检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Florio, Alexandre M. Martins, Pedro Schiffer, Maximilian Serra, Thiago Vidal, Thibaut CIRRELT SCALE-AI Chair in Data-Driven Supply Chains Department of Mathematical and Industrial Engineering Polytechnique Montréal Canada Department of Computer Science Pontifical Catholic University of Rio de Janeiro Brazil School of Management Munich Data Science Institute Technical University of Munich Germany Freeman College of Management Bucknell University United States

Decision diagrams for classification have some notable advantages over decision trees, as their internal connections can be determined at training time and their width is not bound to grow exponentially with their depth. Accordingly, decision diagrams are usually less prone to data fragmentation in internal nodes. However, the inherent complexity of training these classifiers acted as a long-standing barrier to their widespread adoption. In this context, we study the training of optimal decision diagrams (ODDs) from a mathematical programming perspective. We introduce a novel mixed-integer linear programming model for training and demonstrate its applicability for many datasets of practical importance. Further, we show how this model can be easily extended for fairness, parsimony, and stability notions. We present numerical analyses showing that our model allows training ODDs in short computational times, and that ODDs achieve better accuracy than optimal decision trees, while allowing for improved stability without significant accuracy *** Codes 68T99 Copyright © 2022, The Authors. All rights reserved.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Modified Term Frequency and Inverse Document Frequency with Optimized Deep Learning Algorithm based Fake News Detection

Modified Term Frequency and Inverse Document Frequency with ...

引用

Intelligent Systems and Computational networks (ICISCN), International Conference on

作者： Rana Veer Samara Sihman Bharattej R Prashanth V Haideer Alabdeli Sunaina Sangeet Thottan S. Ananthi Department of Computer Science Saint Leo University FL USA Department of Electrical and Electronics Engineering Nitte Meenakshi Institute of Technology Bengaluru India Department of Computers Techniques Engineering College of Technical Engineering The Islamic University of Al Diwaniyah Al Diwaniyah Iraq Department of Artificial Intelligence and Data Science Dhanalakshmi Srinivasan College of Engineering and Technology Mamallapuram India Department of Electrical and Electronics Engineering New Prince Shri Bhavani College of Engineering and Technology Chennai India

ISBN: (数字)9798331529246

ISBN: (纸本)9798331529253

The identification of real and fake news has become difficult task in the recent years due to more similar feature between them. As the issues of fake news are leading the miscommunication to the reads, various automated software has been introduced for the detection of fake news. The existing models tried to advance the identification of the fake new but failed to reach the expected outcomes due to overfitting issues and limited feature handling abilities. To overcome the existing issues the Latent Dirichlet Allocation based Term Frequency and Inverse Document Frequency with Brown-bear Optimization Algorithm-Bidirectional Long Short-Term Memory (LDA based TF-IDF with BOA-BiLSTM) is developed for the detection of fake news. The news data is collected and get cleaned by tokenization and normalization techniques. Then the LDA based TF-IDF model is used for the extraction of significant details of the news text data. Further the BOA-BiLSTM algorithm is used for the detection of fake news. The developed LDA based TF-IDF with BOA-BiLSTM algorithm has exhibited the better result having accuracy of 0.9489 and recall of 0.9012 for ISOT fake news dataset compared to the existing Knowledge Graphs for multi-domain fake news detection (KG-MFEND) model.

关键词： Phase frequency detectors Feature extraction Tokenization data mining Resource management Fake news Optimization Long short term memory Radio spectrum management Overfitting

来源：评论

学校读者我要写书评

暂无评论

AI-DRIVEN DAY-TO-DAY ROUTE CHOICE

arXiv

引用

arXiv 2024年

作者： Wang, Leizhen Duan, Peibo He, Zhengbing Lyu, Cheng Chen, Xin Zheng, Nan Yao, Li Ma, Zhenliang Department of Data Science and Artificial Intelligence Monash University Melbourne Australia Laboratory for Information & Decision Systems Massachusetts Institute of Technology Cambridge United States Chair of Transportation Systems Engineering Technical University of Munich Munich Germany School of Civil Engineering The University of Queensland Brisbane Australia Department of Civil Engineering Monash University Melbourne Australia School of Computer Science and Engineering Southeast University Nanjing China Department of Civil and Architectural Engineering KTH Royal Institute of Technology Stockholm Sweden

Understanding travelers’ route choices can help policymakers devise optimal operational and planning strategies for both normal and abnormal circumstances. However, existing choice modeling methods often rely on predefined assumptions and struggle to capture the dynamic and adaptive nature of travel behavior. Recently, Large Language Models (LLMs) have emerged as a promising alternative, demonstrating remarkable ability to replicate human-like behaviors across various fields. Despite this potential, their capacity to accurately simulate human route choice behavior in transportation contexts remains doubtful. To satisfy this curiosity, this paper investigates the potential of LLMs for route choice modeling by introducing an LLM-empowered agent, "LLMTraveler." This agent integrates an LLM as its core, equipped with a memory system that learns from past experiences and makes decisions by balancing retrieved data and personality traits. The study systematically evaluates the LLMTraveler’s ability to replicate human-like decision-making through two stages of day-to-day (DTD) congestion games: (1) analyzing its route-switching behavior in single origin-destination (OD) pair scenarios, where it demonstrates patterns that align with laboratory data but cannot be fully explained by traditional models, and (2) testing its capacity to model adaptive learning behaviors in multi-OD scenarios on the Ortuzar and Willumsen (OW) network, producing results comparable to Multinomial Logit (MNL) and Reinforcement Learning (RL) models. Additionally, the study assesses lightweight, open-source LLMs, highlighting their effectiveness in route choice simulation and their potential as cost-effective alternatives to more advanced closed-source models. These experiments demonstrate that the framework can partially replicate human-like decision-making in route choice while providing natural language explanations for its decisions. This capability offers valuable insights for transportation poli

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Cloud Computing Approach in Healthcare Technology and Application: A Review

Cloud Computing Approach in Healthcare Technology and Applic...

引用

IEEE International Conference on Emerging & Sustainable Technologies for Power & ICT in a Developing Society (NIGERCON)

作者： R. Kishore Kanna R. Anitha K. Sundaramoorthy Ayodeji Olalekan Salau Satendar Ray Jhum Swain Department of Biomedical Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai India Department of Biomedical Engineering Jerusalem College of Engineering Chennai India Department of Information Technology Jerusalem College of Engineering Chennai India Department of Electrical/ Electronics and Computer Engineering Afe Babalola University Ado-Ekiti Nigeria Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India School of Nursing Science ITM University Gwalior MP India Department of CSE - Data Science Swami Vivekananda Institute of Technology Telangana India

ISBN: (数字)9798331542559

ISBN: (纸本)9798331542566

Cloud computing is transforming the healthcare industry by providing scalable, and cost-effective solutions for storage, analysis, and access to health information and services. This comprehensive review examines the roles, benefits, challenges, and the future prospects of cloud computing in healthcare. The paper highlights the ways in which cloud computing improves data management and collaboration, enables telemedicine, lowers costs, and supports research and development. To fully realize the promise of cloud computing, hurdles such as data security, compliance and stability of the system must be overcome. The integration of new technologies such as blockchain, IoT with cloud computing show the possibility of future developments and shows that the application of cloud computing in healthcare will have a significant impact on healthcare delivery, enabling healthcare solutions that are personalized, flexible and global.

关键词： Industries Cloud computing Reviews data security Telemedicine Medical services Blockchains Stakeholders Research and development Thermal stability

来源：评论

学校读者我要写书评

暂无评论

On the parity-check matrix of generalized concatenated code

引用

science China(Information sciences) 2020年第4期63卷 233-235页

作者： Sha SHI Yang LIU Junzhi YAN Jingliang GAO Yunjiang WANG Engineering Research Center of Molecular and Neuro Imaging Ministry of Education School of Life Science and Technology Xidian University National Computer Network Emergency Response Technical Team/Coordination Center of China China Mobile Research Institute State Key Laboratory of Integrated Services Networks Xidian University

Dear editor,Single-level concatenation using a nonbinary code as outer code and a binary code as inner code is widely used in communication and digital data storage systems to achieve high reliability with reduced decoding complexity [1]. Moreover, concatenation can be multilevel, where multiple outer codes are concatenated with multiple inner codes

关键词： On the parity-check matrix of generalized concatenated code

来源：评论

学校读者我要写书评

暂无评论

Incorporating Transfer Learning in Engine Health Assessment for Accurate Remaining Useful Life Prediction

Incorporating Transfer Learning in Engine Health Assessment ...

引用

Sentiment Analysis and Deep Learning (ICSADL), International Conference on

作者： C. Karpagavalli Nelson A R. Raja Saranya E Manzoore Elahi M. Soudagar Christu Paul Ramaian Department of Artificial Intelligence and Data Science Ramco Institute of Technology Rajapalayam Tamil Nadu India Department of Mathematics Panimalar Engineering College Chennai Tamil Nadu India Department of Electronics and Communication Engineering Pandian Saraswathi Yadav Engineering College Sivagangai Tamil Nadu India Department of Computer Science and Business Systems Sri Eshwar College of Engineering Coimbatore Tamil Nadu India Department of VLSI Microelectronics Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India Department of Automobile Engineering Hindustan Institute of Technology and Science Chennai Tamil Nadu India

ISBN: (数字)9798350396157

ISBN: (纸本)9798350396164

Aircraft engines are critical, therefore any move to make them safer, more reliable, and fuel-efficient is highly encouraged. To solve the challenges of flight safety and maintenance expense during aircraft engine operation, a prognostics and health management system is deployed. This system is primarily concerned with flaw detection, health evaluation, and life prediction. Making decisions about aircraft engine operation and maintenance is strongly reliant on estimating the remaining useful life (RUL). This study provides an ensemble transfer learning model for RUL prediction using the C-MAPSS turbofan engine dataset. Pre-processing procedures such as filtering and normalization are used to improve the dataset. The proposed ensemble model for RUL prediction is then trained on the processed data. Some of the well-known transfer learning models that are compared include Xception, ResNet-50, and VGG-16. The ensemble model outperforms the other models, with the highest R2 value of 0.9901. Furthermore, the ensemble model is very effective; it can predict RUL in just 37 seconds, which suggests that it could be useful for keeping an eye on engine health and making decisions about aircraft.

关键词： Training Accuracy Atmospheric modeling Computational modeling Transfer learning Predictive models Maintenance

来源：评论

学校读者我要写书评

暂无评论

Advancing NICU Monitoring with IoT and Real-Time AI Analytics

Advancing NICU Monitoring with IoT and Real-Time AI Analytic...

引用

Visual Analytics and data Visualization (ICVADV), International Conference on

作者： N. Vini Antony Grace S Balakrishna Reddy D Sahaya Lenin N. Mohankumar L.M. Merlin Livingston M. Rajmohan Department of Electronics and Communication Engineering R.M.D. Engineering College Chennai Tamil Nadu India Department of Computer Science and Engineering (Data Science) CVR College of Engineering Hyderabad Telangana India Department of Electronics and Communication Engineering Saveetha School of Engineering Saveetha Institute of Medical And Technical Sciences (SIMATS) Saveetha University Chennai Tamil Nadu India Symbiosis Institute of Technology Symbiosis International (Deemed University) Pune India Department of Electronics and Communication Engineering DMI College of Engineering Chennai Tamil Nadu India Department of Electronics and Communication Engineering Hindustan Institute of Technology and Science Chennai Tamil Nadu India

ISBN: (数字)9798331521394

ISBN: (纸本)9798331521400

In neonatal intensive care units (NICUs), the prompt and accurate observation of sick and premature infants is of the most critical significance. Using fuzzy logic and the Internet of Things (IoT), this research demonstrates an innovative method for NICU monitoring. Our system constantly records data on critical factors, including temperature, oxygen saturation, and heart rate, via an IoT sensor network. To facilitate proactive management of newborn health, this data is analysed using Artificial Intelligence (AI) algorithms based on fuzzy logic. The results of this processing include predictive analytics and real-time insights. To provide more adaptable and precise decision-making assistance, fuzzy logic is used to deal with physiological data's inherent uncertainties and unpredictability. The proposed approach aims to have a more responsive NICU staff, better patient outcomes, and fewer critical events. This integrated strategy is useful for improving NICU operations and providing the best care for premature newborns via clinical trials and simulations.

关键词： Fuzzy logic Pediatrics Uncertainty Visual analytics Decision making Real-time systems Internet of Things Artificial intelligence Predictive analytics Monitoring

来源：评论

学校读者我要写书评

暂无评论

Supporting AI Engineering on the IoT Edge through Model-Driven TinyML

arXiv

引用

arXiv 2021年

作者： Moin, Armin Challenger, Moharram Badii, Atta Günnemann, Stephan Department of Informatics Technical University of Munich Germany Department of Computer Science Univ. of Antwerp & Flanders Make Belgium Department of Computer Science Univ. of Reading United Kingdom Dep. of Informatics Munich Data Science Institute Technical University of Munich Germany

Software engineering of network-centric Artificial Intelligence (AI) and Internet of Things (IoT) enabled Cyber-Physical Systems (CPS) and services, involves complex design and validation challenges. In this paper, we propose a novel approach, based on the model-driven software engineering paradigm, in particular the domain-specific modeling methodology. We focus on a sub-discipline of AI, namely Machine Learning (ML) and propose the delegation of data analytics and ML to the IoT edge. This way, we may increase the service quality of ML, for example, its availability and performance, regardless of the network conditions, as well as maintaining the privacy, security and sustainability. We let practitioners assign ML tasks to heterogeneous edge devices, including highly resource-constrained embedded microcontrollers with main memories in the order of Kilobytes, and energy consumption in the order of milliwatts. This is known as TinyML. Furthermore, we show how software models with different levels of abstraction, namely platform-independent and platform-specific models can be used in the software development process. Finally, we validate the proposed approach using a case study addressing the predictive maintenance of a hydraulics system with various networked sensors and actuators. © 2021, CC BY-NC-SA.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Efficient DNA Sequence Identification: A Classification Approach Integrating Gaussian RBM

Efficient DNA Sequence Identification: A Classification Appr...

引用

Electronics, Computing, Communication and Control Technology (ICECCC), International Conference on

作者： Chahat Gulati Biswajit Barman Govind Hanmantrao Balde Arul Mary Rexy V Meena Sachdeva Harshal Patil Department of Electronics and Communication Birla Institute of Technology and Science BITS Pilani Rajasthan India Department of Biotechnology Asian International University Imphal West Manipur India Department of Zoology N.T.V.S'S G.T.Patil Arts Commerce and Science College Nandurbar India Department of Commerce Saveetha College of Liberal Arts and Sciences SIMATS Chennai India Department of Computer Science JIMS Engineering Management and Technical Campus Greater Noida India Department of Data Science Balaji Institute of Technology & Management (BITM) Sri Balaji University Pune Maharashtra India

ISBN: (数字)9798350371802

ISBN: (纸本)9798350371819

Using machine learning techniques, this article examines cancer patients' DNA sequences. Cancer is certainly one of the most common and devastating diseases in the contemporary era, with a large number of new cases and deaths every year. Many people lose their lives each year to this terrible illness. Methods to combat this illness are the focus of intense investigation by scientists from a wide range of fields. Recently, machine learning has improved the analysis of cancer patients' DNA sequences. Sequencing is crucial for preprocessing, feature extraction, and model training. Among the preprocessing stages is cleaning up the sequence, which entails eliminating PCR repetitions, impurities, and vectors. Feature extraction has been carried out on each DNA sequence in order to retrieve statistical characteristics. It is of utmost importance to regulate features accurately when training a Gaussian RBM. A grade of 96.44% demonstrated a considerable improvement in accuracy, according to the results.

关键词： Training Sequential analysis Accuracy Sequences Reviews DNA Machine learning

来源：评论

学校读者我要写书评

暂无评论

Salient Object Detection in Optical Remote Sensing Images Driven by Transformer

arXiv

引用

arXiv 2023年

作者： Li, Gongyang Bai, Zhen Liu, Zhi Zhang, Xinpeng Ling, Haibin Key Laboratory of Specialty Fiber Optics and Optical Access Networks Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication Shanghai Institute for Advanced Communication and Data Science Shanghai University Shanghai200444 China School of Communication and Information Engineering Shanghai University Shanghai200444 China Wenzhou Institute of Shanghai University Wenzhou325000 China The Department of Computer Science Stony Brook University Stony BrookNY11794 United States

Existing methods for Salient Object Detection in Optical Remote Sensing Images (ORSI-SOD) mainly adopt Convolutional Neural networks (CNNs) as the backbone, such as VGG and ResNet. Since CNNs can only extract features within certain receptive fields, most ORSI-SOD methods generally follow the local-to-contextual paradigm. In this paper, we propose a novel Global Extraction Local Exploration Network (GeleNet) for ORSI-SOD following the global-to-local paradigm. Specifically, GeleNet first adopts a transformer backbone to generate four-level feature embeddings with global long-range dependencies. Then, GeleNet employs a Direction-aware Shuffle Weighted Spatial Attention Module (D-SWSAM) and its simplified version (SWSAM) to enhance local interactions, and a Knowledge Transfer Module (KTM) to further enhance cross-level contextual interactions. D-SWSAM comprehensively perceives the orientation information in the lowest-level features through directional convolutions to adapt to various orientations of salient objects in ORSIs, and effectively enhances the details of salient objects with an improved attention mechanism. SWSAM discards the direction-aware part of D-SWSAM to focus on localizing salient objects in the highest-level features. KTM models the contextual correlation knowledge of two middle-level features of different scales based on the self-attention mechanism, and transfers the knowledge to the raw features to generate more discriminative features. Finally, a saliency predictor is used to generate the saliency map based on the outputs of the above three modules. Extensive experiments on three public datasets demonstrate that the proposed GeleNet outperforms relevant state-of-the-art methods. The code and results of our method are available at https://***/MathLee/GeleNet. © 2023, CC BY-NC-ND.

关键词： Convolution

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：