检索结果-内蒙古大学图书馆

1st International Conference on Innovations in Communications, Electrical and computer engineering, ICICEC 2024

作者： Swetha, P. Sreenivasa, B.R. Pes University Department of Computer Science and Engineering Bangalore India Bapuji Institute of Engineering & Technology Department of Computer Science and Design Davangere India

ISBN: (数字)9798350376517

ISBN: (纸本)9798350376517

Understanding and interpreting sign languages are crucial for promoting communication among the Deaf and Hard of Hearing (DHH) populations [1]. Kannada Sign Language (KSL), primarily utilized in Karnataka, lacks sufficient digital tools and technical support compared to several other well-studied sign languages. To reduce this gap, this study uses machine language learning (ML) techniques to convert KSL gestures into text and speech. The hand movements and facial expressions used in the KSL signs were gathered and examined for this purpose. Convolutional neural networks (CNNs) and recurrent neural networks (RNNs), two examples of advanced machine-learning methods, have been used to create a reliable recognition system that can perform KSL in real time. The model has shown promising accuracy rates in the preliminary findings, instilling confidence in its potential to enhance KSL users' communication significantly. This study aims to improve education and daily communication among KSL speakers. The proposed model can be used at the regional Primary Healthcare Centers (PHC) for the effective interaction of a patient and doctors. In the future, we plan to expand the dataset, improve the algorithmic performance, and create user-friendly programs to make such programs useful at urban hospitals, too. © 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

Trends in The Sustainability of Related Blockchain Technologies and Bitcoin 5

Trends in The Sustainability of Related Blockchain Technolog...

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Pavitra, Mutyala Bardhiya, Himanshu S Gourshettiwar, Palash Computer Science and Design Sawangi India Artificial Intelligence & Data Science Sawangi India Computer Science and Medical Engineering Sawangi India

ISBN: (纸本)9798350383522

Based on an open-source software-powered peer-to-peer payment mechanism, Bitcoin is a digital currency that operates independently of a central bank. Its advantages over fiat money include cheaper transaction costs, increased security, and scalability. Scientists are becoming interested in it despite concerns about illicit usage and societal repercussions. This paper aims to describe and assess existing patterns inside the literature about the sustainability of bitcoin, considering social, economic, and environmental implications. Based on the study, it is evident that the entire system of money transitioning would need an exorbitant quantity of energy to the new cryptocurrency to operate the virtual currency system and mine new bitcoins, meaning that bitcoin is likely to remain a niche currency. A fragmented and democratic maintained public record of transactions is built on blockchain technology, which may open up new and difficult prospects. Block-layer and new state-driven cryptocurrency, the sharing of medical data, the production and distribution of energy in microgrids at the citizen level, and blockchain technology may all gain from the broad adoption of blockchain-based transactions. Bitcoin and associated blockchain technologies have the potential to transcend the concerns raised by many critics when seen as a catalyst for social change. © 2024 IEEE.

关键词： bitcoin digital money energy usage monetary transactions sustainability

来源：评论

学校读者我要写书评

暂无评论

Bitcoin Price Prediction Using Deep Learning Models 4

Bitcoin Price Prediction Using Deep Learning Models

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Hajare, Rasika Puri, Chetan Gote, Pradnyawant M. Faculty of Engineering and Technology Department of Computer Science and Design Maharashtra Wardha442001 India

ISBN: (纸本)9798331523923

Forecasting the price of bitcoins is significant in contemporary research, given the fact that the digital currency is relatively unpredictable and highly integrated in global securities markets. This paper compares the use of three deep learning models, namely recurrent neural networks (RNN), gated recurrent unit (GRU), and a convolutional neural network-long short-term memory (CNN-LSTM) for Bitcoin price prediction. Historical Bitcoin price data is used in the dataset, and every one of the models is trained and tested based on its performance to predict future prices based on past data. The proposed models include the RNN and GRU, which incorporate sequential dependency mappings to learn complex sequences, and the CNN-LSTM structures combine convolution layers for feature extraction and LSTM layers for sequencing. Different models' competency is discussed using the averaged Mean Squared Error (MSE) and graphs of the model's prediction against actual prices. The experimental results reveal that the proposed CNN-LSTM model has better prediction accuracy than RNN and GRU in time-series forecasting tasks, indicating that more complex architecture hybrid models might provide better forecasting performance. In analyzing and analyzing cryptocurrency price dynamics, this investigation gives information about the opportunities and challenges of these models to enhance future research. © 2025 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Noise4Denoise:Leveraging noise for unsupervised point cloud denoising

引用

Computational Visual Media 2024年第4期10卷 659-669页

作者： Weijia Wang Xiao Liu Hailing Zhou Lei Wei Zhigang Deng Manzur Murshed Xuequan Lu Deakin University GeelongVIC 3216Australia Department of Mechanical Engineering and Product Design Engineering Swinburne University of TechnologyMelbourneVIC 3122Australia Department of Computer Science University of HoustonHoustonTX 77204-3027USA Department of Computer Science and Information Technology La Trobe UniversityMelbourneVIC 3086Australia

Existing deep learning-based point cloud denoising methods are generally trained in a supervised manner that requires clean data as ground-truth ***,in practice,it is not always feasible to obtain clean point *** this paper,we introduce a novel unsupervised point cloud denoising method that eliminates the need to use clean point clouds as groundtruth labels during *** demonstrate that it is feasible for neural networks to only take noisy point clouds as input,and learn to approximate and restore their clean *** particular,we generate two noise levels for the original point clouds,requiring the second noise level to be twice the amount of the first noise *** this,we can deduce the relationship between the displacement information that recovers the clean surfaces across the two levels of noise,and thus learn the displacement of each noisy point in order to recover the corresponding clean *** experiments demonstrate that our method achieves outstanding denoising results across various datasets with synthetic and real-world noise,obtaining better performance than previous unsupervised methods and competitive performance to current supervised methods.

关键词： point clouds denoising geometry processing deep learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Air Quality Prediction with Hybrid Deep Learning Techniques: A Review 4

Enhancing Air Quality Prediction with Hybrid Deep Learning T...

引用

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

作者： Divya, J. Jaison, B. Computer Science and Design R.M.K. Engineering College India

ISBN: (纸本)9798331515720

Nowadays, air pollution is among the significant and crucial areas of concern to policymakers and environmental and public health experts internationally. It has been considered that bad air can badly affect human health, ecosystems, and climate change. This air pollution, or poor air quality, has been proven to have negatively life-Threatening and serious impacts. Accurate and timely adaption of air quality for various impacts is critical to avert the adverse impacts. The paper aims to provide an in-depth review of recent advances in air quality prediction using hybrid deep learning techniques. Mostly, the current methods of predicting the quality of air face challenges, like the inability to reproduce the complex and non-linear characteristics of air pollution. To tackle the existing challenges that bedevil traditional approaches, deep learning, being part of artificial intelligence with the capacity to bolster the efficiency and accuracy of the projections, has been adopted. Hybrid deep learning models, in association with physical or statistical models, offer promising approaches to enhance air quality prediction. This paper introduces the state-of-The-Art review of the major concepts and methodologies applied to air quality prediction with hybrid deep learning techniques, showing benefits and limits of such models, the summary of recent studies, and discussions on future research trends in this fast-growing and interesting field. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection for Secure Optimal Routing Techniques in Wireless Sensor Networks 2

Intrusion Detection for Secure Optimal Routing Techniques in...

引用

2nd IEEE International Conference on Advances in Information Technology, ICAIT 2024

作者： Karthick, V. Nirmalkumar, P. Parthasarathi, C. Sanjay, S.S. Department of Computer Science and Design Rajalakshmi Engineering College Tamilnadu Chennai India

ISBN: (纸本)9798350383867

There is a Wide variety of areas where WSNs are heavily relied upon, these network are referred to as radio frequency sensor networks, or simply WSNs. As far as the environment monitoring is concerned, WSNs are very imperative in that they facilitate the measurements of temperature, humidity, and air *** systems should be able to detect abnormal and suspicious movements like malware, denial of service attacks, and illegal access attempts. Our systems is also able to detect those attackers of WNS (Wireless Network System) attacks by using CHS(Cluster Head Selection) based optimal secure solution. We can do as well to build a secure wireless network that suits everyone, and protects all the data. Routing and security issues are tackled using AWNS and thereby, the availability of data becomes *** performs the task of anomaly detection and thereby the identification of extraordinary events and trends on the collected data is possible. These uncommon events are not just to be passed by and thrown up because of the fact that they might as well suggest a sensor failure, equipment failure, or even a possible hazard to the safety of the institution. © 2024 IEEE.

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

GNN-based Disease Detection and Classification in Cassava Leaf 5

GNN-based Disease Detection and Classification in Cassava Le...

引用

5th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2024

作者： Meenalochini, M. Amalroshini, A. Nandhini, K L Megha Murugan, C R Sogil Kongu Engineering College Dept. of Computer Science and Design Erode India

ISBN: (纸本)9798331518097

Cassava, a staple crop for millions of people worldwide, is highly susceptible to various leaf diseases, which can significantly reduce crop yields. Detecting and classifying these diseases at an early stage is crucial for effective disease management and crop protection. In this paper, we propose a novel approach for cassava leaf disease classification by combining Convolutional Neural Networks (CNNs) and Graph Neural Networks (GNNs). While CNNs excel at extracting local features from images, they often fail to capture complex spatial relationships between different regions of the leaf. To address this limitation, we integrate GNNs, which are well-suited for learning from irregular, structured data, such as the vein patterns and disease spread structures found in cassava leaves. By modeling the relationship between different regions of the cassava leaf as a graph G (V, E), where V represents nodes corresponding to superpixel regions of the leaf, and E represents edges capturing spatial relationships, the hybrid CNN-GNN model offers a more comprehensive and accurate classification system. The model is trained and evaluated on a dataset of cassava leaf images covering multiple disease categories, demonstrating superior performance over traditional CNN-based image classification techniques. This approach provides a scalable solution for improving the detection and management of cassava leaf diseases. © 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

True Random Number Generation on IBM Real-Time Quantum computer for Secure and Unpredictable Cryptographic Applications 2

True Random Number Generation on IBM Real-Time Quantum Compu...

引用

2nd IEEE International Conference on Advances in Information Technology, ICAIT 2024

作者： Karthick, V. Haritha, S. Janani, K. Department of Computer Science and Design Rajalakshmi Engineering College Tamilnadu Chennai India

ISBN: (纸本)9798350383867

Truly random integers, which are the absolute requirement for this type of cryptography, are necessary for data security. Conventional PRNGs is deterministically which makes them predicted. This type of weakness is present in them. Unlike conventional algorithms, QRNG uses something very fundamental, quantum physics. It has allowed for a breakthrough in using random numbers that are unpredictable. The main goal of the project to design a system including the QRNG (quantum random number generator) and cloud platform developed by IBM. The system produces robust and ideal output for cryptography while being both effective and efficient. We will conduct detailed and effective tuning and testing so as to increase output. Outputs of this project are a QRNG system built on the cloud that can be connected with cryptographic applications, certified sequence, and informational materials of the organization. With this research of QRNGs synchronized with the IBM cloud platform, we make cryptographic security stronger by using the quantum mechanical method to create truly random numbers. Moreover, QRNGs contribute to the cryptographic applications which are intended to be incredibly secure and of high dependability by providing random numbers to enter the realm of crypto-with very little human participation. Basically, the cloud-based architecture enable systems to scale and possible failure resilience via migrating the workload or storing the data online. Quantum improvements will speed up the process of replacing the currently accepted cryptographic paradigm with something opening new ways of digital communication. This research is about quantum physics, cloud computing, and cryptography, bringing together how these concepts operate, as a result, of the unexpected and secure cryptographic applications. © 2024 IEEE.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

MeshWGAN: Mesh-to-Mesh Wasserstein GAN with Multi-Task Gradient Penalty for 3D Facial Geometric Age Transformation

引用

IEEE Transactions on Visualization and computer Graphics 2024年第8期30卷 4927-4940页

作者： Zhang, Jie Zhou, Kangneng Luximon, Yan Lee, Tong-Yee Li, Ping The Hong Kong Polytechnic University Department of Computing The School of Design Hong Kong University of Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China The Hong Kong Polytechnic University School of Design Hong Kong Laboratory for Artificial Intelligence in Design Hong Kong National Cheng-Kung University Department of Computer Science and Information Engineering Tainan70101 Taiwan

As the metaverse develops rapidly, 3D facial age transformation is attracting increasing attention, which may bring many potential benefits to a wide variety of users, e.g., 3D aging figures creation, 3D facial data augmentation and editing. Compared with 2D methods, 3D face aging is an underexplored problem. To fill this gap, we propose a new mesh-to-mesh Wasserstein generative adversarial network (MeshWGAN) with a multi-task gradient penalty to model a continuous bi-directional 3D facial geometric aging process. To the best of our knowledge, this is the first architecture to achieve 3D facial geometric age transformation via real 3D scans. As previous image-to-image translation methods cannot be directly applied to the 3D facial mesh, which is totally different from 2D images, we built a mesh encoder, decoder, and multi-task discriminator to facilitate mesh-to-mesh transformations. To mitigate the lack of 3D datasets containing children's faces, we collected scans from 765 subjects aged 5-17 in combination with existing 3D face databases, which provided a large training dataset. Experiments have shown that our architecture can predict 3D facial aging geometries with better identity preservation and age closeness compared to 3D trivial baselines. We also demonstrated the advantages of our approach via various 3D face-related graphics applications. © 1995-2012 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Review on Role of IoT and Machine Learning in Agriculture 7

A Review on Role of IoT and Machine Learning in Agriculture

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Kumar, Gulshan Choudhary, Vishal Kumar Kumar, Shravan Kumar, Rajan Kumar, Mukesh Gourshettiwar, Palash M. Faculty of Engineering And Technology Department of Computer Science And Design Maharashtra Wardha India Faculty of Engineering And Technology Department of Computer Science And Medical Engineering Maharashtra Wardha India

ISBN: (纸本)9798350359299

The agricultural area has undergone a significant transformation owing to the progress made in IoT. It is imperative to have a dependable remote monitoring solution right now. This study aims to accomplish two goals. First, a solution based on an app is offered, which effectively assists in remotely administering the field by displaying the current sensor values. In an Internet of Things based prototype surveillance system, a multi-class categorization method utilizing machine learning and deep learning is incorporated to classify labels such as clear farm, cow, horse, wild boar, and wild elephant. The analysis involved Support Vector Machines and Convolutional Neural Networks, with the accuracy measure being employed to determine the optimal model. The advancements in the Internet of Things (IoT) have significantly transformed the daily lives of individuals. A comprehensive understanding of soil properties gives a variety of soil-related information that can be used to improve crop yields. Machine learning is a cutting-edge technology that aids with agricultural precision and provides answers to crop yield issues. Significant informative advances and Machine Learning (ML) open up new opportunities for deciphering, quantifying, and comprehending data-intensive prediction in agricultural settings. This study thoroughly examines a number of machine learning topics for Internet of Things-based smart agriculture systems. © 2024 IEEE.

关键词： Support vector machines

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：