检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Innovation and Novelty in Engineering and Technology, INNOVA 2024

作者： Govinda Rajulu, G. Sharmila, L. Venkatesan, D. Srinivas, K. Krishnaiah, Nallam Kumar, K. Laxman Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Tamil Nadu Chennai India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Tamil Nadu India Dept. of Artificial Intelligence and Machine Learning St. Martin’s Engineering College Hyderabad India St. Martin’s Engineering College Hyderabad India Department of IT St. Martin's Engineering College Dhulapally Telangana Secunderabad India Deptartment of Computer Science and Design St. Martin’s Engineering College Hyderabad India

ISBN: (纸本)9798331505134

Lung and Colon (L&C) tumors are lethal sicknesses that can foster in a few organs all the while and, in specific circumstances, jeopardize human existence. Even though it is highly unlikely that these two types of cancer will develop simultaneously, delaying diagnosis significantly increases the likelihood of metastasis between the organs that are affected. To really treat specific sorts of malignant growth, histological determination is fundamental. In the past, doctors had to go through a long and difficult process to look at thermal images and figure out if a patient had cancer;however, this procedure may now be completed much more quickly thanks to the new technology options. Histological images of L&C tumors were classified using a hybrid Deep learning (DL) model with an attention mechanism and a multipath network in this study. To zero in on the main attributes and negligence the less significant ones, a consideration component was utilized. In a multipath network, data travels over a number of channels before each channel is converted and the output from all of the branches is combined. The multipath network is similar to grouped convolution when simplified. The five thermal image categories of the LC25000 dataset were utilized. Among these classes were two for colon disease and three for cellular breakdown in the lungs. The proposed model was compared to a number of well-known DL models, such as ResNet-50, VGG-16, and AlexNet. The proposed approach showed the best exhibition concerning exactness (99.2%), particularity (99.12%), responsiveness (99.28%), accuracy (99.12%), and F1 score (99.2%), as indicated by the exploratory discoveries. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

AI auditing: The Broken Bus on the Road to AI Accountability

AI auditing: The Broken Bus on the Road to AI Accountability

引用

Secure and Trustworthy machine learning (SaTML), IEEE Conference on

作者： Abeba Birhane Ryan Steed Victor Ojewale Briana Vecchione Inioluwa Deborah Raji Mozilla Foundation and Sch. of Computer Science and Statistics Trinity College Dublin Dublin Ireland Heinz College & Machine Learning Dept. Carnegie Mellon University Pittsburgh USA Ctr. for Technological Responsibility Reimagination & Redesign Brown University Providence USA Data & Society New York City USA Mozilla Foundation and University of California Berkeley Berkeley USA

One of the most concrete measures towards meaningful AI accountability is to consequentially assess and report the systems’ performance and impact. However, the practical nature of the "AI audit" ecosystem is muddled and imprecise, making it difficult to work through various concepts, practices, and involved (as well as ignored) stakeholders. First, we taxonomize current AI audit practices as completed by regulators, law firms, civil society, journalism, academia, and consulting agencies. Next, we assess the impact of audits done by stakeholders within each domain. We find that only a subset of AI audit studies translate to desired accountability outcomes. We thus assess and isolate practices necessary for effective AI audit results, articulating the observed connections between AI audit design, methodology and institutional context on its effectiveness as a meaningful mechanism for accountability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A comparative study of image dehazing algorithms 5

A comparative study of image dehazing algorithms

引用

5th International Conference on Communication and Electronics Systems, ICCES 2020

作者： Parihar, Anil Singh Gupta, Yash Kumar Singodia, Yash Singh, Vibhu Singh, Kavinder Machine Learning Research Lab Dept. of Computer Science Delhi Technological University Delhi India

ISBN: (纸本)9781728153711

Haze poses a great challenge in modern-day applications. Removing haze is a challenging task because haze varies with the dept. of the scenes in the image. Many automated systems like surveillance systems, object tracking, etc. use the dehazing methods internally to improve their overall performance in a hazy environment. Hence, recovering the original image from the hazy image is a crucial task. This paper provides a detailed survey of many algorithms that have been proposed for haze removal, which refines the image, either by using statistical observation of the scene or by network-based learning method. These algorithms have been assessed quantitatively and visually to compare based on their dehazing potential. The paper presents a comparative study of the various image dehazing methods having a different way of estimation of transmission and atmospheric light. This paper reviews different prior-based technique and learning-based technique image dehazing algorithms. © 2020 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Using InterCloudFramework to migrate application and data between two public clouds 7

Using InterCloudFramework to migrate application and data be...

引用

7th IEEE International Conference on Electronics, Computing and Communication Technologies, CONECCT 2021

作者： Koushik, S Patil, Annapurna P. Suma, C.S. M. S. Ramaiah Institute of Technology Dept. of Computer Science and Engineering Bengaluru India Dayananda Sagar Academy of Technology and Management Department of Artificial Intelligence and Machine Learning Bengaluru India

ISBN: (纸本)9781665428491

Cloud computing is an emerging computing platform for sharing resources over the internet, including infrastructure, applications, software, and business processes. Cloud computing is popular because of its public presentation, least cost, high availability. These days, many organizations use cloud services for their business activities to enhance their computing resource capabilities at lower prices. Cloud computing plays a vital role in research and academia to share resources and improve the teaching-learning process. One of the Cloud platforms' drawbacks is the data and application tightly coupled with the Cloud Service called Vendor Lock-In. Methods and procedures are available to migrate live data within the same cloud service providers. But to migrate the applications or data from one cloud service provider to another cloud service provider is complex. The paper proposes a novel methodology for migrating the application or data from one cloud service provider to another cloud service provider. The proposed approach presents CPU and RAM usage for the migration of applications or data. The paper also provides insights into the time taken for the Live Migration between heterogeneous clouds. © 2021 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Detection of Emergency Vehicles in Traffic and Assign Traffic Free Path Using Deep learning

Detection of Emergency Vehicles in Traffic and Assign Traffi...

引用

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

作者： Sriharsha Vikruthi Tejesh Reddy Singasani V T Ram Pavan Kumar M P V V S D Nagendrudu Ch Raghavendra R. Sahith Dept of CSE B V Raju Institute of Technology Narsapur Medak Telangana India University of Cumberlands Lousiville KY Dept of Computer Science Kakaraparti Bhavanarayana College Vijayawada Andhrapradesh India Department of Artificial Intelligence and Machine Learning Aditya Univeristy Suramplaem India Dept of CSE(Data Science) KKR & KSR Institute of Technology and Sciences Guntur Andhra Pradesh Dept of Computer Science and Engineering CVR College of Engineering Hyderabad Telangana India

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

Too much of Traffic jams are in a highly populated country. Sometimes emergency vehicles such as fire-fighter and ambulance get stuck in traffic, putting lives at threat in many cases. Priority should be given to special vehicles and their way should be cleared. However, traffic police find it difficult or sometimes impossible to handle with it. Emergency vehicles have visual and audio warning devices help them to overtake traffic by demanding as little space as possible from other vehicles. Many death happen due to delay in doctors, ambulance and fire engine vehicles while reaching their destinations. The traditional systems didn't provide path free route accurately. Therefore, by using detection of emergency vehicles in traffic and assign traffic free path using deep learning system, emergency vehicles can get free path or fast route by observing the traffic cameras. So, those emergency vehicles can reach the location on time by using RNN system. Therefore, the main objective is to improve this system for better results interms of accuracy, detection rate and precision.

关键词： Deep learning Space vehicles Visualization Sentiment analysis Recurrent neural networks Accuracy Law enforcement Roads Medical services Automobiles

来源：评论

学校读者我要写书评

暂无评论

Translation System for the Visually Impaired from English to Braille

Translation System for the Visually Impaired from English to...

引用

Communication & Computing (WCONF), World Conference on

作者： J. Aswini Lokesh Krishnaa M C. Lakshmipriya G. Lavanya Siva Subramanian R Dept of Artificial Intelligence & Machine Learning Saveetha Engineering College(Autonomous) Department of Artificial Intelligence and a Science Saveetha Engineering College (Autonomous) Department CSE S.A. Engineering College Department of Artificial Intelligence and Data Science Saveetha Engineering College(Autonomous) Department CSE R.M.K College of Engineering and Technology

ISBN: (数字)9798350395327

ISBN: (纸本)9798350395334

The amount of information in the modern world is huge and is growing at a rapid speed because of new technological advancements and new researches being conducted every day. Internet has paved a pivotal role in the distribution of information easily which has enriched human knowledge. This interconnected digital landscape has significantly enhanced accessibility and the flow of information, marking a transformative shift in how knowledge is shared and updated. Various software and websites enable the translation of information into any language, providing flexibility and accessibility across diverse linguistic preferences which helps people to grow their knowledge. But the Visually Impaired have no standard means to translate information to Braille which has caused a significant information gap for them. They are unable to get updated to new information and the information is not available for them in their language. This paper proposes to use deep learning which facilitates the translation of English text to Braille that aids the visually impaired in staying updated and also get access to information in Braille language.

关键词： Training Knowledge engineering Braille Accuracy Visual impairment Linguistics Software Internet Reliability Standards

来源：评论

学校读者我要写书评

暂无评论

Real-Time GPS Tracking and Health Monitoring for Animals Using IoT and Mobile Application

Real-Time GPS Tracking and Health Monitoring for Animals Usi...

引用

machine learning and Autonomous Systems (ICMLAS), International Conference on

作者： V. Usha Sandeep Karagatla P. Sheela Gowr P.M.G Jegathambal A. Lizy V. Sathya Dept. of CSE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Dept. of CSE (AI&DS) Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Vels Institute of Science Technology & Advanced Studies Chennai Dept. of Artificial Intelligence and Machine Learning Vel Tech Rangarajan Dr. Sagunthala (R&D) Institute of Science and Technology Chennai India Dept of Information Technology Velammal Engineering College Chennai India

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

The Internet of Things (IoT) grounded solution of Real Time Global Positioning System (GPS) tracking with Health Monitoring of Animals for Owners to track their animals like cows, buffaloes, dogs etc. This GPS module and a heartbeat sensor are attached to the animals in order to be able to follow them closely. This data is sent to a mobile app, and the owner can see their heart on the map as well as monitor its pulse. Based on analysis of such heart rate variations, the system determines when it is seeing an abnormal activity related to e.g. stress (increased heart rate) or potential health risks (no sign of a heartbeat), which could be interpreted as fear or death. Each animal has an initial heart rate level that is set, and when this rate exceeds it, the system sounds an alert to indicate danger. This method is especially helpful for keeping an eye on animals in urban areas, areas close to forests, and areas with high rates of theft and loss. The project demonstrates the successful execution of a reliable, real-time animal monitoring system with practical applications in both urban and rural environments.

关键词： Animals Tracking Heart beat LoRa Real-time systems Mobile applications Safety Internet of Things Monitoring Global Positioning System

来源：评论

学校读者我要写书评

暂无评论

Neural Meta-Symbolic Reasoning and learning

arXiv

引用

arXiv 2022年

作者： Ye, Zihan Shindo, Hikaru Dhami, Devendra Singh Kersting, Kristian AI and Machine Learning Group Dept. of Computer Science TU Darmstadt Germany Centre for Cognitive Science TU Darmstadt Germany Germany Germany Eindhoven University of Technology Netherlands

Deep neural learning uses an increasing amount of computation and data to solve very specific problems. By stark contrast, human minds solve a wide range of problems using a fixed amount of computation and limited experience. One ability that seems crucial to this kind of general intelligence is meta-reasoning, i.e., our ability to reason about reasoning. To make deep learning do more from less, we propose the first neural meta-symbolic system (NEMESYS) for reasoning and learning: meta programming using differentiable forward-chaining reasoning in first-order logic. Differentiable meta programming naturally allows NEMESYS to reason and learn several tasks efficiently. This is different from performing object-level deep reasoning and learning, which refers in some way to entities external to the system. In contrast, NEMESYS enables self-introspection, lifting from object- to meta-level reasoning and vice versa. In our extensive experiments, we demonstrate that NEMESYS can solve different kinds of tasks by adapting the meta-level programs without modifying the internal reasoning system. Moreover, we show that NEMESYS can learn meta-level programs given examples. This is difficult, if not impossible, for standard differentiable logic programming. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

LaCK: Lung Cancer Classification and Detection using Convolutional Neural Network-based Gated Recurrent Unit Neural Network Model

LaCK: Lung Cancer Classification and Detection using Convolu...

引用

Innovation in Technology (APCIT), Asia Pacific Conference on

作者： Machakanti Navya Thara Kalyan Chatterjee Muntha Raju Sandip Rout M. Priyadharshini Kokkula Shiva Prasad Samala Suraj Kumar Mandadi Sriya Reddy Artificial Intelligence & Machine Learning Nalla Malla Reddy Engineering College Hyderabad India Computer Science & Engineering Nalla Malla Reddy Engineering College Hyderabad India Angul Odisha Dept. of Higher Education Mathematics Government Autonomous College Government of Odisha India

ISBN: (数字)9798350361537

ISBN: (纸本)9798350361544

Cancer instills fear in people worldwide, with millions succumbing to its grasp each year. Among the various types, lung cancer stands as a prominent contributor to this alarming statistic. Therefore, this novel research Lung Cancer Classification and Detection using Convolutional Neural Network-based Gated Recurrent Unit Neural Network Model (LaCK) has focused on classifying lung cancer, notably Non-Small Cell Lung Cancer, which constitutes the majority of cases. We employed five units of gated recurrent unit neural network (GRU-NN) together to achieve this classification, utilizing logistic regression (LR) and support vector classifier (SVC) models for comparisons. Among all models, the LaCK model demonstrated remarkable accuracy, achieving approximately 98% success rate, outperforming its counterparts. Implementing this model in clinical settings enables medical professionals to establish a precise and automated approach to diagnosing lung cancer.

关键词： Logistic regression Technological innovation Accuracy Neural networks Lung cancer Static VAr compensators Logic gates

来源：评论

学校读者我要写书评

暂无评论

A hybrid approach for image denoising using explicit guided filter and collaborative wiener filter 2

A hybrid approach for image denoising using explicit guided ...

引用

2nd IEEE International Conference on Advances in Computing, Communication Control and Networking, ICACCCN 2020

作者： Parihar, Anil Singh Garg, Yash Bisht, Suverna Delhi Technological University Machine Learning Research Laboratory Dept. of Computer Science and Engineering Delhi India

ISBN: (纸本)9781728183374

In this paper, we propose an image denoising strategy which combines the edge-preserving property of an explicit filter, known as the guided filter, with the de-blurring property of a collaborative wiener filter. Removing noise from an image without losing the main image features such as object edges, corners, and other fine structures, while minimizing the blurring effects in the denoised image is the main objective of our proposed strategy. The guided filter is used in the preprocessing step and it takes into account the content from a reference image and transfers the structure of this image to the output, i.e. preprocessed image. The noisy input image is then processed by the wiener filter, which also involves the use of this preprocessed output image for collaborative filtering. The experimental results of our proposed approach show that not only the edges and other refined features in the input noisy image are preserved to a great extent, but also the extent of blurring is reduced to a satisfactory level. Our results, when compared to those of Guided filter, demonstrate that we are able to achieve a better denoising performance than this approach, regardless of the type of image used. © 2020 IEEE.

关键词： Image denoising

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：