检索结果-内蒙古大学图书馆

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Rama Krishna, S. Patan, Muzeeb Khan Sudarsan, J.S. Padmapriya, R. Bhagavathiperumal, S. Balaram, Allam Department of Computer Science & Engineering Hyderabad502329 India College of Engineering and Technology University of Technology and Applied Sciences Department of EEE Muscat Oman India Sathyabama Institute of Science and Technology Department of Civil Engineering Chennai India Sri Krishna College of Engineering and Technology Coimbatore India MLR Institute of Technology Department of Computer Science and Engineering Hyderabad500043 India

ISBN: (纸本)9798331530013

Due to rapid urbanization and population growth, urban waste management has become one of the major challenges faced by cities around the world. Solid waste classification and sorting are necessary for intensifying recycling, safeguarding environment and manage additional landfilling of materials that are reusable or recyclable, and are getting in landfill of solid waste in certain extent. In this study, an original ensemble model using the VGG19 and EfficientNet architectures is proposed to classify solid waste in urban area. This proposed model was applied on a dataset consists of 2,527 number of images in to six classes to increase the accuracy of classification as well as to maximize the efficiency of waste. It preprocesses the incoming data using various techniques such as image resizing, normalization and augmentation to make the dataset more diverse and robust. The ensemble mechanism performed better combining the detailed feature extraction skills of VGG19 and versatile and scalable architecture of EfficientNet. On test set, it outperformed individual models and the accuracy for the proposed model was 98.75% which closely followed, previously obtain the best result. © 2024 IEEE.

关键词： Population statistics

来源：评论

学校读者我要写书评

暂无评论

Impact Assessment and Mitigation Strategies for Plug-in Electric Vehicles on Distribution Networks: A Probabilistic Approach 7

Impact Assessment and Mitigation Strategies for Plug-in Elec...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Raj, Vijilius Helena Reddy, M. Siva Swetha Thethi, H. Pal Ramesh, G. Mohammad, Q. Bhavana, Munugapati New Horizon College of Engineering Department of Applied Sciences Bangalore India Institute of Aeronautical Engineering Telangana Hyderabad50043 India Lovely Professional University Phagwara India Griet Department of Computer Science and Engineering Bachupally Hyderabad India Hilla University College Babylon Iraq Mlr Institute of Technology Department of Computer Science and Engineering Telangana Hyderabad India

ISBN: (纸本)9798350350067

The rapid depletion of fossil fuel reserves coupled with the ever-increasing demand for electrical power has prompted the search for new energy sources. Electric vehicles (EVs) are one potential answer because of the technology that allows for more efficient transportation while simultaneously reducing fossil fuel usage and emissions of greenhouse chemicals. Depending on the power system's capability, structure, and architecture, several studies have shown that the distribution network may be negatively affected by the widespread interconnection of electric vehicles. Consequently, it is important to determine the effects of this additional load on the network so that measures can be taken to prevent threats to the system's stability, dependability, and security, especially because the Indian federal and state governments have introduced incentives to increase sales of this type of vehicle. © 2024 IEEE.

关键词： Power distribution networks

来源：评论

学校读者我要写书评

暂无评论

The Big Data Myth: Using Diffusion Models for Dataset Generation to Train Deep Detection Models

arXiv

引用

arXiv 2023年

作者： Voetman, Roy Aghaei, Maya Dijkstra, Klaas The NHL Stenden University of Applied Sciences Netherlands The NHL Stenden Professorship in Computer Vision & Data Science Netherlands

Despite the notable accomplishments of deep object detection models, a major challenge that persists is the requirement for extensive amounts of training data. The process of procuring such real-world data is a laborious undertaking, which has prompted researchers to explore new avenues of research, such as synthetic data generation techniques. This study presents a framework for the generation of synthetic datasets by fine-tuning pretrained stable diffusion models. The synthetic datasets are then manually annotated and employed for training various object detection models. These detectors are evaluated on a real-world test set of 331 images and compared against a baseline model that was trained on real-world images. The results of this study reveal that the object detection models trained on synthetic data perform similarly to the baseline model. In the context of apple detection in orchards, the average precision deviation with the baseline ranges from 0.09 to 0.12. This study illustrates the potential of synthetic data generation techniques as a viable alternative to the collection of extensive training data for the training of deep models. Copyright © 2023, The Authors. All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

WisPerMed at "Discharge Me!": Advancing Text Generation in Healthcare with Large Language Models, Dynamic Expert Selection, and Priming Techniques on MIMIC-IV 23

WisPerMed at "Discharge Me!": Advancing Text Generation in H...

引用

23rd Meeting of the ACL Special Interest Group on Biomedical Natural Language Processing, BioNLP 2024

作者： Damm, Hendrik Pakull, Tabea M.G. Eryılmaz, Bahadır Becker, Helmut Idrissi-Yaghir, Ahmad Schäfer, Henning Schultenkämper, Sergej Friedrich, Christoph M. Department of Computer Science University of Applied Sciences and Arts Dortmund Dortmund Germany University Hospital Essen Essen Germany Institute for Transfusion Medicine University Hospital Essen Essen Germany University Hospital Essen Essen Germany Institute of Diagnostic and Interventional Radiology and Neuroradiology University Hospital Essen Essen Germany Bielefeld University of Applied Sciences and Arts Bielefeld Germany

ISBN: (纸本)9798891761308

This study aims to leverage state of the art language models to automate generating the "Brief Hospital Course" and "Discharge Instructions" sections of Discharge Summaries from the MIMIC-IV dataset, reducing clinicians’ administrative workload. We investigate how automation can improve documentation accuracy, alleviate clinician burnout, and enhance operational efficacy in healthcare facilities. This research was conducted within our participation in the Shared Task Discharge Me! at BioNLP @ ACL 2024. Various strategies were employed, including Few-Shot learning, instruction tuning, and Dynamic Expert Selection (DES), to develop models capable of generating the required text sections. Utilizing an additional clinical domain-specific dataset demonstrated substantial potential to enhance clinical language processing. The DES method, which optimizes the selection of text outputs from multiple predictions, proved to be especially effective. It achieved the highest overall score of 0.332 in the competition, surpassing single-model outputs. This finding suggests that advanced deep learning methods in combination with DES can effectively automate parts of electronic health record documentation. These advancements could enhance patient care by freeing clinician time for patient interactions. The integration of text selection strategies represents a promising avenue for further research.. ©2024 Association for Computational Linguistics.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

ROStopbox: A Human-Centered Vehicle Environment Data Acquisition System

ROStopbox: A Human-Centered Vehicle Environment Data Acquisi...

引用

Automated Vehicle Validation Conference (IAVVC), IEEE International

作者： Daniel Schneider Jonas Nesensohn Bernhard Schick Daniel Watzenig Institute for Advanced Driver Assistance Systems and Connected Mobility Kempten University of Applied Sciences Institute of Computer Graphics and Vision Graz University of Technology AVL Deutschland GmbH Advanced Solution Lab Karlsruhe

ISBN: (数字)9798350354072

ISBN: (纸本)9798350354089

As the development towards fully automated driving continues, passenger trust in automation and human well-being when using advanced driver assistance systems will become increasingly important. To support the existing data-driven development process, systems for acquiring perceptual data such as from camera and LiDAR along with physiological and subjective information will be required in the future. The simultaneous recording of physiological signals alongside data from traditional perception sensors can therefore help to identify scenarios in which passengers are stressed, have an increased workload, or feel unsafe. By recording questionnaires in parallel, it is possible to also correlate the physiological signals with passengers’ subjective perception. The combination of these signal sources makes it possible to identify causes of drivers’ increased workload in the environmental data, describe development targets, and safeguard rules for future assistance systems and automated driving functions, keeping humans in the loop. Here, we present an approach for the simultaneous acquisition of sensor information from multiple domains such as physiological measurement data, environmental sensors, vehicle-internal communication, and subjective questionnaires, paying attention to an unobtrusive measurement setup. We demonstrate the benefits of our approach by identifying a relevant scenario in real traffic conditions in which we observe the impact on the driver’s physiological parameters.

关键词： Laser radar Operating systems Data acquisition Human factors Cameras Physiology Human in the loop Sensors Recording Testing

来源：评论

学校读者我要写书评

暂无评论

Quantum Network Coding and Distribution of Maximally Entangled States in Measurement-Based Quantum Computing

Quantum Network Coding and Distribution of Maximally Entangl...

引用

2023 National Conference on Communications, NCC 2023

作者： Pandey, Cheeranjiv Gupta, Sanidhya Das, Rimon Ranjit Raina, Ankur Indian Institute of Technology Department of Physics Ropar India Indian Institute of Science Education and Research Department of Electrical Engineering and Computer Science Bhopal India Amity University Amity Institute of Applied Sciences Department of Physics India

ISBN: (纸本)9781665456258

Classical network coding uses encoding of information over networks to achieve secure and high throughput communication with low latency. Its quantum analog, namely Quantum Network Coding (QNC) is a promising protocol to achieve quantum communication over quantum networks. In this paper, we propose a method for establishing QNC in Measurement-Based Quantum Computing (MBQC), which is a universal quantum computational model. We demonstrate that the problem of multiple unicast or multiple multicast of distinct computational basis states over a quantum network can be solved by simulating existing classical networks, with the CNOT implementation in MBQC as a basis for transmitting and encoding of states. We also show how it can be further extended to simultaneously distribute the Bell pairs and Greenberger-Horne-Zeilinger (GHZ) states required for quantum communication between distant transmitter and corresponding receiver nodes of a network. © 2023 IEEE.

关键词： Network coding

来源：评论

学校读者我要写书评

暂无评论

Completely entangled subspaces of entanglement depth k

引用

Physical Review A 2024年第1期110卷 012403-012403页

作者： Maciej Demianowicz Kajetan Vogtt Remigiusz Augusiak Institute of Physics and Applied Computer Science Faculty of Applied Physics and Mathematics Polish Academy of Sciences Aleja Lotników 32/46 02-668 Warsaw Poland Faculty of Physics

We introduce a class of entangled subspaces: completely entangled subspaces of entanglement depth k (k−CESs). These are subspaces of multipartite Hilbert spaces containing only pure states with an entanglement depth of at least k. We present an efficient construction of k−CESs of any achievable dimensionality in any multipartite scenario. Further, we discuss the relation between these subspaces and unextendible product bases (UPBs). In particular, we establish that there is a nontrivial bound on the cardinality of a UPB whose orthocomplement is a k−CES. Further, we discuss the existence of such UPBs for qubit systems.

关键词： Entanglement detection Quantum entanglement Quantum error correction Quantum information theory

来源：评论

学校读者我要写书评

暂无评论

Wizard of Oz Prototyping for Interactive Spatial Augmented Reality in HCI Education: Experiences with Rapid Prototyping for Interactive Spatial Augmented Reality

Wizard of Oz Prototyping for Interactive Spatial Augmented R...

引用

Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems, CHI EA 2023

作者： Mast, Danića Roidl, Alex Jylha, Antti Faculty of It & Design Research Group Healthy Lifestyle in A Supporting Environment Faculty of Health Nutrition & Sports The Hague University of Applied Sciences Netherlands Leiden Institute of Advanced Computer Science Leiden University Netherlands Communication Design Mainz University of Applied Sciences Germany Faculty of It & Design The Hague University of Applied Sciences Netherlands Service Business Development and Design Haaga-Helia University of Applied Sciences Finland

ISBN: (纸本)9781450394222

In this paper we present our findings that emerged from Wizard of Oz (WOz) prototyping workshops of an undergrad course on UX design between 2017 - 2022. The purpose of these workshops is both to familiarize the students with WOz as a rapid low-complexity prototyping method and to facilitate them in designing for interactive systems beyond typical graphical user interfaces. In these workshops, students develop and test Wizard of Oz prototypes for interactive spatial augmented reality (SAR). Over the past six years, in total 93 prototypes have been created on the course. We analyzed the prototypes that emerged from the workshops based on input, purpose, play characteristics and projection surfaces. Based on the analysis and our experiences during the workshops, we conclude that the workshops stimulate creativity, enable students to rapidly create interactive SAR interfaces without being limited by their technical skills and time limitations and provide them with a tool that they apply beyond the scope of the prototyping course. We discuss advantages and limitations of the use of WOz prototyping for interactive Spatial Augmented Reality. © 2023 Owner/Author.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Supervised machine learning-based salp swarm algorithm for fault diagnosis of photovoltaic systems

引用

Journal of Engineering and applied Science 2024年第1期71卷 12页

作者： Hichri, Amal Hajji, Mansour Mansouri, Majdi Nounou, Hazem Bouzrara, Kais Research Unit Advanced Materials and Nanotechnologies Higher Institute of Applied Sciences and Technology of Kasserine Kairouan University Kairouan Tunisia Electrical and Computer Engineering Program Texas A&M University at Qatar Doha Qatar Laboratory of Automatic Signal and Image Processing National School of Engineers of Monastir University of Monastir Monastir5019 Tunisia

The diagnosis of faults in grid-connected photovoltaic (GCPV) systems is a challenging task due to their complex nature and the high similarity between faults. To address this issue, we propose a wrapper approach called the salp swarm algorithm (SSA) for feature selection. The main objective of SSA is to extract only the most important features from the raw data and eliminate unnecessary ones to improve the classification accuracy of supervised machine learning (SML) classifiers. Subsequently, the selected features are used to train supervised machine learning (SML) techniques in distinguishing between various operating modes. To evaluate the efficiency of the technique, we used healthy and faulty data from GCPV systems that have been injected with frequent faults, 20 different types of faults were introduced, including line-to-line, line-to-ground, connectivity faults, and those affecting the operation of bay-pass diodes. These faults present diverse conditions, such as simple and multiple faults in the PV arrays and mixed faults in both arrays. The performances of the developed SSA-SML are compared with those using principal component analysis (PCA) and kernel PCA (KPCA) based SML techniques through different criteria (i.e., accuracy, recall, precision, F1 score, and computation time). The experimental findings demonstrated that the proposed diagnosis paradigm outperformed the other techniques and achieved a high diagnostic accuracy (an average accuracy greater than 99%) while significantly reducing computation time. © 2023, The Author(s).

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Improving Food Safety by IoT-based Climate Monitoring and Control Systems for Food Processing Plants

引用

Remote Sensing in Earth Systems sciences 2025年第2期8卷 387-399页

作者： Kolikipogu, Ramakrishna Shivaputra Muniyandy, Elangovan Maroor, Jnaneshwar Pai Lakshmi, Gundala Venkata Rama Konduri, Bhagavan Naveenkumar, R. Department of Information Technology Chaitanya Bharathi Institute of Technology Hyderabad India Department of Electronics and Communication Engineering Dr. Ambedkar Institute of Technology Bengaluru India Department of Biosciences Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Applied Science Research Center Applied Science Private University Amman Jordan Department of Business Administration Nitte Institute of Professional Education Nitte (Deemed to Be University) Karnataka Mangaluru India Department of Computer Science and Engineering CVR College of Engineering Hyderabad India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh India Department of Computer Science and Engineering Chandigarh Colleges of Engineering Chandigarh Group of Colleges Jhanjeri Punjab Mohali 140307 India

Web different IoT apps offer lot more options for every player in the meat supply chain to monitor, control, and optimize their manufacturing method. Beginning within late 2017, industrial IoF2020 program will concentrate toward massive deployments of IoT via three use cases in the meat supply chain: pig farm management, poultry chain tracking, and for livestock visibility with openness. This initiative will include eleven collaborators spanning 5 nations. Installing and integrating IoT sensors for environmental and livestock management would alleviate producers’ difficulty getting knowledge that data needed regarding continuously tracking how well they are doing. Alert detection is additionally being created, integrating multiple sources of data in order to give farmers helpful input along with communicating news with other partners. By carrying out this, preventative or remedial measures can be done for infections, swine taint, bird mortality, feed waste, the natural world, et cetera. Additionally, EPCIS-based traceability from farm to fork will be allowed to ensure customers may get precise data about the source and caliber of their livestock. Each of these three use scenarios’ existing stage in work along with future plans are expected to be discussed. IoF2020 seeks to support the digital revolution in smart farming by tackling various educational and commercial problems while also promoting its use throughout Europe. It maintains mechanical necessary degree and security against physical along with toxic contaminants during industrial butchering of chicken, a lot measures have been taken. Buyers’ worries about food safety and health are the result of eating chicken increasingly. Our authorities have begun many kinds of initiatives aimed at improving safeguards for food. Our goal is to create an apparatus that alerts the factory farms affecting potential threats for product hygiene of food. With such setup, the detector can be mounted on top of the poultry slaugh

关键词： Food safety Internet of Things Meat processing Monitoring Supply chain

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：