检索结果-内蒙古大学图书馆

5th IEEE International Conference on Cybernetics, Cognition and Machine Learning Applications, ICCCMLA 2023

作者： Sarma, Himangshu Saharia, Navanath IIIT Department of Computer Science & Engineering Andhra PradeshSri City India IIIT Data Engineering Lab CSE Senapati Manipur India

ISBN: (纸本)9798350338287

According to the World Health Organization (WHO), 1.3 million people loss their life annually as a result of road accidents. By alerting or assisting the driver while they are driving, information technology such as computer vision can play a significant part in reducing the accident rate. Keeping that in mind, in this article we presents one traffic sign recognition tool using deep neural network (DNN) models with speech-based feedback for vehicle drivers. The proposed system can give voice-based feedback to driver to direct or inform them to take the appropriate action while driving, such as 'Drive slow, speed breaker ahead', 'Maximum Speed Limit is 80km/hr', 'School Ahead, drive slow', 'Don't take overtake' etc. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Pushing AI to wireless network edge: an overview on integrated sensing, communication, and computation towards 6G

引用

science China(Information sciences) 2023年第3期66卷 7-25页

作者： Guangxu ZHU Zhonghao LYU Xiang JIAO Peixi LIU Mingzhe CHEN Jie XU Shuguang CUI Ping ZHANG Shenzhen Research Institute of Big Data Future Network of Intelligence Institute (FNii) The Chinese University of Hong Kong (Shenzhen) School of Science and Engineering (SSE) The Chinese University of Hong Kong (Shenzhen) State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Peking University Department of Electrical and Computer Engineering and Institute for Data Science and Computing University of Miami Peng Cheng Laboratory State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications

Pushing artificial intelligence(AI) from central cloud to network edge has reached board consensus in both industry and academia for materializing the vision of artificial intelligence of things(AIoT) in the sixth-generation(6G) era. This gives rise to an emerging research area known as edge intelligence, which concerns the distillation of human-like intelligence from the vast amount of data scattered at the wireless network edge. Typically, realizing edge intelligence corresponds to the processes of sensing, communication,and computation, which are coupled ingredients for data generation, exchanging, and processing, ***, conventional wireless networks design the three mentioned ingredients separately in a task-agnostic manner, which leads to difficulties in accommodating the stringent demands of ultra-low latency, ultra-high reliability, and high capacity in emerging AI applications like auto-driving and metaverse. This thus prompts a new design paradigm of seamlessly integrated sensing, communication, and computation(ISCC) in a taskoriented manner, which comprehensively accounts for the use of the data in downstream AI tasks. In view of its growing interest, this study provides a timely overview of ISCC for edge intelligence by introducing its basic concept, design challenges, and enabling techniques, surveying the state-of-the-art advancements, and shedding light on the road ahead.

关键词： sixth-generation (6G) edge intelligence artificial intelligence of things (AIoT) integrated sensing communication and computation (ISCC)

来源：评论

学校读者我要写书评

暂无评论

MeghaOS: Cloud based operating system and a framework for mobile application development

MeghaOS: Cloud based operating system and a framework for mo...

引用

2011 World Congress on Information and Communication Technologies, WICT 2011

作者： Srinivasa, K.G. Harish Raddi, C.S. Mohan Krishna, S.H. Venkatesh, Nidhi Data Mining Laboratory Department of Computer Science and Engineering M. S. Ramaiah Institute of Technology Bangalore - 560054 India

ISBN: (纸本)9781467301251

With the advent in high-speed Internet technologies, the concept of cloud computing has become more popular. In the proposed system, users work with Cloud-based framework accessible via browser on any device, which is similar in services, applications, look and feel of an operating system. With this design, users can work from multiple devices and multiple places which are accessible to Internet over the same set of applications and files. Cloud computing makes collaboration simpler and can reduce platform-incompatibility problems. Proposed system is a interface that allows people to access applications stored completely or partly on the Cloud. Though it mimics the user interface of traditional computer operating systems, it doesn't interact directly with the computer's hardware as done by the typical operating system. The traditional OS on the device must exist on the mobile device in order to have the web browser which is necessary for accessing the system. This is important for people who don't have their own computers and must work out of libraries, schools and Cyber cafes. Also, user can work, log out, and then log in later from a different computer. By giving cross-platform applications to developers, it is an easy way to access enhanced features on system helping them to embrace this as a target platform. The applications developed under this SDK will usually be cached on the client side as it should not burden the network to access it frequently thus the data intensive applications can work even if the device is offline and sync the updated data on to the Cloud. With this, we have demonstrated that there is a better way to build Cloud based operating system framework that runs in an ordinary web browser without installation or browser plug-in components, thereby supporting cloud based applications with rich user interface features and direct interaction, also enables application development for in web browser and deployment on cloud using nothing more than e

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Oil Spill Detection System in the Arabian Gulf Region: An Azure Machine-Learning Approach

Oil Spill Detection System in the Arabian Gulf Region: An Az...

引用

2021 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies, 3ICT 2021

作者： Almeer, Shaima Albalooshi, Fatema Alhajeri, Aysha National Space Science Agency Space Data Analysis Laboratory Manama Bahrain Univeristy of Bahrain Computer Engineering Department Manama Bahrain

ISBN: (纸本)9781665440325

Locating oil spills is a crucial portion of an effective marine contamination administration. In this paper, we address the issue of oil spillage location exposure within the Arabian Gulf region, by leveraging a Machine-Learning (ML) workflow on a cloud-based computing platform: Microsoft Azure Machine-Learning Service (Custom Vision). Our workflow comprises of virtual machine, database, and four modules (Information Collection Module, Discovery Show, Application Module, and a Choice Module). The adequacy of the proposed workflow is assessed on Synthetic Aperture Radar (SAR) imagery of the targeted region. Qualitative and quantitative analysis show that the purposed algorithm can detect oil spill occurrence with an accuracy of 90.5%. © 2021 IEEE.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of algorithm with multichannel load balancing and failover for generic storage area networks 9

Design and implementation of algorithm with multichannel loa...

引用

9th International Conference on Communications Systems, ICCS 2004

作者： Ng, Kelvin Wang, Wilson Y.H Department of Electrical and Computer Engineering National University of Singapore Singapore Data Storage Institute Agency for Science Teclmology and Research Singapore Singapore

ISBN: (纸本)0780385497

This paper presents the design of an algorithm to provide end-toend multichannel load balancing and failover for generic SANs. A virtual channel is formed by the aggregation of multiple subchannels. This provides scalability as sub-channels can be added or removed when required. Multiple sub-channels also improve the reliability of storage network. By exchanging information between 2 hosts, the algorithm is also able to balance both the transmission and reception load. Additional information can be added to transmitted packets by lowering the MTU value of a virtual network interface. This additional information can be used to identifY the network storage protocol used so as to provide end-to-end multichannel functionality independent of the network storage protocol used. Results have shown that the implementation is able to provide higher throughput with the added benefits of end-to-end load balancing and failover to both HyperSCSI and iSCSI. © 2004 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Socially Intelligent Agent-Building

Towards Socially Intelligent Agent-Building

引用

1997 AAAI Fall Symposium

作者： Sengers, Phoebe Department of Computer Science and Program in Literary and Cultural Theory Carnegie Mellon University PittsburghPA15213 United States

If agents are going to interact socially with humans, they can not be simply correct;they must also be comprehensible. This article describes my thesis work-in-progress, which focuseson designingagents that caneffectively expressto users the goals and activities their designer has chosen for them. In order to build agents that express clearly the intentions of their designers, I am creating tools that allow a designer to build agents with respect, not merely to their internal goals and behaviors, but also to the signs that agents communicate to their audiences. By focusing on the agent within a social, communicative environment and explicitly considering the narrative structure of the agent's behaviors, builders can construct agents whose goals and intentions are clearly, effectively, and explicitly communicated;rather than, as has been done in the past, leaving the communication of these essential aspects of their agents over to a chance side-effect of their agents' internally-defined behaviors. My thesis is that it is not only the agents themselves that must become social;the process of designing agents must become socially intelligent as well - by putting agents in the context of their designer and audience, we can allow designers to build agents that function more effectively in the social and cultural environment within which the agents will be inserted. copyright © 1997, AAAI (***). All rights reserved.

关键词： Intelligent agents

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Algorithms used in Crop Yield Prediction for Precision Agriculture 4

Machine Learning Algorithms used in Crop Yield Prediction fo...

引用

4th International Conference on Soft Computing for Security Applications, ICSCSA 2024

作者： Umamaheswari, R. Shanmugapriya, S. Vimala, P. Ganesan, R. Vel Tech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology Department of Computer Science and Engineering Chennai India Vel Tech High Tech Dr.Rangarajan Dr. Sagunthala Engineering College Department of Computer Science and Engineering Chennai India Saveetha Engineering College Department of Artificial Intelligence and Data Science Chennai India

ISBN: (纸本)9798331515720

Agriculture is a crucial sector that plays a vital role in producing food for human consumption. However, predicting crop yield accurately can be a challenging task due to various natural factors, such as soil quality, climate, rainfall, and resource availability. In the past, farmers relied on their expertise and judgment to determine crop yield, but their traditional methods have become less effective due to the unpredictable nature of these factors. To address this challenge, researchers have developed various algorithms and models for predicting crop yield based on different parameters, such as soil quality, climate, and image analysis. These algorithms can help farmers make informed decisions about when and where to grow their crops, leading to improved productivity and higher yields. Among these algorithms, neural networks are showing great promise as they can analyze vast amounts of data and identify patterns that may not be immediately apparent to human observers. By training neural networks on historical crop yield data, researchers can develop models that accurately predict crop yield based on a variety of factors. Ensuring accurate crop yield prediction is critical to ensuring food security and preventing famine, particularly in developing countries such as India. As technology continues to advance, we can expect even more advanced algorithms and models for predicting crop yield that will help farmers make better decisions and ultimately lead to increased productivity and better outcomes for agriculture. © 2024 IEEE.

关键词： Agriculture Crop yield prediction (CYP) Machine learning Neural Network (NN)

来源：评论

学校读者我要写书评

暂无评论

Physically Grounded Deep Learning-Enabled Gold Nanoparticle Localization and Quantification in Photonic Resonator Absorption Microscopy for Digital Resolution Molecular Diagnostics

SSRN

引用

SSRN 2025年

作者： Lee, Hankeun Li, Siyan Liu, Leyang Wang, Weijing Ayupova, Takhmina Tibbs, Joseph Kim, Chansong Fang, Ying Do, Minh N. Cunningham, Brian T. Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign UrbanaIL United States Department of Bioengineering University of Illinois at Urbana-Champaign UrbanaIL United States Department of Chemistry University of Illinois at Urbana-Champaign UrbanaIL United States Department of Pathobiology College of Veterinary Medicine University of Illinois at Urbana-Champaign UrbanaIL United States Department of Materials Science and Engineering University of Illinois at Urbana-Champaign UrbanaIL United States Nick Holonyak Jr. Micro and Nanotechnology Lab University of Illinois at Urbana-Champaign UrbanaIL United States Center for Genomic Diagnostics Woese Institute for Genomic Biology UrbanaIL United States Carl R. Woese Institute for Genomic Biology University of Illinois at Urbana-Champaign UrbanaIL United States Grainger College of Engineering University of Illinois at Urbana-Champaign UrbanaIL United States Siebel School of Computing and Data Science University of Illinois at Urbana-Champaign UrbanaIL United States Carle Illinois College of Medicine University of Illinois at Urbana-Champaign UrbanaIL United States VinUni-Illinois Smart Health Center VinUniversity Hanoi Viet Nam

Accurate molecular biomarker detection with digital-resolution sensitivity is essential for applications such as disease diagnostics, therapeutic studies, and biomedical research. Here, we present LOCA-PRAM (LOcalization with Context Awareness), a deep learning-based method integrated with a Photonic Resonator Absorption Microscope (PRAM) to achieve digital-resolution detection of biomolecules using gold nanoparticles (AuNPs) as molecular tags. LOCA-PRAM leverages photonic crystal (PC)-AuNP resonant-coupling to enhance signal contrast, facilitating precise quantification of target molecules without partitioning the sample into droplets or enzymatic amplification. Through registration of PRAM images with Scanning Electron Microscopy (SEM) images, we empirically obtain the point spread function (PSF) of AuNP tags, enabling realistic training data generation for the deep learning framework. LOCA-PRAM surpasses conventional image processing method in accuracy and sensitivity, achieving reliable AuNP detection and localization even in high-density conditions, minimizing false-positive and false-negative quantifications and expending the dynamic range of assay. Benchmarking with SEM-derived ground truth confirms LOCA-PRAM’s sub-pixel resolution and ability to accurately quantify AuNPs with overlapping PSF. Overall, the PRAM combined with LOCA-based AuNP digital counting enables real-time, high-precision detection of molecular biomarkers, advancing digital-resolution biosensing for biomedical research and diagnostics. © 2025, The Authors. All rights reserved.

关键词： Gold nanoparticles

来源：评论

学校读者我要写书评

暂无评论

Development of Detection Lung Disease Stand Alone System Based on Convolutional Neural Network (CNN) 7

Development of Detection Lung Disease Stand Alone System Bas...

引用

7th International Conference of computer and Informatics Engineering, IC2IE 2024

作者： Liewarnata, Edgar Caesar Mariana, Yosica Tan, Sofyan Liawatimena, Suryadiputra Astuti, Winda Bina Nusantara University Binus Aso School of Engineering Automotive and Robotics Program Computer Engineering Department Jakarta11480 Indonesia Bina Nusantara University Binus Aso School of Engineering Product Design Program Industrial Engineering Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program - Master of Computer Science Automotive and Robotics Program Computer Engineering Department Binus Aso School of Engineering Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798331505530

Lung disease, especially Tuberculosis (TBC), placed the highest death rate in Indonesia. Tuberculosis (TB) in Indonesia is ranked second after India. Therefore, it is important to reduce or early detection of the lung disease, to prevent this disease and speed up handling. The system can recognize the disease lung identification, and the system applied as standalone system. In this work, the Convolutional Neural Network (CNN) approach for identifying diseases lung identification is proposed. The Mel Frequency Cepstral Coefficient (MFCC) applied to process the stethoscope sounds which will used as input to the CNN. The performance of the proposed system has been investigated and resulted. The accuracy of 99% and 98%, for training and testing accuracy respectively. Furthermore, the system accurately detects lung diseases identification. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Anomaly detection using Federated Learning: A Performance Based Parameter Aggregation Approach 3

Anomaly detection using Federated Learning: A Performance Ba...

引用

3rd IEEE International Conference on Intelligent Technologies, CONIT 2023

作者： Bhat, Pushkar Manohara Pai, M.M. Pai, Radhika M Manipal Institute of Technology Department of Information and Communication Technology Manipal India Manipal Institute of Technology Department of Data Science and Computer Applications Manipal India

ISBN: (纸本)9798350338607

Anomaly detection is a significant challenge that exists in multiple industries, including healthcare, finance, and manufacturing. Machine Learning techniques are extensively being used to solve these problems. However, data privacy concerns and regulations are making acquiring the necessary data for model training increasingly challenging, particularly in sensitive sectors. Federated learning has emerged as a promising solution, allowing local models to be trained on edge devices using local datasets and model parameters to be shared with a central server for aggregation. This allows the models to reap the benefits of the distributed data without actually sharing any data. However, the current aggregation method used in federated learning is susceptible to models trained on bad data, which can impact the accuracy and reliability of the resulting model. To address this issue, the study proposes a new filtered aggregation algorithm that greatly mitigates the effect of models trained on bad data. The proposed algorithm accounts for models that cannot detect anomalous patterns and gives them much less representation in the final model, resulting in improved accuracy and reliability. © 2023 IEEE.

关键词： Anomaly detection

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：