检索结果-内蒙古大学图书馆

7th International Conference on Intelligent Computing and Control Systems, ICICCS 2023

作者： Shirisha, N. Divyajyothi, G. Prashanthi, A. Sowmya, G. MLR Institute of Technology Department of Computer Science & Engineering Hyderabad India Nalla Narasimha Reddy Education Society's Group of Institutions Department of Computer Science & Engineering Hyderabad India MLR Institute of Technology Department of AI&ML Hyderabad India

ISBN: (纸本)9798350397253

The amount of data produced at educational institutions today is growing quickly. It is challenging to analyze the student performance from the vast amount of data using conventional data processing methods. One can quickly analyze the vast amount of data by using big data. Previously, different databases are used for students. So that it takes more time to analyze the performance of a student. By using this application, it takes less time to analyze the data, as it is just like a centralized database where the entire profile of a student is found. In this study, data are analyzed using map-reduce techniques, which is a programming model suitable for processing large amounts of data, and a Hadoop cluster for ease of processing. This helps educational institutions analyze the students' data better and focus on their weak spots. © 2023 IEEE.

关键词： MapReduce

来源：评论

学校读者我要写书评

暂无评论

Forecasting Bitcoin Prices Using Deep Learning for Consumer-Centric Industrial Applications

引用

IEEE Transactions on Consumer Electronics 2024年第1期70卷 1351-1358页

作者： Roy, Pradeep Kumar Kumar, Abhinav Singh, Ashish Sangaiah, Arun Kumar Indian Institute of Information Technology Surat Department of Computer Science and Engineering Surat394190 India Motilal Nehru National Institute of Technology Allahabad Department of Computer Science and Engineering Prayagraj211004 India KIIT Deemed to Be University School of Computer Engineering Bhubaneswar751024 India National Yunlin University of Science and Technology International Graduate Institute of AI Douliou64002 Taiwan Lebanese American University Department of Electrical and Computer Engineering Byblos1102-2801 Lebanon

As cryptocurrencies become more popular as investment vehicles, bitcoin draws interest from businesses, consumers, and computer scientists all across the world. Bitcoin is a computer file stored in digital wallet applications where each transaction is secured using strong cryptographic algorithms. It was challenging to forecast the future price of bitcoin due to its nonlinearity and extreme volatility. Several recent classic parametric models have been found with limited accuracy. To address the limitations and fill the existing research gaps, there is a need for a good prediction model which will provide the desired accuracy in the case of uncertainty and dynamism. This research suggested a deep learning-based framework for predicting and forecasting Bitcoin price. The research will be helpful for worldwide consumers and industries to take their decision on whether to invest or not. The research utilizes Yahoo! finance dataset for the period of 01-03-2016 to 26-02-2021 having 1828 samples. The experimental outcomes of the proposed Long Short-Term Memory (LSTM) model outperformed similar deep learning models by securing minimum loss and confirming that it can be used for future price prediction of the cryptocurrencies, which is helpful for the buyer to take their decision. © 1975-2011 IEEE.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

An Ensemble Approach to Identify Intrusions in Edge IoT and IIoT Networks

An Ensemble Approach to Identify Intrusions in Edge IoT and ...

引用

Communications and Information Technologies (GCCIT), Global Conference on

作者： Vishnu Kurnala Sujith Reddy Kalam Department of Computer Science and Engineering (AI&ML) Vardhaman College of Engineering Hyderabad India

ISBN: (数字)9798350388916

ISBN: (纸本)9798350388923

This work presents an IDS for Internet of Things (IoT) that makes use of the ml-EdgeIIoT-dataset to safeguard critical IoT infrastructures. The proposed model integrates CNN and GRU with an XGBoost layer to enhance predictive accuracy. The CNN-GRU architecture is specifically engineered to effectively capture both spatial and temporal features. The CNN component in this design is tasked with capturing local patterns, whereas the GRU component is responsible for managing sequential dependencies. The results are combined with the initial characteristics and improved using XGBoost to generate the ultimate forecasts. The ensemble approach ensures robust real-time data processing, enabling fast and accurate risk identification. The effectiveness of the Intrusion Detection System (IDS) is evaluated using the four accuracy metrics, demonstrating its outstanding efficiency and resilience across various workloads. This comprehensive architecture prioritizes the security and dependability of the IoT system and is adaptable to evolving cyber threats. Our Intrusion Detection System (IDS) establishes a higher benchmark for taking initiative and adapting to changing circumstances in order to defend IoT networks. It offers robust safeguards to ensure the stability and security of these networks. The study emphasizes the significance of employing sophisticated machine learning methods to enhance the detection capabilities and overall robustness of IDS in Internet of Things (IoT) environments.

关键词： Measurement Accuracy Intrusion detection Predictive models Stability analysis Robustness Real-time systems Security Ensemble learning Resilience

来源：评论

学校读者我要写书评

暂无评论

Next-Gen Human-computer Interaction: A Hybrid LSTM-CNN Model for Superior Adaptive User Experience 3

Next-Gen Human-Computer Interaction: A Hybrid LSTM-CNN Model...

引用

3rd International Conference on Electrical, Electronics, Information and Communication Technologies, ICEEICT 2024

作者： Changala, Ravindra Manoranjini, J. Misba, M. Kakad, Shital Deepthi, S Sai Ponni Valavan, M. Guru Nanak Institutions Technical Campus Department of Computer Science and Engineering Hyderabad India Rajalakshmi Engineering College Department Of Ai&ml Chennai India Tamil Nadu Chennai India Vishwakarma Institute of Technology Department of Ai & Ds Maharashtra Pune India Department It Hyderabad Narsapur India K. Ramakrishnan College of Engineering Department of Ai & Ds Tamil Nadu Trichy India

ISBN: (纸本)9798350369083

In the rapidly evolving landscape of human-computer interaction (HCI), the demand for personalized and adaptive user experiences has grown exponentially. To meet this demand, Research propose a groundbreaking approach leveraging the fusion of Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) architectures. This hybrid LSTM-CNN model is designed to enhance adaptability, responsiveness, and user engagement across various interactive platforms. Traditional HCI models often struggle to effectively capture the dynamic nature of user behavior and preferences. By integrating LSTM and CNN, This model achieves a synergistic blend of temporal and spatial feature extraction capabilities. The LSTM component excels in capturing sequential dependencies and long-term patterns, enabling the system to learn from past interactions and anticipate future user actions. Meanwhile, the CNN component efficiently processes spatial information, extracting meaningful features from multimedia inputs such as images, videos, and text. One of the key strengths of proposed model is its adaptability to diverse user contexts and preferences. Through continuous learning and adaptation, it dynamically adjusts its interface, content, and interaction patterns to match the evolving needs and preferences of individual users. Moreover, the hybrid architecture enables real-time processing of multimodal inputs, facilitating seamless interaction across a wide range of devices and platforms. In experimental evaluations, Hybrid LSTM-CNN model demonstrated superior performance compared to baseline methods in terms of user satisfaction, engagement, and task completion rates. Furthermore, it exhibited robustness and scalability, making it suitable for deployment in real-world applications across domains such as e-commerce, entertainment, education, and healthcare. In summary, The proposed approach represents a significant advancement in HCI research, paving the way for next-generation interactiv

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Intelligent Application for Dog Emotion Detection using EfficientNet-B0

Intelligent Application for Dog Emotion Detection using Effi...

引用

International Conference on Computing Communication Control and Automation (ICCUBEA)

作者： Pradnya Narkhede Anuradha Thakare Sakshi Shitole Ayush Dongardive Vrushali Guldagad Department of Computer science and Engineering(AI&ML) Pimpri Chinchwad College of Engineering Pune

ISBN: (数字)9798350391770

ISBN: (纸本)9798350391787

The present research paper introduces an innovative methodology for classifying canine emotions by employing the EfficientNet-B0 algorithm. The recognition of emotions by animals, specifically canines, is a crucial factor in comprehending their conduct and improving the quality of human-animal relationships. This research study addresses the task of precise dog emotion recognition, like happy, sad, angry, relaxed. In this study, the model, fine-tuned, is used to cover different emotions in dogs and has a classification accuracy of 89%, thus showing its potential to recognize emotions like anger, happiness, relaxation and sadness among dogs. The Efficient net- B0 model is meticulously trained on an augmented dataset known as Stanford’s Dog Emotion dataset, which consists of images of dogs with labels indicating their emotional state: angry, happy, relaxed, or sad. Metrics that show constant performance, such as accuracy, loss, AUC, and precision when viewed visually, show consistent performance. According to the data, EfficientNet-B0 is good at correctly detecting dogs' emotions, which could be useful in veterinary care, animal behavior research, and studies of how people interact with animals.

关键词： Training Measurement Deep learning Emotion recognition Accuracy Computational modeling Dogs Medical services Feature extraction Planning

来源：评论

学校读者我要写书评

暂无评论

Unmasking Deep Fakes: Detecting Low-Quality Forgeries through Unseen Artifacts

Unmasking Deep Fakes: Detecting Low-Quality Forgeries throug...

引用

Electronics and Sustainable Communication Systems (ICESC), 2020 International Conference on

作者： M. Venkateshwarlu M. Yashaswi Dhanya Shah R. Akash Reddy Department of Computer Science and Engineering(AI & ML) Vignan Institute of Technology and Science Nalgonda Telangana

ISBN: (数字)9798350379945

ISBN: (纸本)9798350379952

The spread of deepfakee-technology is a danger to the veracity of multimedia material, since it may be used to manipulate people's identities or spread false information. Low-quality forgeries continue to be difficult to detect because of their subtle artifacts, which elude traditional detection approaches. This is true even while deep fake detection algorithms have made significant progress in identifying high-quality forgeries. This research work presents a unique method for identifying hidden elements in low-quality forgeries, which may be used to uncover deep fakes. The proposed approach, which makes use of sophisticated machine learning algorithms and computer vision techniques, is centred on locating and taking advantage of distinctive artifacts that are introduced throughout the deep fake production process. This study provides a thorough analysis of these artefacts and show how well they can distinguish between real multimedia material and poor-quality deep fakes. The proposed technique is effective in properly detecting low-quality forgeries of photos, videos, and audio recordings. These findings are based on experiments conducted on a variety of datasets. Additionally, the proposed method's resilience is assessed against the cutting-edge deep fake creation techniques and emphasize its practical benefits in preventing the distribution of false information.

关键词： Deepfakes computer vision Machine learning algorithms Communication systems Neural networks Production Streaming media Forgery Detection algorithms Resilience

来源：评论

学校读者我要写书评

暂无评论

Dynamic and Energy-Efficient Resource Allocation using Bat Optimization in 5G Cloud Radio Access Networks 2

Dynamic and Energy-Efficient Resource Allocation using Bat O...

引用

2nd IEEE International Conference on Networks, Multimedia and Information Technology, NMITCON 2024

作者： Padmakala, S. Al-Farouni, Mohammed Rao, Deepak Dasaratha Saritha, Kambhampati Puneeth, R.P. Saveetha Institute of Medical And Technical Sciences Saveetha University Saveetha School of Engineering Department of Computer Science And Engineering Chennai India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq Indian Institute of Technology Patna India Gokaraju Rangaraju Institute of Engineering and Technology Department of Ai & Ml Hyderabad Bachupally India Department of Computer Science and Engineering Karnataka India

ISBN: (纸本)9798350372892

G networks represent the fifth iteration of cellular networks, thus aimed at resolving the challenges and constraints faced by the preceding 4G network. Cloud Radio Access Networks (CRAN) provides economical and EnergyEfficient (EE) solutions customized to the requirements of 5G networks. This research proposes an energy-efficient CRAN that automatically allocates Baseband Unit (BBU) resources to Remote Radio Unit (RRHs) based on traffic, increasing network throughput as well as reducing power usage. Bat Optimization Algorithm (BOA) is a Swarm Intelligence (SI) approach used to optimize Resource Allocation (RA) in CRAN by mapping BBURRHs. Through controlling the BBU's mode based on resource utilization, this research minimizes the Power Consumption (PC) in 5G CRAN. Moreover, the findings revealed that the proposed BOA-CRAN reduced the power usage upto 95% when compared to existing methods such as 5G CRAN, Green-RAN while increasing BBU efficiency. © 2024 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Adaptive residual convolutional neural network for moiré image restoration

引用

International Journal of Information Technology (Singapore) 2025年第2期17卷 783-791页

作者： Malagi, Vindhya P. Naresh, E. Mithra, C. Suresh, B. V. N. V. Krishna Department of AI & amp ML Dayananda Sagar College of Engineering Bengaluru India Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of Computer Science and Engineering School of Computing Vel Tech Rangarajan Dr. Sagunthala R & amp D Institute of Science and Technology Chennai 600062 India Computer Science & amp Engineering KLEF KL University Andhra Pradesh Vaddeswaram India

Restoring Moiré images presents significant challenges due to the complex interference patterns that obscure image details. These patterns often degrade the quality of images, making accurate restoration crucial for various applications. Effective Moiré image restoration requires advanced techniques to overcome the difficulties posed by these intricate artifacts. This study introduces an Adaptive Residual Convolutional Neural Network (RCNN) for Moiré image restoration, augmented with the Zebra Optimization Algorithm (ZOA) to enhance both feature extraction and restoration accuracy. The hybrid model leverages ZOA's capability to balance exploration and exploitation, optimizing network parameters to improve learning efficiency. Tested on the DIV2K dataset, this approach demonstrates significant improvements in handling complex Moiré patterns, as evidenced by enhanced Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) values. © The Author(s) 2024.

关键词： Adaptive residual convolutional neural network Moiré images Peak signal-to-noise ratio Structural similarity index measure Zebra optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Sorting Algorithms: Time Complexity and Practical Applications

Comparative Analysis of Sorting Algorithms: Time Complexity ...

引用

Intelligent Data Communication Technologies and Internet of Things (IDCIoT), International Conference on

作者： Manish Rai Hemlata Parmar Suhani Sharma Department of Computer Science and Engineering(AI&ML) Manipal University Jaipur Jaipur India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527556

In the field of computer science, sorting algorithms are crucial because they facilitate the effective processing and arrangement of data in a variety of scenarios, including data analysis, searching, and optimal system operation. The objective of this study is to look at and compare different sorting algorithms to see how well they work and how useful they are in different situations. The study tests popular sorting algorithms like Quick Sort, Merge Sort, and Bubble Sort on different input sizes, types of data (sorted, reversed, and random), and how they are implemented in the C++ programming language. The study shows how they work in terms of time complexity, resource use, and real applications through a systematic analysis. The most important results show that algorithms work differently depending on the inputs. For example, Quick Sort does better in most situations, while Merge Sort stays stable in the worst ones. This work also finds situations where simpler algorithms, like Bubble Sort, are good for small data sets. This paper is unique because it gives real-life cases, suggestions for choosing the best algorithm based on specific needs, and suggestions for how to do that. The goal of these results is to help programmers, teachers, and experts pick the right sorting algorithms for their computer tasks.

关键词： Machine learning algorithms Data analysis Systematics Systems operation Instruction sets Machine learning Internet of Things Time complexity Optimization Sorting

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning in Endoscopic Imaging: A Machine Vision Approach to GIT Disease Identification

Transfer Learning in Endoscopic Imaging: A Machine Vision Ap...

引用

Communications and computer science (InCCCS), International Conference on

作者： Jayavrinda Vrindavanam Pradeep Kumar Gaurav Kamath Abhilash S Bharadwaj Department of Computer Science and Engineering(AI & ML) Dayananda Sagar University Bengaluru India

ISBN: (数字)9798350358858

ISBN: (纸本)9798350358865

In the context of rapidly rising Gastro-Intestinal tract related diseases among the population, the study explores the use of ai and ml that can enable early detection of the GI tract related abnormalities. The study after a detailed review of the existing studies, proposes on transfer learning to fine tune model weights trained on large data sets for GI-tract applications. The study has implemented models such as EfficientNet, MobileNet V3 Large, ResNet-50, DenseNet-201 and CNN (Convolutional Neural Network) on the endoscopic images. The top performing model, EfifcientNet2S, showcased superior proficiency identifying the eight distinct GIT diseases. The paper highlights the scope of applying transfer learning neural network architectures in enhancing disease diagnosis as well as selecting optimal architectures for accurate and efficient medical image classification in gastrointestinal pathology.

关键词： Pathology Transfer learning Neural networks computer architecture Gastrointestinal tract Medical diagnosis Convolutional neural networks

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：