检索结果-内蒙古大学图书馆

International Interdisciplinary Conference on Mathematics, engineering and Science (MESIICON)

作者： Snigdha Kesh Gour Sundar Mitra Thakur Department of Computer Science and Engineering AMC Engineering College Bangalore Karnataka India Department of Artificial Intelligence and Machine Learning Dr B.C Roy Engineering College Durgapur West Bengal India

Transportation is the key context ingredient in modern life. Optimised route prediction is the vital aspect for commercial enterprises and individuals also. Proper route prediction not only helps to save time, fuel, and money, it additionally prevents accident, air pollution. Operational efficiency like uncertain event and incident can be cause for delay delivery, reaching late in destination that cause also the revenue loss for organisation and individual also. According to the 2019 Urban Mobility Report in 2017, congestion caused urban Americans to travel an extra 8.8 billion hours and purchase an extra 3.3 billion gallons of fuel for a congestion cost of $166 billion. Trucks account for $21 billion (12 percent) of the cost, much more than their 7 percent of traffic. The average auto commuter spends 54 hours in congestion and wastes 21 gallons of fuel due to congestion at a cost of $1,010 in wasted time and fuel. [1]. Nowadays drivers are using different Map software and GPS(Global Positioning System) to choose the appropriate route but sudden changes like climate variation, road congestion due to social gathering, road construction work etc. are difficult to incorporate in existing map software. With the development of Intelligent Transportation Systems (ITS) and Internet of Things (IoT), transportation data has become more and more ubiquitous. This triggers a series of data-driven research to investigate transportation phenomena. Among them, machine learning theory is considered one of the most promising techniques to tackle tremendous high-dimensional data. machine learning models are able to predict more accurate rote in transportation systems. This paper deeply analyses existing route prediction systems and different technology used in those systems. The Authors will focus on improving this route prediction using a machine learning model.

关键词： Deep learning Costs Roads Predictive models Software Mathematical models Delays

来源：评论

学校读者我要写书评

暂无评论

The Effective Way of using machine learning Classifier Technique to Predict the Heart Muscle Condition

The Effective Way of using Machine Learning Classifier Techn...

引用

Advance Computing and Innovative Technologies in engineering (ICACITE), International Conference on

作者： V.R. Vimal R. M. Joany Kolli Himantha Rao P. Muthu Krishnammal Zakhara Abdel Hassan Rashid Hassn Safi Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Thandalam Chennai Department of ECE Sathyabama Institute of Science and Technology Chennai Department of Artificial intelligence and machine learning Institute of CSE Saveetha Engineering College School of Electronics Engineering VITAP University Amaravati Andhra Pradesh College of Technical Engineering National University of Science and Technology Dhi Qar Iraq Al-Farahidi University Baghdad Iraq

ISBN: (数字)9798350360165

ISBN: (纸本)9798350360172

Free-text is categorised into predetermined groups in text classification, a crucial field of machine learning. Due to its many uses, such as sentiment analysis, topic labelling, language identification, and spam filtering, it has attracted a great deal of study interest. Ontologies and machine learning give the knowledge of data relations or patterns, which greatly increases the text categorization efficiency. The goal of this study is to diagnose myocardial infraction among patients by machine learning classifiers. The code that goes with the created approach is meant to be flexible and work with any text categorization system. In this research, we present an improved architecture that makes use of ontology to improve the efficacy of text categorization and diagnose myocardial infraction. In particular, we provide a novel ontology-driven text categorization technique that leverages the extensive semantic data from the Disease Ontology (DOID). We examine previous research and argue that ontology-based text categorization strategies are better than traditional techniques in a number of criteria, including as F-measure, Accuracy, Precision, and Recall.

关键词： Heart Sentiment analysis Filtering Text categorization Semantics machine learning Ontologies

来源：评论

学校读者我要写书评

暂无评论

Indian Sign Language Recognition Using Scale-Invariant Feature Transform by Depth Sensor

Indian Sign Language Recognition Using Scale-Invariant Featu...

引用

Cybernetics, Cognition and machine learning Applications (ICCCMLA), IEEE International Conference on

作者： Jayesh Gangrade Shweta Gangrade Ashish Mishra Gautam Kumar Vinit Kumar Gunjan Dept. of Artificial Intelligence & Machine Learning Manipal University Jaipur Jaipur India Dept of Information Technology Manipal University Jaipur Jaipur India Dept of Computer Science & Engineering Jaypee Institute of Information Technology Noida India Department of Computer Science & Engineering CMR Institute of Technology Hyderabad India

Deaf and hard of hearing people in the Indian community now have a way to communicate with society because to Indian Sign Language (ISL). The hand is accorded significant importance in the framework of the ISL. ISL is composed of both static and dynamic sign hand gestures. Both static and dynamic signs are made up of three components: hand movement, hand orientation, and hand position. The proposed method can recognize static ISL signs. The technique that was suggested makes use of the Microsoft Kinect sensor to locate and separate a hand from its background in a complex scene. SIFT, which stands for “scale-invariant feature transform,” was used to extract the feature. The SIFT algorithm is invariant under changes in perspective, orientation, and lighting. Recognize the 10 ISL digit movements with an accuracy of 94.9% using a multi support vector machine (MSVM).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Congestion Control Routing Scheme for WSN using AI Technologies

Congestion Control Routing Scheme for WSN using AI Technolog...

引用

Electrical, Electronics, Information and Communication Technologies (ICEEICT), International Conference on

作者： SK Mahaboob Basha E. Gurumoorthi E. Mercy Beulah R. Kesavan S.A. Kalaiselvan Lenin Kumar Department of Computer Science and Engineering TKR College of Engineering and Technology Telangana India Department of Computer Science and Engineering CMR College of Engineering & Technology Telangana India Department of Computer Science and Engineering Vel Tech Multi Tech Dr. Rangarajan Dr.Sakunthala Engineering College Chennai India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Department of Artificial Intelligence and Machine Learning Rajalakshmi Engineering College Chennai India Department of Electronics Communication and Engineering Vignan Institute of Technology and Sciences Telangana India

ISBN: (数字)9798350369083

ISBN: (纸本)9798350369090

An essential part of wireless sensor networks (WSN) is managing congestion, which occurs when the amount of traffic exceeds the combined or individual capacities of the underlying channel. As a result, developing more advanced methods to prevent, detect, and alleviate congestion requires particular considerations. In order to obtain the highest throughput, these strategies must take into account the limited resources of the WSN. Dedicated congestion control strategies and routing protocols that help in congestion detection as well as management are two of the many methods that have been created in recent years. As a means of avoiding congestion, the sink node in the previous designs would reset the topology and reduce bulk traffic. In this article, we lay the groundwork for WSNs and AI, the latter of which will try to prevent congestion in WSNs from the get-go and the former of which will try to minimize the spread of impending congestion by rerouting traffic. An integral part of modern life, artificial intelligence (AI) allows us to create self-governing systems. It is possible to enhance performance and reliability by making use of several sophisticated AI approaches. Better network management and routing in WSN may be the outcome of studying the AI algorithm used by WSN, leading to a more dependable network. Here we'll take a look at several AI algorithms that have found their way into WSNs, and we'll talk about how these algorithms might help WSNs overcome their challenges and become more reliable and efficient. Additionally, artificial intelligence has often been disregarded in these networks because of limitations on data processing as well as power consumptions. Thanks to AI, WSN is now lightning fast, error-free, as well as effective in almost every way. Using AI methods in nodes of wireless sensors for congestion aware routes is the goal of this work.

关键词： Wireless communication Training Wireless sensor networks System performance Routing Throughput Topology Reliability Communication system security artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement learning for IRS-assisted Secure NOMA Transmissions Against Eavesdroppers

Deep Reinforcement Learning for IRS-assisted Secure NOMA Tra...

引用

International Wireless Communications and Mobile Computing Conference, IWCMC

作者： Defeng Zhou Shimin Gong Lanhua Li Bo Gu Mohsen Guizani School of Intelligent Systems Engineering Shenzhen Campus of Sun Yat-sen University China Guangdong Provincial Key Laboratory of Fire Science and Intelligent Emergency Technology Guangzhou China Machine Learning Department Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI) Abu Dhabi UAE

ISBN: (数字)9798350361261

ISBN: (纸本)9798350361278

Physical layer security issues have attracted significant attention in wireless networks to protect information leakage from illegitimate eavesdroppers. In this paper, we focus on an intelligent reflecting surface (IRS)-assisted secure non-orthogonal multiple access (NOMA) uplink system. Multiple users intend to transmit sensitive data to an access point (AP) considering the existence of a nearby eavesdropper (Eve). The IRS can be used to enhance the NOMA users’ sum rates while concurrently weakening the Eve’s channel condition, suppressing information leakage to the Eve without resorting to a cooperative jammer or the power injection of artificial noise in the system. The users’ scheduling, the IRS’s passive beamforming, and the AP’s receive beamforming are jointly optimized to maximize the secure rate of the IRS-assisted NOMA system. We develop a hierarchical deep reinforcement learning (DRL) framework to iteratively search for an optimal solution considering the combinatorial nature of the NOMA users’ scheduling and the high-dimensional beamforming design. Firstly, we search for the NOMA users’ scheduling strategy by using the PPO-based DRL algorithm. Given the NOMA scheduling strategy, we then optimize the active and passive beamforming strategies by the alternating optimization (AO) algorithm. The inner optimization helps evaluate the quality of the scheduling strategy and thus guides the outer-PPO algorithm to update a better scheduling strategy. Simulation results demonstrate the superiority of the proposed scheme over existing benchmarks, resulting in significant gains in secure rate.

关键词： NOMA Array signal processing Simulation Noise Information leakage Deep reinforcement learning Scheduling

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation for Ultra-Dense 5G and Beyond Networks Based on Proximal Policy Optimization 3

Resource Allocation for Ultra-Dense 5G and Beyond Networks B...

引用

3rd International Conference on Integrated Circuits and Communication Systems, ICICACS 2025

作者： Husseyn, Muhamed Nagarathna, P. Rajasekar, S.S. Varsha, R. Venkatasubramanian, R. College of Technical Engineering The Islamic University Department of Computers Techniques Engineering Al Diwaniyah Iraq Nitte Meenakshi Institute of Technology Department of Computer Science Bengaluru India Bannari Amman Institute of Technology Department of Artificial Intelligence and Machine Learning Sathyamangalam India Dhanalakshmi Srinivasan College of Engineering Technology Department of Computer Science and Engineering Mamallapuram India New Prince Shri Bhavani College of Engineering and Technology Department of Electrical and Electronics Engineering Chennai India

ISBN: (纸本)9798331508456

In recent years, resource allocation in Ultra Dense Networks (UDNs), which consist of Small Base Stations (SBSs), plays a crucial role in enhancing the efficiency and capacity of the network. However, significant challenges such as severe interference, inefficient resource utilization and congestion are introduced in the network due to the high density of SBSs. To overcome these challenges, a policy-based reinforcement learning method, Proximal Policy Optimization (PPO) is proposed, which continuously learns and adapts the network conditions by adjusting power levels and resource allocations, ensuring maximum Spectral Efficiency (SE) and Energy Efficiency (EE). Firstly, a 5G UDN downlink framework is developed, which includes a Macro Base Station (MBS). This MBS is integrated with a server, namely Mobile Edge Computing (MEC), which performs resource allocation among distributed SBSs and User Equipment (UEs). Furthermore, PPO is employed to train the MEC, which acts as an agent and interacts with the whole UDN environment, to make better decisions by improving its policy through reinforcement learning updates. The proposed PPO outperformed DQN by achieving 800bps/Hz in SE and 700bps/J in EE respectively. © 2025 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Exploring the Tangible Impact of artificial intelligence and machine learning: Bridging the Gap between Hype and Reality

Exploring the Tangible Impact of Artificial Intelligence and...

引用

Advanced Computing and Emerging Technologies (ACET), International Conference on

作者： Rahul Dattangire Ruchika Vaidya Divya Biradar Ashish Joon Data Engineering Publicis Sapient Houston Texas USA Department of Artificial Intelligence and Machine Learning Datta Meghe Institute of Higher Education and Research (DU) Wardha Maharashtra India Computer Science University of Texas at Arlington Arlington Texas USA Software Developer Andhus Technologies Inc Pensacola FL

ISBN: (数字)9798350367720

ISBN: (纸本)9798350367737

Beyond being merely trendy terms in technology, machine learning (ML) and artificial intelligence (AI) have directly influenced every industry. This article thus demystifies the true meaning of these technologies by sifting through the sultry descriptions. Here, we explore how AI and ML enhance efficiency, decision-making, and problem-solving in various sectors including health, Agriculture, finance, and production as we discover real-world applications. Continuing with the discussion of implementation challenges, the aspects of bias, ethical pitfalls, and report cards are examined. In addition, the article also covered how the integration of AI as well as ML remains a way of improving processes, creating better user experiences, and spurring innovation. This paper, which is also based on case studies, discusses the relationship between social welfare and AI and the importance of AI’s development and use being done responsibly. Considering all the discussed aspects, this volume provides a rather nuanced perspective on AI and ML, unmasking the myths around these concepts to reveal the fact that they have a highly significant impact on the current reality and its projected evolutions.

关键词： Technological innovation Ethics Decision making Finance machine learning Production Pressing Medical services Writing Problem-solving

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation for Ultra-Dense 5G and Beyond Networks Based on Proximal Policy Optimization

Resource Allocation for Ultra-Dense 5G and Beyond Networks B...

引用

Integrated Circuits and Communication Systems (ICICACS), IEEE International Conference on

作者： Muhamed Husseyn P Nagarathna S. S. Rajasekar Varsha R R. Venkatasubramanian Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Al Diwaniyah Iraq Department of Computer Science Nitte Meenakshi Institute of Technology Bengaluru India Department of Artificial intelligence and Machine Learning Bannari Amman Institute of technology Sathyamangalam India Department of Computer Science and Engineering Dhanalakshmi Srinivasan College of Engineering Technology Mamallapuram India Department of Electrical and Electronics Engineering New Prince Shri Bhavani College of Engineering and Technology Chennai India

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

关键词： Base stations Multi-access edge computing 5G mobile communication Spectral efficiency Reinforcement learning Interference Resource management Servers Optimization Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Particle Swarm Optimization for Efficient Brain Tumor Classification Using InceptionV3 Deep learning Model

Particle Swarm Optimization for Efficient Brain Tumor Classi...

引用

International Conference on Communication and Electronics Systems (ICCES)

作者： P. Akhila G. Prabaharan K. Pandiiyan S. L. Swarna Hussain. A U. Sakthivelu Department of Artificial Intelligence and Machine Learning B V Raju Institute of Technology Narsapur Telangana India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Department of Computer Science with Artificial Intelligence SRM Arts and Science College Chengalpattu India Department of Computer Science Science and Engineering Sona College of Technology Salem Tamil Nadu India Department of Networking and Communications College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamil Nadu India

ISBN: (数字)9798350377972

ISBN: (纸本)9798350377989

This research proposes a novel framework for brain tumor classification utilizing a combination of deep learning and optimization techniques. The framework employs an autoencoder network for image preprocessing, followed by SegNet for accurate tumor segmentation. The core classification is performed using the InceptionV3 model, further optimized through Particle Swarm Optimization (PSO) to enhance predictive performance. The proposed system achieved a classification accuracy of 98.75% on a dataset of 7,023 MRI images, demonstrating its effectiveness in accurately classifying brain tumors. This research contributes to the advancement of medical image analysis and provides a valuable tool for supporting clinicians in the early diagnosis and treatment of brain tumors.

关键词： Deep learning Accuracy Brain tumors Predictive models Brain modeling Planning Reliability Particle swarm optimization Optimization Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

MiniVLN: Efficient Vision-and-Language Navigation by Progressive Knowledge Distillation

arXiv

引用

arXiv 2024年

作者： Zhu, Junyou Qiao, Yanyuan Zhang, Siqi He, Xingjian Wu, Qi Liu, Jing The Institute of Automation Chinese Academy of Sciences Beijing100190 China The School of Artificial Intelligence University of Chinese Academy of Science Beijing100190 China The Australian Institute for Machine Learning The University of Adelaide AdelaideSA5005 Australia The Department of Computer Science and Technology Tongji University Shanghai201804 China

In recent years, Embodied artificial intelligence (Embodied AI) has advanced rapidly, yet the increasing size of models conflicts with the limited computational capabilities of Embodied AI platforms. To address this challenge, we aim to achieve both high model performance and practical deployability. Specifically, we focus on Vision-and-Language Navigation (VLN), a core task in Embodied AI. This paper introduces a two-stage knowledge distillation framework, producing a student model, MiniVLN, and showcasing the significant potential of distillation techniques in developing lightweight models. The proposed method aims to capture fine-grained knowledge during the pretraining phase and navigation-specific knowledge during the fine-tuning phase. Our findings indicate that the two-stage distillation approach is more effective in narrowing the performance gap between the teacher model and the student model compared to single-stage distillation. On the public R2R and REVERIE benchmarks, MiniVLN achieves performance on par with the teacher model while having only about 12% of the teacher model's parameter count. Copyright © 2024, The Authors. All rights reserved.

关键词： Students

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：