检索结果-内蒙古大学图书馆

IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Imran Kabir Shubham Shaurya Vijayalaxmi Maigur Nikhil Thakurdesai Mahesh Latnekar Mayank Raunak David Crandall Md Alimoor Reza College of Information Sciences and Technology Pennsylvania State University PA USA Luddy School of Informatics Computing and Engineering Indiana University Bloomington IN USA Department of Mathematics and Computer Science Drake University Des Moines IA USA

This paper tackles image segmentation problems for underwater environments. First, we introduce a novel under-water animal-centric dataset with dense pixel-level annotations containing diverse fine-grained animal categories to mitigate the lack of diverse categories in the existing benchmarks. Then, we solve two image segmentation tasks using underwater images in this dataset: (i) few-shot segmentation, and (ii) semantic segmentation. For the segmentation task in a few-shot learning framework, we propose a novel attention-guided deep neural network architecture by infusing attention modules in various stages of our proposed network. We systematically explore how the learned attention maps can improve few-shot segmentation performance for underwater imagery. Finally, we assess the semantic segmentation problem on our proposed dataset by benchmarking it with two state-of-the-art semantic segmentation methods. We believe our new problem setup, i.e., few-shot segmentation for underwater environments, will be a valuable addition to the existing underwater semantic segmentation task. We believe our novel dataset will pave the way for developing better algorithms and exploring new research directions for marine robotics and underwater image understanding. We publicly release our dataset and the code to advance image understanding research in underwater environments: https://***/Imran220S/uwsnet.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data-driven machine learning approaches for simultaneous prediction of peak particle velocity and frequency induced by rock blasting in mining

Rock Mechanics Bulletin

引用

Rock Mechanics Bulletin 2025年第1期4卷 29-52页

作者： Yewuhalashet Fissha Prashanth Ragam Hajime Ikeda N.Kushal Kumar Tsuyoshi Adachi P.S.Paul Youhei Kawamura Department of Geosciences Geotechnologyand Materials Engineering for ResourcesGraduate School of International Resource SciencesAkita UniversityAkita010-8502Japan Department of Mining Engineering Aksum UniversityAksum7080TigrayEthiopia School of Computer Science and Engineering VIT-AP UniversityAmaravatiAndhra PradeshIndia Department of Systems Controland Information EngineeringNational Institute of TechnologyAsahikawa College2-2-1-6 Syunkodai Asahikawa city Hokkaido071-8142Japan Department of Mining Engineering Indian Institute of Technology(Indian School of Mines)Dhanbad826004India Faculty of Engineering Hokkaido UniversityKita 8Nishi 5Kita-KuSapporo0608628Japan

The vibrations generated by rock blasting are a serious and hazardous outcome of these activities,causing harmful effects on the surrounding environment as well as the nearby *** the local ecology and human communities suffer from the consequences of these *** the severity of blasting vibrations necessitates a thorough evaluation of Peak Particle Velocity(PPV)and frequency,which are essential parameters for measuring vibration *** prediction of vibration occurrence is critically ***,this study employs five machine learning models for predicting the PPV and frequency resulting from quarry *** work compares five machine learning models(XGBoost,Catboost,Bagging,Gradient Boosting,and Random Forest Regression)to choose the most efficient performance *** performance evaluation of each five machine learning models demonstrates each model achieved a performance of more than 0.90 during the testing phase,there was a strong correlation observed between the actual and the predicted *** analysis of performance metrics shows Catboost regression model demonstrate better performance prediction comparing with the other models with R^(2)=0.983,MSE=0.000078,RMSE=0.008,NRMSE=0.019,MAD=0.004,MAPE=35.197 in the PPV prediction,and R^(2)=0.975,MSE=0.000243,RMSE=0.015,NRMSE=0.031,MAD=0.008,MAPE=37.281 for the frequency *** study will help mining engineers and blasting experts to select the best machine learning model and its hyperparameters in estimating ground vibration,and *** the context of the mining and civil industry,the application of this study offers significant potential for enhancing safety protocols and optimizing operational *** employing machine learning models,this research aims to accurately predict and assess ground vibrations with frequency resulting from rock blasting.

关键词： PPV Frequency Machine learning Blasting Regression Catboost XGboost

来源：评论

学校读者我要写书评

暂无评论

MediVault DApp: A Electronic Health Record Application Using Blockchain Technology

MediVault DApp: A Electronic Health Record Application Using...

引用

Machine Learning and Autonomous systems (ICMLAS), International Conference on

作者： Lingeswara Reddy Peddu Aditya Mishra Amirineni Rama L Padmaja Rekha G Palanikumar S R. K. Pongiannan Dept. of Computing Technologies SRM Institute of Science and Technology Kattankulathur Tamil Nadu India Department of ECE Geethanjali College of Engg. And Tech. Hyderabad India Dept. of Computer science and business systems Vel Tech Multi Tech Dr Rangarajan Dr Sakunthala Engg. College Avadi Chennai Tamilnadu India

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

The healthcare industry stands to benefit greatly from blockchain technology due to its robust security, privacy protection, confidentiality, and decentralized nature. This study outlines how blockchain can revolutionize current medical data systems and proposes a framework for its implementation. The primary objective of this framework is to ensure secure storage of electronic records by establishing comprehensive access protocols for users. When patients seek medical care, hospitals generate and store patient records in a decentralized application (DApp), which is a blockchain- based platform for maintaining electronic medical records. Medical professionals can modify patient records, while patients can retrieve their medical information from the DApp using public keys. Electronic Health Records (EHRs) allow healthcare providers to monitor information necessary for compliance with insurance companies and government regulations. EHRs serve as a centralized data repository for storing doctors' orders related to laboratory tests, x-rays, and other diagnostic procedures. The proposed system aims to optimize individual medical information management, minimize redundant testing, reduce treatment delays, and equip patients with adequate information to make informed decisions.

关键词： Privacy Scalability Medical services Decentralized applications Regulation Blockchains InterPlanetary File System Electronic medical records Usability Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Knowledge Representation of Complex Tasks Based on Dynamic Motion Primitives 7th

Hierarchical Knowledge Representation of Complex Tasks Based...

引用

7th International Conference on Cognitive systems and Information Processing, ICCSIP 2022

作者： Miao, Shengyi Zhong, Daming Miao, Runqing Sun, Fuchun Wen, Zhenkun Huang, Haiming Zhang, Xiaodong Wang, Na College of Electronics and Information Engineering Shenzhen University Shenzhen518060 China College of Modern Post Beijing University of Posts and Telecommunications Beijing100083 China Department of Computer Science and Technology Tsinghua University Beijing100083 China College of Computer Science and Software Shenzhen University Shenzhen518060 China Beijing Key Laboratory of Intelligent Space Robotic Systems Technology and Application Beijing100083 China

ISBN: (纸本)9789819906161

Current service robots without learning ability are not qualified for many complex tasks. Therefore, it is very significant to decompose the complex task into repeatable execution unit. In this paper, we propose a complex task representation method based on dynamic motion primitives, and use hierarchical knowledge graph to represent the analytic results of complex tasks. To realize the execution of complex robot manipulation tasks, we decompose the semantic tasks into the minimum motion units that can be executed by the robot and combine the multi-modal information: posture, force and robot joint parameters, obtained by the sensors. We use the knowledge graph to record the end-effector required by the robot to perform different tasks and make appropriate selection of end-effector according to different needs. Finally, Taking the long sequence complex task of service scene as an example, we use UR5 robot to verify the effectiveness and feasibility of this design. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： End effectors

来源：评论

学校读者我要写书评

暂无评论

Segmentation and Multi-facet Classification of Individual Logs in Wooden Piles 18th

Segmentation and Multi-facet Classification of Individual Lo...

引用

18th International Conference on computer Aided systems Theory, EUROCAST 2022

作者： Praschl, Christoph Auersperg-Castell, Philipp Forster-Heinlein, Brigitte Zwettler, Gerald Adam Research Group Advanced Information Systems and Technology Research and Development Department University of Applied Sciences Upper Austria Hagenberg Austria Department of Software Engineering School of Informatics Communications and Media University of Applied Sciences Upper Austria Hagenberg Austria Bluedynamics Auersperg-Castell KG Kritzing 31 Freinberg Austria Faculty of Computer Science and Mathematics University of Passau Passau Germany

ISBN: (纸本)9783031253119

The inspection of products and assessment of quality is connected with high costs and time effort in many industrial domains. This also applies to the forestry industry. Utilizing state-of-the-art deep learning models allows automizing the analysis of wooden piles in a vision-based manner. In this work, a parallel two-step approach is presented for the segmentation and multi-facet classification of individual logs, according to the wood type and quality. The present approach is based on a preliminary log localization step and like this allows determining the quality, volume and also the value of individual logs, respectively the whole wooden pile. Using a YOLOv4 model for wood species classification for douglas firs, pines and larches results in an accuracy of 74.53%, while a quality classification model for spruce logs reaches 86.58%. In addition to that, the trained U-NET segmentation model reaches an accuracy of 93%. In the future, the underlying data set and models will be further improved and integrated to a mobile application for the on site analysis of wooden piles by foresters. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Solar Electrification Station for Sustainable Energy Access

Design and Implementation of Solar Electrification Station f...

引用

International Conference on Communication, Computing and Internet of Things (IC3IoT)

作者： Soma Prathibha S Siva Chandran M Kirthiga K Dhanya S Abhijay Gopal M Manish Department of Information Technology Sri Sairam Engineering College Chennai India Department of Mechanical Engineering Sri Sairam Engineering College Chennai India Department of Electronics and Communication Sri Sairam Engineering College Chennai India Electrical and Electronics Engineering Sri Sairam Engineering College Chennai India Department of Electrical Engineering Sri Sairam Engineering College Chennai India Department of Computer Science and Business Systems Sri Sairam Engineering College Chennai India

ISBN: (数字)9798350352689

ISBN: (纸本)9798350352696

A power outage can have serious consequences in today’s modern society, since technology has become an essential component of our everyday existence. Also continuous power breakdowns have far-reaching consequences in our increasingly connected world. From communication disruptions to healthcare risks, transportation challenges, economic setbacks, and psychological impact, the hardships faced by people during power outages are significant. People suffer a great deal as a result of frequent power outages, which can interfere with vital services like emergency response and healthcare as well as disrupt communication and transportation networks. To address the hardships faced by remote and underprivileged villages due to continuous power breakdowns, a solar electrification station is developed as a sustainable energy solution. The project focuses on providing a reliable and uninterrupted power source, particularly during the rainy season when floods disrupt normal life. The installation of a 3kW monocrystalline solar panel system, operated as a standalone solar system, powers the village school, ensuring uninterrupted education for students.

关键词： Electric breakdown Transportation Psychology Medical services Power system reliability Telecommunication computing Solar system

来源：评论

学校读者我要写书评

暂无评论

Multiplexed Implantable 'Barcode' Platform for Continuous Oxygen and Glucose Monitoring

引用

IEEE Sensors Journal 2024年

作者： Chen, Zheyuan Falohun, Tokunbo Kameoka, Jun Mcshane, Michael J. Texas A&M University Department of Biomedical Engineering College StationTX77843 United States Texas A&M University Department of Electrical and Computer Engineering College StationTX77843 United States Waseda University Graduate School of Information Production and Systems Fukuoka808-0135 Japan Texas A&M University Department of Biomedical Engineering Department of Materials Science and Engineering College StationTX77843 United States

Multianalyte biosensors have been of interest in various applications, especially in healthcare areas that target a broad range of biomarkers related to various pathological diseases. However, successful examples of such sensors generally utilize electrochemical transducers, a fact which limits their use as implants due to the presence of interferents in vivo, the difficulty of transdermal signal transduction, and the difficulty of miniaturizing the electronics into an integrated biocompatible form factor suitable for implantation. In this study, we demonstrate an attractive alternative for multiplexed sensing platform based on oxidoreductase enzymes coupled with optically distinct oxygen-sensitive metalloporphyrin phosphors which are immobilized within nanofilm-coated alginate microparticles;these are embedded in discrete compartments of a single miniature biocompatible hydrogel to achieve a 'barcode' sensor device. Continuous multiplex oxygen and glucose monitoring were demonstrated through the measurement of phosphorescence lifetime changes of the metalloporphyrin phosphors when exposed to different environmental conditions. The phosphorescence lifetime exhibited a negative correlation with increases in oxygen concentration for all compartments. In contrast, the oxygen-responsive assays maintained a constant phosphorescence lifetime and the glucose-responsive assays showed increased phosphorescence lifetime when the glucose concentration increased from 0 to 400 mg/dL. This observation confirmed the desired behavior without any apparent crosstalk between the adjacent oxygen- and glucose-responsive compartments. Furthermore, the sensors demonstrated high stability during repeated glucose challenges over 10 cycles. These findings suggest that the hydrogel barcode optical sensing platform has potential for use in various situations requiring multiplexed chemical analysis such as in continuous medical monitoring. © 2001-2012 IEEE.

关键词： Phosphorescence

来源：评论

学校读者我要写书评

暂无评论

Blockchain Technology for Secure Shared Medical Data

Blockchain Technology for Secure Shared Medical Data

引用

Information Technology (ACIT)

作者： M'hamed Mancer Khelili Mohamed Akram Ezedin Barka Kazar Okba Slatnia Sihem Saad Harous Belkacem Athamena Zina Houhamdi Department of Computer Science Smart computer science laboratory Biskra Algeria University of Mohamed Khider Biskra Algeria Numidia Institute of Technology Algeria Algeria Department of Information Systems and Security UAE University Al Ain UAE Department of Information Systems and Security College of Information Technology United Arab Emirate University United Arab Emirate Department of Computer Science College of Computing and Informatics AL Ain United Arab Emirates University of Sharjah Al Ain United Arab Emirate College of Business Al Ain University Al Ain UAE University of Al Ain Al Ain UAE

ISBN: (数字)9798350320244

ISBN: (纸本)9798350320251

A blockchain is a shared database allowing trust to be created between individuals without using intermediaries. The architecture here is decentralized, the data is distributed among the users, and therefore the information can never be erased. Today, many fields are interested in the development of products and technical solutions based on Blockchain technology. In this paper, we investigate blockchain in developing a Secure Shared Medical Record system (SSMR) for health data management. The proposed system aims to collect, store and share electronic medical records securely. It also makes it possible to provide doctors, for example, with medical information from other healthcare professionals, by defining a medical profile for each patient.

关键词： Drugs Medical services X-rays Data models Blockchains Security Electronic medical records

来源：评论

学校读者我要写书评

暂无评论

OpenVNA: A Framework for Analyzing the Behavior of Multimodal Language Understanding System under Noisy Scenarios

arXiv

引用

arXiv 2024年

作者： Yuan, Ziqi Zhang, Baozheng Xu, Hua Liang, Zhiyun Gao, Kai State Key Laboratory of Intelligent Technology and Systems Department of Computer Science and Technology Tsinghua University China China School of Information Science and Engineering Hebei University of Science and Technology China College of Information and Electrical Engineering China Agricultural University China Technology Development Co. Ltd. China

We present OpenVNA, an open-source framework designed for analyzing the behavior of multimodal language understanding systems under noisy conditions. OpenVNA serves as an intuitive toolkit tailored for researchers, facilitating convenience batch-level robustness evaluation and on-the-fly instance-level demonstration. It primarily features a benchmark Python library for assessing global model robustness, offering high flexibility and extensibility, thereby enabling customization with user-defined noise types and models. Additionally, a GUI-based interface has been developed to intuitively analyze local model behavior. In this paper, we delineate the design principles and utilization of the created library and GUI-based web platform. Currently, OpenVNA is publicly accessible at https://***/thuiar/OpenVNA, with a demonstration video available at https://***/0Z9cW7RGct4. © 2024, CC BY-NC-SA.

关键词： Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

Enhancing Marine Litter Management in the Gulf of Aqaba Through AI 9th

Enhancing Marine Litter Management in the Gulf of Aqaba Thro...

引用

9th International Conference on Information, Communication and Computing Technology, ICICCT 2024

作者： Wahsha, Mohammad Wahsheh, Heider Al-Najjar, Tariq Marine Science Station The University of Jordan Aqaba Branch Aqaba Jordan Department of Information Systems College of Computer Science and Information Technology King Faisal University Al-Ahsa Al Hofuf31982 Saudi Arabia Faculty of Basic and Marine Sciences The University of Jordan Aqaba Branch Aqaba Jordan

ISBN: (纸本)9783031724824

This paper investigates the critical issue of marine litter in the Gulf of Aqaba, a key marine ecosystem in the Red Sea known for its rich biodiversity and economic significance to tourism and fishing industries. It emphasizes the vulnerability of this semi-enclosed body of water to various types of marine litter, including plastic waste and discarded fishing gear, posing significant threats to marine life through ingestion and entanglement. To address the limitations of traditional monitoring methods, the study proposes the innovative use of Artificial Intelligence (AI) technologies, such as machine learning and computer vision, to enhance the detection, quantification, and categorization of marine debris. The paper aims to develop an advanced prototype for underwater image analysis using AI, designed to significantly contribute to environmental preservation efforts by providing efficient, real-time assessments of marine litter in the Gulf of Aqaba, demonstrating the potential of AI to transform marine conservation strategies. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

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：