communication Engineering SCAD College of Engineering and Technology Cheranmahadevi India Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai India Department of Artificial Intelligence and Machine Learning Saveetha Engineering College Chennai India

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

This research proposes a hybrid deep learning model combining Long Short-Term Memory (LSTM) networks and Transformers to enhance decision-making in international trading. The model leverages advanced techniques such as roBErTa for text tokenization, FinBErT for sentiment analysis, and XLM-roberta for multilingual language processing. LSTM is employed to analyze sequential numerical data like historical prices and trading volumes, providing accurate price and volatility forecasts. The Transformer component processes textual data to extract sentiment classifications and event-driven market impacts, facilitating a comprehensive understanding of market conditions. A fully connected fusion layer integrates insights from both components, enabling the model to classify market conditions holistically. The optimization process utilizes the Adam optimizer with learning rate scheduling to ensure efficient and effective training. Loss functions like Mean Squared Error (MSE) and Cross-Entropy Loss are employed to optimize numerical predictions and categorical outcomes, respectively. By combining temporal analysis with sentiment-driven insights, this hybrid model offers improved price forecasting, advanced multilingual sentiment analysis, and event-driven market condition predictions. The proposed approach aims to provide traders with actionable insights, enabling more informed decision-making in the highly dynamic and multilingual environment of international trading.

关键词： deep learning Adaptation models Sentiment analysis Analytical models Predictive models Transformers data models Numerical models Multilingual Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Computational Approach for respiratory Pressure Parameters in Neonatal Ventilation

Computational Approach for Respiratory Pressure Parameters i...

引用

Annual Siberian russian Workshop on Electron devices and Materials (EdM)

作者： daria Lipchak Aleksey Chupov Anton dolganov Aleksei Zhdanov Medical Devices R&D Bureau Joint Stock Company “Production Association “Urals Optical & Mechanical Plant” named after Mr. E. S. Yalamov” Yekaterinburg Russia Engineering School of Information Technologies Telecommunications and Control Systems Ural Federal University named after the first President of Russia B.N. Yeltsin Yekaterinburg Russia Machine Learning and Data Analytics Lab University of Erlangen-Nuremberg Erlangen Germany

In the context of mechanical ventilation, the accurate calculation of secondary pressure parameters is essential for clinicians to effectively assess a patient's clinical condition. In the case of neonatal resuscitation with the T-piece, both the inspiratory and expiratory triggers are manually operated. The device provides a constant flow at the initiation of inspiration and reduces the flow to limit output pressure according to the set peak inspiratory pressure. However, without an algorithmic classification of the inspiration and expiration pressure, data analysis may only be performed postfactum. To address the need for the separate trend analysis of PIP and PEEP in non-invasive mechanical ventilation with a T-piece, there is a requirement to develop and implement an accurate algorithm for respiratory pressure parameters calculation. In this study, we review the current state-of-the-art methods for the calculation of respiratory pressure parameters for non-invasive mechanical ventilation with a T-piece. We then present the development and implementation of an algorithm for respiratory pressure parameters calculation and discuss the results of the analysis. This algorithm is designed to provide accurate and reliable measurements of PIP and PEEP in neonatal resuscitation with the T-piece, allowing clinicians to more effectively monitor and assess a patient's clinical condition during mechanical ventilation. The results demonstrate the effectiveness of the algorithm in accurately calculating PIP and PEEP values, providing valuable insights into the patient's respiratory mechanics and helping to inform clinical decision-making.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Python Based Fake Jobs Post Identification And Analysis Methodology Using Elevated learning Strategy

A Novel Python Based Fake Jobs Post Identification And Analy...

引用

Innovation in Technology (ASIANCON), Asian Conference on

作者： Vijayalakshmi V Anni Princy B Vijay Anand Kandaswamy S. Sujatha Sarva Naveen Kumar Aruna V Department of CSE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Artificial Intelligence and Machine Learning Panimalar Engineering College Chennai Tamil Nadu India Department of Electronics and Communication Engineering R.M.K. Engineering College Kavaraipettai Tamil Nadu India Department of EEE Sri Sairam College of Engineering Bangalore Karnataka India Department of ECE MLR Institute of Technology Hyderabad India Department of Management Studies St.Joseph's Institute of Technology Chennai Tamil Nadu India

ISBN: (数字)9798350354218

ISBN: (纸本)9798350354225

Online job boards and portals have grown in popularity in recent years, making it easier and more effective for people to look for work. False job ads have proliferated with the advent of digital transformation, which is both an opportunity and a threat. People looking for work may fall victim to these misleading listings, which can lead them astray, waste their time, and expose them to scams. The research presents Elevated learning based Fake Job Prediction (ELFJP), a claim that utilizes learning based classification algorithms to stop fake job advertisements on the internet. To assess the effectiveness of the suggested method, it is cross-validated using a traditional learning model known as random Forest Classifier (rFC). We find the best job fraud detection model by comparing the results of different classifiers. Web fraud may be detected and prevented with the help of these classifiers. In a sea of seemingly legitimate job ads, it helps to single out the fraudulent ones. This system is able to identify fake job ads on the web by integrating classifiers with an ensemble learning model and then comparing and evaluating the results. In light of the ever-changing strategies used by con artists, the research stresses the significance of being proactive. To keep up with ever-changing fraud tactics, machine learning models are continuously improved and adjusted. The ultimate aim of this proposed approach is to help make a safer online job market by reducing the likelihood of fraudulent ads and increasing confidence among those looking for work.

关键词： Technological innovation digital transformation Employment Forestry Lead Fraud Ensemble learning Stress random forests Portals

来源：评论

学校读者我要写书评

暂无评论

Visual Attention Prediction for Stereoscopic Video by Multi-Module Fully Convolutional Network

引用

IEEE TrANSACTIONS ON IMAGE PrOCESSING 2019年第11期28卷 5253-5265页

作者： Fang, Yuming Zhang, Chi Huang, Hanqin Lei, Jianjun Jiangxi Univ Finance & Econ Sch Informat Management Nanchang 330032 Jiangxi Peoples R China Machine Learning R&D Dept Sina Weibo Peoples R China Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China

Visual attention is an important mechanism in the human visual system (HVS) and there have been numerous saliency detection algorithms designed for 2d images/video recently. However, the research for fixation detection of stereoscopic video is still limited and challenging due to the complicated depth and motion information. In this paper, we design a novel multi-module fully convolutional network (MM-FCN) for fixation detection of stereoscopic video. Specifically, we design a fully convolutional network for spatial saliency prediction (S-FCN), where the initial spatial saliency map of stereoscopic video is learned by image database of object detection. Furthermore, the fully convolutional network for temporal saliency prediction (T-FCN) is constructed by combining saliency results from S-FCN and motion information from video frames. Finally, the fully convolutional network for depth fixation prediction (d-FCN) is designed to compute the final fixation map of stereoscopic video by learning depth features with spatiotemporal features from T-FCN. The experimental results show that the proposed MM-FCN can predict fixation results for stereoscopic video more effectively and efficiently than other related fixation prediction methods.

关键词： Visual attention stereoscopic video spatiotemporal saliency detection fixation detection fully convolutional network

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

引用

KNOWLEdGE-BASEd SYSTEMS 2021年 213卷 106710-106710页

作者： Tran, Cong Vu, dung d. Shin, Won-Yong Dankook Univ Dept Comp Sci & Engn Yongin 16890 South Korea Korbit AI Machine Learning R&D Montreal PQ H2T 2A3 Canada Yonsei Univ Machine Intelligence & Data Sci Lab Seoul 03722 South Korea Yonsei Univ Sch Math & Comp Computat Sci & Engn Seoul 03722 South Korea

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. (C) 2020 Elsevier B.V. All rights reserved.

关键词： Boundary estimation quality Geo-tagged record representative coordinate Social point-of-interest boundary Spatio-textual data

来源：评论

学校读者我要写书评

暂无评论

Adaptive Movie recommendations: A deep learning Framework with Mood and Sentiment Integration

Adaptive Movie Recommendations: A Deep Learning Framework wi...

引用

Sustainable Communication Networks and Application (ICSCNA), International Conference on

作者： M. Saravana Karthikeyan S. Vijay Shankar r. Santhana Krishnan M. Sornavalli J. relin Francis raj P. Sundaravadivel Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Department of Electrical and Electronics Engineering Sona College of Technology Salem India Department of Electronics and Communication Engineering SCAD College of Engineering and Technology Cheranmahadevi India Department of Mathematics Velammal College of Engineering and Technology Madurai India Department of Electronics and Communication Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Department of Artificial Intelligence and Machine Learning Saveetha Engineering College Chennai India

ISBN: (数字)9798331530013

ISBN: (纸本)9798331530020

This research study proposes an advanced movie recommendation system that combines deep learning models with mood detection and sentiment analysis for highly personalized suggestions. The system collects data from diverse sources, including user watch history from OTT platforms along with real-time social media sentiment from social media platforms. Additionally, wearable devices track heart rate to infer the user's emotional state during media interaction. The recommendation engine uses a multi-layered approach. Neural Collaborative Filtering (NCF) analyzes watch patterns, while BErT-based embeddings capture key movie metadata such as genres and actors for content-based filtering. The system also employs an LSTM model for mood-based recommendations, integrating heart rate data and social media sentiment to align suggestions with the user's current mood. Key advantages include a hybrid recommendation approach that combines collaborative filtering, content-based suggestions, and real-time mood analysis. The system adapts to both long-term preferences and short-term emotional states, delivering more relevant and personalized results. deployed on scalable cloud infrastructure (AWS EC2), with continuous learning from user feedback, the system ensures dynamic and evolving movie recommendations that enhance user satisfaction.

关键词： Heart rate Adaptation models Analytical models Sentiment analysis Accuracy Mood Social networking (online) Collaborative filtering Motion pictures real-time systems

来源：评论

学校读者我要写书评

暂无评论

Medical Image Classification Using Thermal Images and diagnosis of Carcinogen

Medical Image Classification Using Thermal Images and Diagno...

引用

Innovation and Novelty in Engineering and Technology (INNOVA), International Conference on

作者： Govinda rajulu. G L. Sharmila d. Venkatesan K Srinivas Nallam Krishnaiah K. Laxman Kumar Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology. Avadi Chennai Tamil Nadu India Dept. of Artificial Intelligence and Machine Learning St. Martin's Engineering College Hyderabad India Deptarment of CSE(AI & ML) St. Martin's Engineering College Hyderabad India Department of IT St. Martin's Engineering College Dhulapally Secunderabad Telangana India Deptartment of Computer Science and Design St. Martin's Engineering College Hyderabad India

ISBN: (数字)9798331505134

ISBN: (纸本)9798331505141

Lung and Colon (L&C) tumors are lethal sicknesses that can foster in a few organs all the while and, in specific circumstances, jeopardize human existence. Even though it is highly unlikely that these two types of cancer will develop simultaneously, delaying diagnosis significantly increases the likelihood of metastasis between the organs that are affected. To really treat specific sorts of malignant growth, histological determination is fundamental. In the past, doctors had to go through a long and difficult process to look at thermal images and figure out if a patient had cancer; however, this procedure may now be completed much more quickly thanks to the new technology options. Histological images of L&C tumors were classified using a hybrid deep learning (dL) model with an attention mechanism and a multipath network in this study. To zero in on the main attributes and negligence the less significant ones, a consideration component was utilized. In a multipath network, data travels over a number of channels before each channel is converted and the output from all of the branches is combined. The multipath network is similar to grouped convolution when simplified. The five thermal image categories of the LC25000 dataset were utilized. Among these classes were two for colon disease and three for cellular breakdown in the lungs. The proposed model was compared to a number of well-known dL models, such as resNet-50, VGG-16, and AlexNet. The proposed approach showed the best exhibition concerning exactness (99.2%), particularity (99.12%), responsiveness (99.28%), accuracy (99.12%), and F1 score (99.2%), as indicated by the exploratory discoveries

关键词： Technological innovation Accuracy Lungs Subject matter experts Medical services Colon Medical diagnostic imaging Cancer Tumors Testing

来源：评论

学校读者我要写书评

暂无评论

Advancing Alzheimer's Nodule detection Through a Comprehensive Multi-Scene deep learning Framework

Advancing Alzheimer's Nodule Detection Through a Comprehensi...

引用

International Conference on Advanced Computing and Communication Systems (ICACCS)

作者： C. Premkumar r. rajeshwari r. remya M. S. Cholaathiraj A. reethika S. Bharathidasan Department of Artificial Intelligence and Data Science Bannari Amman Institute of Technology Sathyamangalam India Department of Computer Science and Engineering CMR Institute of Technology Bengaluru India Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr Sagunthala R&D institute of science and Technology Chennai India Department of Artificial Intelligence and Machine Learning Bannari Amman Institute of Technology Sathyamangalam India Department of Electronics and Communication Engineering Sri Ramakrishna Engineering College Coimbatore India Department of Electronics and Communication Engineering Erode Sengunthar Engineering College Erode India

ISBN: (数字)9798350384369

ISBN: (纸本)9798350384376

determining the precise location of Alzheimer's nodules is essential for estimating the risk of brain cancer. Conventional CAd modules, including MrI, PET, and CT, struggle with feature extraction and segmentation due to time limits and complexity. This study proposes an efficient brain nodule detection technique based on the Multi-Scene deep learning Framework (MSdLF) that makes use of the vesselness filter. A four-channel CNN model is developed using information from two image sequences to enhance radiologists' ability to recognise four-stage nodules. This adaptable model may be used in two different classes. The outcomes demonstrate how well the MSdLF performs while processing substantial volumes of image data for brain nodule recognition, improving with accuracy 98.86% and 98.45% of sensitivity by using decreasing false positives.

关键词： deep learning Training Solid modeling Accuracy Sensitivity Image recognition Magnetic resonance imaging Brain modeling Classification algorithms Alzheimer's disease

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：