检索结果-内蒙古大学图书馆

2024 International Conference on Advances in Data engineering and Intelligent Computing Systems, ADICS 2024

作者： Mary, Anne Khanna, Bobby Malarvel, Muthukumaran Hindustan Institute Of Technology And Science Department Of Computer Science And Engineering Chennai India

ISBN: (纸本)9798350364828

Deep learning, a prominent facet of AI, has rapidly reshaped the healthcare landscape by offering swift and accurate data analysis techniques. These methodologies aid medical professionals and caregivers worldwide in achieving precise diagnoses and administering follow-up treatments. The brain, serving as the central control unit of the human body is accountable for making decisions. and overseeing the functionality of all other organs and systems, both voluntary and involuntary. Brain tumors, characterized by abnormal cell growth in the brain, can lead to severe conditions like Cancer. Examination through Magnetic Resonance Imaging (MRI) scans are the primary the technique employed by medical professionals to identify brain tumors offers detailed insights into any atypical tissue growth within the brain. By applying machine learning (ML) and deep learning (DL) algorithms to MRI images accelerates and enhances the identification and prediction of brain tumors, empowering radiologists to make quick and well-informed decisions. Our proposed methodology entails training a Deep Neural Network (DNN) model on a dataset of MRI images to pinpoint tumor segments within them for further analysis. We utilize the Flask web framework to detect tumor presence. Convolutional Neural Networks (CNNs) are harnessed in our model to detect and classify brain tumors using advanced deep learning techniques. We evaluate our system's performance by comparing it with traditional methods, validating its effectiveness and accuracy through diverse performance metrics. The results exhibit promising potential for future healthcare applications, enabling more precise and timely diagnoses. © 2024 IEEE.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition from Electroencephalogram (EEG) Signals Using a Multiple Column Convolutional Neural Network Model

引用

SN computer science 2024年第2期5卷 213页

作者： Jha, Sonu Kumar Suvvari, Somaraju Kumar, Mukesh Department of Computer Science and Engineering National Institute of Technology Patna Patna 800005 India

Emotions are vital in human cognition and are essential for human survival. Emotion is often associated with smart decisions, interpersonal behavior, and, to some extent, intellectual cognition. From the recent literature on emotion recognition, we understand that the researchers are showing interest in creating meaningful "emotional" associations between humans and machines;there is a demand for accurate and scalable systems to detect human emotional states, as emotion recognition is needed to understand the mental status of such persons who cannot communicate their emotions, such as disabled people, mentally challenged persons, etc. Therefore, EEG signals provide a non-invasive method to identify the emotions of these disabled humans. The research community has recently been very interested in employing electroencephalography (EEG) for emotion classification since end-users have wearable EEG systems that may offer a portable, cheap, and straightforward technique for identifying emotions. Deep learning models have recently been extensively used to extract characteristics and recognize emotions from EEG recordings. Apart from that, various papers were reviewed in this research. This paper presented a multiple-column CNN network with a leaky ReLU activation function on the EEG brain wave and DEAP datasets. Multiple scalp electrode locations are used to collect EEG signals, and each electrode offers spatially unique data. The network can detect spatial correlations and extract characteristics that depict the spatial distribution of brain activity by employing a multiple-column CNN, which simultaneously processes signals from many channels. This makes it possible for the model to recognize emotions using the spatial information in EEG data. The result analysis was evaluated on different CNN models, and it was observed that an accuracy of 98.10% was achieved on the EEG brainwave dataset and 81% on the DEAP dataset. © 2024, The Author(s), under exclusive licence to Sprin

关键词： Attention Convolution neural network (CNN) Deep learning EEG Emotion recognition GCNN Multicolumn CNN

来源：评论

学校读者我要写书评

暂无评论

Generative AI: A Transformative Force in Business Intelligence 2

Generative AI: A Transformative Force in Business Intelligen...

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Thiruneelakandan, A. Umamageswari, A. SRM Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350327533

In an era where data is the cornerstone of strategic decision-making, Generative Artificial Intelligence (Gen AI) is revolutionizing the Business Intelligence (BI) landscape. This study investigates the multifaceted role of Generative AI in BI, encompassing data generation and augmentation, predictive analytics, reporting automation, product and service innovation, and personalization of customer experiences. The work employs a combination of synthetic data generated by Generative Adversarial Networks (GANs) and Seasonal Autoregressive Integrated Moving Average (SARIMA) predictive modeling techniques to demonstrate the potent capabilities of Generative AI in enhancing data-driven insights. The findings reveal that Generative AI not only significantly improves the accuracy of predictive models, especially in scenarios with limited historical data but also streamlines reporting processes and catalyzes innovation by uncovering latent customer needs. The research underscores the transformative impact of Generative AI in BI, while also addressing the attendant ethical considerations and the necessity for rigorous data governance. Through this exploration, the study provides a roadmap for businesses to harness the power of Generative AI, paving the way for smarter, more agile, and more personalized business strategies. © 2024 IEEE.

关键词： Data Augmentation Ethical Artificial Intelligence Generative Adversarial Networks Generative Artificial Intelligence Reporting Automation

来源：评论

学校读者我要写书评

暂无评论

Secure Channel Estimation Using Norm Estimation Model for 5G Next Generation Wireless Networks

引用

computers, Materials & Continua 2025年第1期82卷 1151-1169页

作者： Khalil Ullah Song Jian Muhammad Naeem Ul Hassan Suliman Khan Mohammad Babar Arshad Ahmad Shafiq Ahmad Faculty of Information Engineering and Automation Kunming University of Science and TechnologyKunming650500China Department of Computer Science Abbottabad University of Science and TechnologyHavelianAbbottabad22500Pakistan Department of Computing and Electronics Engineering Middle East CollegeMuscat124Oman Department of CS&IT Pak-Austria Fachhochschule Institute of Applied Sciences and Technology MangHaripur22621Pakistan Industrial Engineering Department College of EngineeringKing Saud UniversityRiyadh11421Saudi Arabia

The emergence of next generation networks(NextG),including 5G and beyond,is reshaping the technological landscape of cellular and mobile *** networks are sufficiently scaled to interconnect billions of users and *** in academia and industry are focusing on technological advancements to achieve highspeed transmission,cell planning,and latency reduction to facilitate emerging applications such as virtual reality,the metaverse,smart cities,smart health,and autonomous *** continuously improves its network functionality to support these *** input multiple output(MIMO)technology offers spectral efficiency,dependability,and overall performance in *** article proposes a secure channel estimation technique in MIMO topology using a norm-estimation model to provide comprehensive insights into protecting NextG network components against adversarial *** technique aims to create long-lasting and secure NextG networks using this extended *** viability of MIMO applications and modern AI-driven methodologies to combat cybersecurity threats are explored in this ***,the proposed model demonstrates high performance in terms of reliability and accuracy,with a 20%reduction in the MalOut-RealOut-Diff metric compared to existing state-of-the-art techniques.

关键词： Next generation networks massive mimo communication network artificial intelligence 5G adversarial attacks channel estimation information security

来源：评论

学校读者我要写书评

暂无评论

Early Diagnosis of Lung Tumors for Extending Patients’ Life Using Deep Neural Networks

引用

computers, Materials & Continua 2023年第7期76卷 993-1007页

作者： A.Manju R.Kaladevi Shanmugasundaram Hariharan Shih-Yu Chen Vinay Kukreja Pradip Kumar Sharma Fayez Alqahtani Amr Tolba Jin Wang Department of Computer Science and Engineering SRM Institute of Science and TechnologyRamapuramChennaiIndia Department of Computer Science and Engineering Saveetha Engineering CollegeChennaiIndia Department of Computer Science and Engineering Vardhaman College of EngineeringHyderabadIndia Department of Computer Science and Information Engineering National Yunlin University of Science and TechnologyYunlin 64002Taiwan Intelligence Recognition Industry Service Research Center National Yunlin University of Science and TechnologyYunlin 64002Taiwan Chitkara University Institute of Engineering and Technology Chitkara UniversityPunjabIndia Department of Computing Science University of AberdeenAberdeenUK Software Engineering Department College of Computer and Information SciencesKing Saud UniversityRiyadh 12372Saudi Arabia Computer Science Department Community CollegeKing Saud UniversityRiyadh 11437Saudi Arabia School of Computer&Communication Engineering Changsha University of Science&TechnologyChangshaChina

The medical community has more concern on lung cancer *** experts’physical segmentation of lung cancers is time-consuming and needs to be *** research study’s objective is to diagnose lung tumors at an early stage to extend the life of humans using deep learning ***-Aided Diagnostic(CAD)system aids in the diagnosis and shortens the time necessary to detect the tumor *** application of Deep Neural Networks(DNN)has also been exhibited as an excellent and effective method in classification and segmentation *** research aims to separate lung cancers from images of Magnetic Resonance Imaging(MRI)with threshold *** Honey hook process categorizes lung cancer based on characteristics retrieved using several *** this principle,the work presents a solution for image compression utilizing a Deep Wave Auto-Encoder(DWAE).The combination of the two approaches significantly reduces the overall size of the feature set required for any future classification process performed using *** proposed DWAE-DNN image classifier is applied to a lung imaging dataset with Radial Basis Function(RBF)*** study reported promising results with an accuracy of 97.34%,whereas using the Decision Tree(DT)classifier has an accuracy of 94.24%.The proposed approach(DWAE-DNN)is found to classify the images with an accuracy of 98.67%,either as malignant or normal *** contrast to the accuracy requirements,the work also uses the benchmark standards like specificity,sensitivity,and precision to evaluate the efficiency of the *** is found from an investigation that the DT classifier provides the maximum performance in the DWAE-DNN depending on the network’s performance on image testing,as shown by the data acquired by the categorizers themselves.

关键词： Lung tumor deep wave auto encoder decision tree classifier deep neural networks extraction techniques

来源：评论

学校读者我要写书评

暂无评论

Study on Implementation of Shor’s Factorization Algorithm on Quantum computer

引用

SN computer science 2024年第4期5卷 413页

作者： Kumar, Mandeep Mondal, Bhaskar Department of Computer Science and Engineering National Institute of Technology Patna Patna 800005 India

The fundamental security aspect of the classical crypto-system depends on integer factorization and discrete logarithm problems. The quantum factorization problem is a crucial problem in quantum computing as it has significant implications for cryptography and security. Shos’s paper on “Polynomial-time algorithms for discrete logarithms and factoring on a quantum compute” has become a threat to the classical crypto-system, influencing many researchers to work on factorization problems using quantum computing. Quantum computers (QC) can be essential in running different factorization algorithms in polynomial time. However, practical implementation on larger numbers is still a major challenge due to the requirement for error correction and massive quantum devices. Although the quantum factorization issue puts traditional cryptographic systems at risk, it also opens up new possibilities for quantum communication and encryption. The challenge of factorization opens up an entirely new field for research into quantum communication protocol security, including quantum key distribution and the development of quantum-resistant cryptographic systems. This paper surveys the various quantum algorithms for factoring a number into prime integers. We present a simulation study of the Quantum factorization algorithm to determine the period of a process. Turning the factoring problem into the challenge of determining a function’s period is the essential strategy of practical implementation using the quantum circuit. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Factorization Quantum Fourier Transformation Quantum period finding Quantum phase estimation Shor’s algorithm

来源：评论

学校读者我要写书评

暂无评论

Smart Monitoring and Irrigation Regulation via IoT and Cloud 8

Smart Monitoring and Irrigation Regulation via IoT and Cloud

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Sumalatha, Konatham Harshdeep, Kumar Vellore Institute of Technology School of Computer Science & Engineering Department of Database Systems Vellore India Vellore Institute of Technology Computer Science and Engineering Vellore India

ISBN: (纸本)9798350376425

The increasing demand for agricultural produce and the strain on global water resources highlight the need for innovative solutions to improve water efficiency in farming. This work introduces an IoT-powered Smart Irrigation System designed to optimize water usage, ensuring sustainable crop cultivation. Traditional irrigation methods often lead to inefficiencies, wasting water and increasing costs, as they fail to consider varying soil moisture and environmental conditions across fields. This can result in suboptimal crop growth and resource depletion. To overcome these challenges, the proposed system integrates IoT technology with smart irrigation practices. Sensors deployed in the field collect real-time data on soil moisture, temperature, humidity, and light intensity, which a central controller then processes. Using cloud-based analytics, the controller adjusts irrigation schedules and water distribution to match current conditions precisely. The system's primary goal is to create an eco-friendly, cost-effective solution that reduces water waste, lowers operational costs, and minimizes environmental impact. Scalable and adaptable to various crops and environments, this smart irrigation system promises to improve crop yields, promote sustainable agriculture, and address water scarcity challenges globally. © 2024 IEEE.

关键词： Cloud Computing Real-Time Data Analytics Smart Irrigation Soil Moisture Sensors

来源：评论

学校读者我要写书评

暂无评论

Interactive Navigation with Human in the Loop Using Reinforcement Learning 10

Interactive Navigation with Human in the Loop Using Reinforc...

引用

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Srija, N. Sindhuja, U. Bobby, M.P. Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (数字)9798350384369

ISBN: (纸本)9798350384369

In this document, we present a groundbreaking concept that has the potential to revolutionize human-computer interaction: 'Hands-Free Mouse Control with Facial Recognition.' Our focus is on seamlessly integrating facial recognition technology with traditional mouse control systems, introducing a hands-free approach that transcends conventional input devices. The primary objective is to enhance accessibility, particularly for individuals facing mobility challenges or disabilities, by enabling users to navigate and interact with their computers through intuitive facial movements. This transformative concept prioritizes user convenience by eliminating the need for external hardware like mice or touchpads. Users can control their computers using natural facial gestures, fostering a more intuitive and user-friendly computing experience. Beyond its practical applications, this approach signifies a paradigm shift in the field of human-computer interaction, offering new possibilities for a more inclusive and accessible digital environment. To assist authors in effectively communicating their research, a concise guide and template are provided. The template covers essential sections such as the abstract, introduction, methodology, results, discussion, and conclusion. By employing this template, authors can contribute to the advancement of this transformative field, exploring the implications, challenges, and future developments of the hands-free mouse control with facial recognition concept. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

LLM-Enhanced Deepfake Detection: Dense CNN and Multi-Modal Fusion Framework for Precise Multimedia Authentication

LLM-Enhanced Deepfake Detection: Dense CNN and Multi-Modal F...

引用

2024 International Conference on Advances in Data engineering and Intelligent Computing Systems, ADICS 2024

作者： Samesh Enathe, V.P. Chandra Mouli, S. Dheepthi, R. Hindustan Institute Of Technology And Science Department Of Computer Science And Engineering Chennai India

ISBN: (纸本)9798350364828

The increasing ubiquity of deepfake technology presents a serious risk to the legitimacy and reliability of multimedia material across a number of sectors, from identity verification to news distribution. Current deepfake detection methods frequently have trouble identifying minor manipulations and are unable to keep up with the latest generation techniques, which creates a serious vulnerability in the defence against the improper use of synthetic media. Using Dense Convolutional Neural Networks (Dense CNN) and Multi-Modal Fusion, this study presents a novel method for deepfake detection. Our Dense CNN architecture which draws inspiration from Dense Net improves sensitivity to complex manipulations while optimizing feature reuse through dense connectivity patterns, thereby mitigating the shortcomings of existing systems. Our suggested approach dynamically combines temporal and visual modalities, enhanced by Multi-Modal Fusion, to offer a comprehensive contextual knowledge that enhances detection accuracy. After thorough tests on several datasets, our method performs exceptionally well and is particularly good at identifying advanced deepfake variations. Our suggested methodology improves the state-of-the-art in deepfake identification by addressing the shortcomings of current systems and providing a reliable response to the urgent problems brought on by the malicious usage of synthetic media in practical applications. Adding Large Language Models (LLMs) is essential to improving the accuracy of the system. To add another level of scrutiny, LLMs are deliberately used to characterize and analyze portions of multimedia information that are vulnerable to manipulation. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Global Perspective of Natural Fibre Reinforced Composites: Properties, and Applications

引用

Journal of The Institution of Engineers (India): Series C 2024年第5期105卷 1335-1350页

作者： Tyagi, Ankit Punia, Upender Dadhich, Abhishek Meena, S.L. Department of Mechanical Engineering Poornima College of Engineering Rajasthan Jaipur India Department of Mechanical Engineering DCRUST Haryana Murthal Sonipat India Department of Computer Science Engineering Poornima Institute of Engineering and Technology Rajasthan Jaipur India Department of Mechanical Engineering RTU Kota Rajasthan Kota India

The primary promoters for the advancement of NFRCs (Natural fibre reinforced composites) in many industries are the imperative need to decrease energy consumption and mitigate environmental consequences. Natural fibres provide several advantages in terms of affordability, biodegradability, lightweight nature, superior life-cycle performance, and good mechanical qualities. The present paper initially provides an overview of the different types, benefits and challenges of NFRCs with a brief description. Then after, the article briefly discussed the about DMA (Dynamic mechanical analysis), mechanical behavior, as well as thermal behavior characteristic of NFRCs. Finally, we shortly introduce natural fibres applications in the field of construction work, structures and buildings, automobiles industry, biomedical and pharmaceutical industries, furniture and architecture and in various other industries. Nonetheless, the intrinsic characteristics of natural fibres derived from plants have posed difficulties in the advancement and utilization of NFRCs. These challenges include inconsistent fibre quality, inadequate thermal stability, restricted mechanical properties, susceptibility to water absorption, and a tendency to clump together. © The Institution of Engineers (India) 2024.

关键词： Natural fibers

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：