检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Gakhar, Ishaan Guha, Aryesh Gupta, Aryaman Agarwal, Amit Toshniwal, Durga Verma, Ujjwal Department of Information and Communication Technology Manipal Institute of Technology Manipal Academy of Higher Education India Department of Electrical and Electronics Engineering Manipal Institute of Technology Manipal Academy of Higher Education India Department of Computer Science Engineering Manipal Institute of Technology Manipal Academy of Higher Education India Enterprise Analytics & Data Science Artificial Intelligence Center of Excellence Wells Fargo International Solutions Private Limited Center For Transportation Systems Indian Institute of Technology Roorkee India Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education India

The scarcity of comprehensive datasets in the traffic light detection and recognition domain and the poor performance of state-of-the-art models under hostile weather conditions present significant challenges. To address these issues, this paper proposes a novel approach by merging two widely used datasets, LISA and S2TLD. The merged dataset is further processed to tackle class imbalance, a common problem in this domain. This merged dataset becomes our source domain. Synthetic rain and fog are added to the dataset to create our target domain. We employ Fourier Domain Adaptation (FDA) to create a final dataset with a minimized domain gap between the two datasets, helping the model trained on this final dataset adapt to rainy and foggy weather conditions. Additionally, we explore Semi-Supervised Learning (SSL) techniques to leverage the available data more effectively. Experimental results demonstrate that models trained on FDA-augmented images outperform those trained without FDA across confidence-dependent and independent metrics, like mAP50, mAP50-95, Precision, and Recall. The best-performing model, YOLOv8, achieved a Precision increase of 5.1860%, Recall increase of 14.8009%, mAP50 increase of 9.5074%, and mAP50- 95 increase of 19.5035%. On average, percentage increases of 7.6892% in Precision, 19.9069% in Recall, 15.8506% in mAP50, and 23.8099% in mAP50-95 were observed across all models, highlighting the effectiveness of FDA in mitigating the impact of adverse weather conditions on model performance. These improvements pave the way for real-world applications where reliable performance in challenging environmental conditions is critical. Impact Statement-This research addresses a critical challenge in autonomous driving systems-poor performance in adverse weather conditions-by introducing a novel method using Fourier Domain Adaptation (FDA). The FDA-enhanced models significantly improve the detection of traffic lights in rain and fog, which has broad implicatio

关键词： Rain

来源：评论

学校读者我要写书评

暂无评论

Examining the Challenges in Implementing AIDriven Systems for Automated data science

Examining the Challenges in Implementing AIDriven Systems fo...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： T Vanaja Priya M. Shelke Sandeep Gautam Rakesh Kumar Yadav Santosh Chowhan G. Ravivarman Department of Information Technology Prince Shri Venkateshwara Padmavathy Engineering College Chennai Department of Information Technology Vishwakarma Institute of Technology Pune INDIA Department of Computer Science & Engineering Vivekananda Global University Jaipur India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Department of Data Analytics and Mathematical Sciences Jain (Deemed to be University) Bangalore Karnataka India Department of Electrical and Electronics Engineering Karpagam Academy of Higher Education Coimbatore

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

- this paper provides an overview brand new the contemporary in employing synthetic Intelligence (AI) strategies to automate statistics technological know-how procedures. It highlights state-of-the-art the demanding situations related to the mixing of those structures with current infrastructure and implementations, as well as ability solutions. It also outlines the significance trendy thinking about a broad range latest AI-driven system, which include supervised and unsupervised studying, Deep Neural network (DNN) architectures, version-based reinforcement present day, and lively state-of-the-art. The paper in addition discusses how every of these systems can be used to automate sure components modern the records technology system, and the way their use can bring about stronger accuracy and effectiveness brand new records science operations. In the end, it evaluates latest the important thing concerns which want to be taken into account while defining and implementing an AIpushed device for computerized information technological know-how.

关键词： Privacy Leadership Accuracy Artificial neural networks computer architecture data science Safety Information technology Artificial intelligence Investment

来源：评论

学校读者我要写书评

暂无评论

Accurate Loss Prediction of Realistic Hollow-core Anti-resonant Fibers Using Machine Learning

arXiv

引用

arXiv 2024年

作者： Jewani, Yordanos Petry, Michael Sanchez-Arias, Rei Amezcua-Correa, Rodrigo Habib, Md Selim The Department of Data Science and Business Analytics Florida Polytechnic University 4700 Research Way LakelandFL33805 United States The Faculty of Electrical Engineering and Information Technology University of Applied Sciences KarlsruheBW-76133 Germany The CREOL University of Central Florida OrlandoFL32816 United States The Department of Electrical Engineering and Computer Science Florida Institute of Technology MelbourneFL32901 United States

Hollow-core anti-resonant fibers (HC-ARFs) have proven to be an indispensable platform for various emerging applications due to their unique and extraordinary optical properties. However, accurately estimating the propagation loss of nested HC-ARFs remains a challenging task due to their complex structure and the lack of precise analytical and theoretical models. To address this challenge, we propose a supervised machine-learning framework that presents an effective solution to accurately predict the propagation loss of a 5-tube nested HC-ARF. Multiple supervised learning models, including random forest, logistic regression, quadratic discriminant analysis, tree-based methods, extreme gradient boosting, and K-nearest neighbors are implemented and compared using a simulated dataset. Among these methods, the random forest algorithm is identified as the most effective, delivering accurate predictions. Notably, this study considers the impact of random structural perturbations on fiber geometry, encompassing random variations in tube wall thicknesses and tube gap separations. In particular, these perturbations involve randomly varying outer and nested tube wall thicknesses, tube angle offsets, and randomly distributed non-circular, anisotropic shapes within the cladding structure. It is worth noting that these specific perturbations have not been previously investigated. Each tube exhibits its unique set of random values, leading to longer simulation times for combinations of these values compared to regular random variables in HC-ARFs with similar tube characteristics. The comprehensive consideration of these factors allows for precise predictions, significantly contributing to the advancement of HC-ARFs for many emerging applications. © 2024, CC BY.

关键词： Fibers

来源：评论

学校读者我要写书评

暂无评论

Metadata Concepts for Advancing the Use of Digital Health Technologies in Clinical Research

引用

Digital Biomarkers 2019年第3期3卷 116-132页

作者： Badawy, Reham Hameed, Farhan Bataille, Lauren Little, Max A. Claes, Kasper Saria, Suchi Cedarbaum, Jesse M. Stephenson, Diane Neville, Jon Maetzler, Walter Espay, Alberto J. Bloem, Bastiaan R. Simuni, Tanya Karlin, Daniel R. School of Computer Science University of Birmingham Birmingham United Kingdom Digital Medicine and Pfizer Innovation Research Lab Early Clinical Development Pfizer Inc. CambridgeMA United States College of Computer and Information Science Northeastern University BostonMA United States Analytics Informatics and Business Intelligence Chief Digital Office Pfizer Inc. New YorkNY United States Michael J. Fox Foundation for Parkinson's Research New YorkNY United States Media Lab Massachusetts Institute of Technology CambridgeMA United States UCB Biopharma Brussels Belgium Machine Learning and Healthcare Laboratory Departments of Computer Science Statistics and Health Policy Malone Center for Engineering in Healthcare Armstrong Institute for Patient Safety and Quality Johns Hopkins University BaltimoreMD United States Biogen CambridgeMA United States Critical Path Institute TucsonAZ United States Clinical Data Interchange Standards Consortium AustinTX United States Department of Neurology Christian Albrecht University Kiel Germany James J. and Joan A. Gardner Family Center for Parkinson's Disease and Movement Disorders University of Cincinnati CincinnatiOH United States Department of Neurology Donders Institute for Brain Cognition and Behavior Radboud University Medical Center Nijmegen Netherlands Department of Neurology Gardner Center for Parkinson's Disease and Movement Disorders UC Gardner Neuroscience Institute University of Cincinnati CincinnatiOH United States Tufts University School of Medicine BostonMA United States HealthMode New YorkNY United States School of Engineering and Applied Science Aston University BirminghamB47ET United Kingdom

Digital health technologies (smartphones, smartwatches, and other body-worn sensors) can act as novel tools to aid in the diagnosis and remote objective monitoring of an individual's disease symptoms, both in clinical care and in research. Nonetheless, such digital health technologies have yet to widely demonstrate value in clinical research due to insufficient data interpretability and lack of regulatory acceptance. Metadata, i.e., data that accompany and describe the primary data, can be utilized to better understand the context of the sensor data and can assist in data management, data sharing, and subsequent data analysis. The need for data and metadata standards for digital health technologies has been raised in academic and industry research communities and has also been noted by regulatory authorities. Therefore, to address this unmet need, we here propose a metadata set that reflects regulatory guidelines and that can serve as a conceptual map to (1) inform researchers on the metadata they should collect in digital health studies, aiming to increase the interpretability and exchangeability of their data, and (2) direct standard development organizations on how to extend their existing standards to incorporate digital health technologies. The proposed metadata set is informed by existing standards pertaining to clinical trials and medical devices, in addition to existing schemas that have supported digital health technology studies. We illustrate this specifically in the context of Parkinson's disease, as a model for a wide range of other chronic conditions for which remote monitoring would be useful in both care and science. We invite the scientific and clinical research communities to apply the proposed metadata set to ongoing and planned research. Where the proposed metadata fall short, we ask users to contribute to its ongoing revision so that an adequate degree of consensus can be maintained in a rapidly evolving technology landscape. © 2019 The Author(s

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

Image Analysis of MRI-based Brain Tumor Classification and Segmentation using BSA and RELM Networks

Image Analysis of MRI-based Brain Tumor Classification and S...

引用

Automation, Computing and Renewable Systems (ICACRS), International Conference on

作者： R. Saranya R Pushpakumar P Srinivasan N Aparna K. Karthika Amit Chauhan Department of Computer science with Data Analytics PSG College of Arts and Science Coimbatore India Department of Information Technology Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of ECE Sona College of Technology Salem Tamilnadu India Department of Biomedical Engineering Dhaanish Ahmed Institute of Technology Verappanur Tamil Nadu India Civil Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Department of Life Sciences School of Sciences CHRIST (Deemed to be university) Bengaluru Karnataka India

Brain tumor segmentation plays a crucial role in medical image analysis. Brain tumor patients considerably benefit from early discovery due to the increased likelihood of a successful outcome from therapy. Due to the sheer volume of MRI images generated in everyday clinical practice, manually isolating brain tumors for cancer diagnosis is a challenging task. Automatic segmentation of images of brain tumors is essential. This system aimed to synthesize previous methods for BSA-RELM-based brain tumor segmentation. The proposed methodology rests on four fundamental pillars: preprocessing, segmentation, feature extraction, and model training. Filtering, scaling, boosting contrast, and sharpening are all examples of preprocessing techniques. When doing segmentation, a clustering technique based on Fuzzy Clustering Means (FCM) is used to breakdown the overall dataset into numerous subsets. The proposed approach used the region of filling for feature extraction. After that, a BSA-RELM is used to train the models with the input features. The proposed technique outperforms BSA and RELM, two of the most common alternatives. There was a 98.61 percent success rate with the recommended method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Awareness requirement and performance management for adaptive systems: a survey

arXiv

引用

arXiv 2023年

作者： Rashid, Tarik A. Hassan, Bryar A. Alsadoon, Abeer Qader, Shko Vimal, S. Chhabra, Amit Yaseen, Zaher Mundher Computer Science and Engineering Department School of Science and Engineering University of Kurdistan Hewler Kurdistan Region Erbil Iraq Department of Information Technology Kurdistan Institution for Strategic Studies and Scientifc Research KRI Sulaymaniyah46001 Iraq School of Computing and Mathematics Charles Sturt University Sydney Australia School of Computing Engineering and Mathematics Western Sydney University Sydney City Campus Sydney Australia Sydney Australia Information Technology Department Kent Institute Australia Sydney Australia Department of Information Technology University College of Goizha Kurdistan Region Sulaimani Iraq Data Analytics Lab Department of Artifcial Intelligence and Data Science Ramco Institute of Technology North Venganallur Village Virudhunagar District Tamilnadu Rajapalayam626 117 India Department of Computer Engineering and Technology Guru Nanak Dev University Amritsar India Civil and Environmental Engineering Department King Fahd University of Petroleum & Minerals Dhahran31621 Saudi Arabia Department of Computer Science College of Science Charmo University KRI Chamchamal46023 Iraq Department of Information Technology Computer Science Institute Sulaimani Polytechnic University KRI Sulaymaniyah46001 Iraq

Self-adaptive software can assess and modify its behavior when the assessment indicates that the program is not performing as intended or when improved functionality or performance is available. Since the mid-1960s, the subject of system adaptivity has been extensively researched, and during the last decade, many application areas and technologies involving self-adaptation have gained prominence. All of these efforts have in common the introduction of self-adaptability through software. Thus, it is essential to investigate systematic software engineering methods to create self-adaptive systems that may be used across different domains. The primary objective of this research is to summarize current advances in awareness requirements for adaptive strategies based on an examination of state-of-the-art methods described in the literature. This paper presents a review of self-adaptive systems in the context of requirement awareness and summarizes the most common methodologies applied. At first glance, it gives a review of the previous surveys and works about self-adaptive systems. Afterward, it classifies the current self-adaptive systems based on six criteria. Then, it presents and evaluates the most common self-adaptive approaches. Lastly, an evaluation among the self-adaptive models is conducted based on four concepts (requirements description, monitoring, relationship, dependency/impact, and tools). © 2023, CC BY-NC-ND.

关键词： Adaptive systems

来源：评论

学校读者我要写书评

暂无评论

Qpplab: A Generally Applicable Software Package for Detecting, Analyzing, and Visualizing Large-Scale Quasiperiodic Spatiotemporal Patterns (Qpps) of Brain Activity

SSRN

引用

SSRN 2024年

作者： Xu, Nan Yousefi, Behnaz Anumba, Nmachi LaGrow, Theodore J. Zhang, Xiaodi Keilholz, Shella Wallace H. Coulter Department of Biomedical Engineering Georgia Institute of Technology Emory University AtlantaGA United States Tri-institutional Center for Translational Research in Neuroimaging and Data Science Georgia State University Georgia Institute of Technology Emory University AtlantaGA United States Electrical and Computer Engineering Georgia Institute of Technology AtlantaGA United States Georgia Institute of Technology United States

One prominent brain dynamic process detected in functional neuroimaging data is large-scale quasi-periodic patterns (QPPs) which display spatiotemporal propagations along brain cortical gradients. QPP associates with the infraslow neural activity related to attention and arousal fluctuations and has been identified in both resting and task-evoked brains across various species. Several QPP detection and analysis tools were developed for distinct applications with study-specific parameters methods. This MATLAB package provides a simplified and user-friendly generally applicable toolbox for detecting, analyzing, and visualizing QPPs from fMRI timeseries of the brain. This paper describes the software functions and presents its ease of use on any brain datasets. © 2024, The Authors. All rights reserved.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Cutting-Edge Robotic Arm Design: Harnessing Flex Sensors and Novel Controller Framework to Meet Real-World Innovations

Cutting-Edge Robotic Arm Design: Harnessing Flex Sensors and...

引用

Intelligent Systems for Cybersecurity (ISCS), International Conference on

作者： V. Syambabu K. Kalaiselvi S. Derisha Mahil Hemalatha S Badi Alekhya N. Kanagavalli Department of Electronics and Communication Engineering MLR Institute of Technology Hyderabad India Department of Data Analytics Saveetha College of Liberal Arts and Sciences Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India Department of CSE(AIML) S.A.Engineering College Chennai Tamil Nadu India Department of Electrical and Electronics Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Tamil Nadu India Department of AIML R.M.D Engineering College Chennai Tamil Nadu India Department of Computer Science and Engineering Rajalakshmi Institute of Technology Chennai Tamil Nadu India

ISBN: (数字)9798350375237

ISBN: (纸本)9798350375244

This research paper introduces a sophisticated arm movement tracking system, leveraging a multi-sensor fusion approach for enhanced precision and versatility. The comprehensive system comprises various components, including a dedicated cabinet, six Leap Motion sensors, six microcomputers, a Kinect depth camera, a KVM switcher, a router, and flex sensors. In addition to the aforementioned components, the integration of flex sensors enhances the system's capability to capture nuanced movements and gestures of the human arm. Flex sensors contribute valuable data to the multi-sensor fusion, further refining the arm movement tracking and providing a comprehensive understanding of the intricacies involved. By quantifying the Root Mean Square Error (RMSE) for each filtering technique, including the data from flex sensors, we gained valuable insights into the accuracy and precision achieved by Particle Filtering in refining data from the specified angles. This approach ensures a thorough validation of Particle Filtering's superior performance when compared to Existing filtering Methods. The systematic evaluation of RMSE serves as a robust method for assessing the effectiveness of Particle Filtering, affirming its potential as a high-performing solution for precise angle estimation and tracking within the context of the presented arm movement tracking system that incorporates flex sensors.

关键词： Flexible printed circuits Systematics Filtering Tracking Refining Switches Sensor fusion

来源：评论

学校读者我要写书评

暂无评论

A Novel Framework for the Development of Quality-Aware Autonomic IoT Applications

A Novel Framework for the Development of Quality-Aware Auton...

引用

Communications and Information Technologies (GCCIT), Global Conference on

作者： Ankur Singh Bisht Manjunatha R M. P. Karnik A. Amudha Nimesh Raj Shalini M Computer Science and Engineering Graphic Era Hill University Bhimtal Graphic Era Deemed to be University Dehradun Uttarakhand India School of Sciences Data Analytics and Mathematical Sciences JAIN (Deemed to be University) Bangalore Karnataka Computer Engineering Vishwakarma Institute of Technology Pune India Department of Electrical and Electronics Engineering Karpagam Academy of Higher Education Coimbatore Centre of Research Impact and Outcome Chitkara University Rajpura Punjab India Department of Electronics and Communication Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai

ISBN: (数字)9798350388916

ISBN: (纸本)9798350388923

A tremendous quantity of data is being generated via the Internet of Things (IoT). While our knowledge of how to assess the quality of this data at the network and device levels is expanding, there are still significant obstacles to overcome when it comes to interpreting and assessing the quality at the informational and application levels. If you want to know what aspects impact the overall system quality, this post will go over some of the problems with IoT systems and how to fix them at various OSI levels. Using two digital health apps made possible by the internet of things (IoT), the authors look at how semantics may be used to measure the system’s data quality and how to integrate multimodal information to clinical decision support. Important data quality issues arise from the fact that the Internet of Things (IoT) ecosystem generates massive amounts of data collected from a variety of heterogeneous sources. The reason for this is that the whole operation of the internet of things system is badly affected by low data quality standards. data quality has been the subject of much research outside of the Internet of Things (IoT) domain, and the idea is backed by massive standardization efforts. However, data quality management inside the IoT has received little attention. An essential idea with many existing applications for issue solving, data quality (DQ) is used in the creation and execution of information, handling data, decision making, as well as engineering systems. But the ways DQ is now integrated into data management pipelines aren’t flexible enough to accommodate all kinds of uses, which limits its use in the IoT space. A generic framework is introduced in this research that allows for the implementation of DQ assessment in a wide range of Internet of Things applications. A knowledge graph serves as the foundation of the framework, making it easy to incorporate into new uses. The study’s findings highlight many gaps in the current state of IoT quality a

关键词： Training Support vector machines Accuracy data integrity Semantics Vectors Classification algorithms Internet of Things Cultural differences Standards

来源：评论

学校读者我要写书评

暂无评论

Seeing biodiversity: Perspectives in machine learning for wildlife conservation

arXiv

引用

arXiv 2021年

作者： Tuia, Devis Kellenberger, Benjamin Beery, Sara Costelloe, Blair R. Zuffi, Silvia Risse, Benjamin Mathis, Alexander Mathis, Mackenzie Weygandt van Langevelde, Frank Burghardt, Tilo Kays, Roland Klinck, Holger Wikelski, Martin Couzin, Iain D. van Horn, Grant Crofoot, Margaret C. Stewart, Charles V. Berger-Wolf, Tanya Switzerland United States Max Planck Institute of Animal Behavior Germany Centre for the Advanced Study of Collective Behaviour University of Konstanz Germany Department of Biology University of Konstanz Germany Institute for Applied Mathematics and Information Technologies IMATI-CNR Italy Computer Science Department University of Münster Germany Switzerland Environmental Sciences Group Wageningen University Netherlands Computer Science Department University of Bristol United Kingdom Department of Forestry and Environmental Resources North Carolina State University United States North Carolina Museum of Natural Sciences United States Cornell Lab of Ornithology Cornell University United States Department of Computer Science Rensselaer Polytechnic Institute United States Translational Data Analytics Institute Ohio State University United States

data acquisition in animal ecology is rapidly accelerating due to inexpensive and accessible sensors such as smartphones, drones, satellites, audio recorders and bio-logging devices. These new technologies and the data they generate hold great potential for large-scale environmental monitoring and understanding, but are limited by current data processing approaches which are inefficient in how they ingest, digest, and distill data into relevant information. We argue that machine learning, and especially deep learning approaches, can meet this analytic challenge to enhance our understanding, monitoring capacity, and conservation of wildlife species. Incorporating machine learning into ecological workflows could improve inputs for population and behavior models and eventually lead to integrated hybrid modeling tools, with ecological models acting as constraints for machine learning models and the latter providing data-supported insights. In essence, by combining new machine learning approaches with ecological domain knowledge, animal ecologists can capitalize on the abundance of data generated by modern sensor technologies in order to reliably estimate population abundances, study animal behavior and mitigate human/wildlife conflicts. To succeed, this approach will require close collaboration and cross-disciplinary education between the computer science and animal ecology communities in order to ensure the quality of machine learning approaches and train a new generation of data scientists in ecology and conservation. © 2021, CC BY-NC-SA.

关键词： Ecology

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：