检索结果-内蒙古大学图书馆

15th International Conference on Computing Communication and Networking technologies, ICCCNT 2024

作者： Geetha Jenifel, M. Anita Jasmine, r. Umanandhini, d. Srm Institute of Science and Technology Data Science and Business Systems KTR Campus Chengalpattu India Vel Tech Rangarajan Dr. Shagunthala R&d Institute of Science and Technology India

ISBN: (纸本)9798350370249

Cryptocurrency markets, exemplified by the notable volatility in Bitcoin prices, have become pivotal arenas for financial exploration and investment. In response to this, our research undertakes a comprehensive comparison of diverse machine-learning models to predict Bitcoin prices. The models scrutinized include Linear regression, ridge regression, decision Tree, random Forest, Support Vector Machine (SVM), K-nearest neighbors (KNN), and Neural Networks. This study evaluates and contrasts these models based on performance metrics such as Mean Absolute Error (MAE), Mean Squared Error (MSE), and r -squared. This work encompasses the collection and preprocessing of historical Bitcoin price data, the engineering of pertinent features, and the division of the dataset into training and test sets. Each machine learning model is meticulously trained on the training set, allowing for the tuning of hyperparameters to optimize predictive capabilities. Subsequently, the models' performance is systematically assessed on the test set, providing valuable insights into their accuracy and reliability. The scope of this research is delimited by a specific timeframe, focusing on historical Bitcoin price data up to 15/11/2023. By addressing these objectives, this research aspires to guide investors, researchers, and analysts in navigating the intricate landscape of cryptocurrency investment decisions. The findings contribute to an enhanced understanding of the nuanced strengths and limitations inherent in different machine learning models when applied to the volatile context of Bitcoin price prediction. Ultimately, this research aims to facilitate more informed and strategic decision-making processes in the cryptocurrency market. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

3d printing with natural fiber composites: a review for advanced manufacturing applications

引用

Interactions 2024年第1期245卷 1-12页

作者： Karthik, K. Kolappan, S. ramesh, V. Muthukumarasamy, S. Department of Mechanical Engineering Vel Tech Rangarajan Dr.Sagunthala R & ampD Institute of Science and Technology Tamil Nadu Chennai600062 India

3d printing has transformed manufacturing by enabling the creation of complex shapes with high precision and minimal material waste. However, the widespread use of non-renewable, petroleum-based plastics in 3d printing raises environmental concerns due to their non-biodegradability and high carbon emissions. The use of natural fiber composites, combining natural fibers like hemp, flax, jute, and sisal with bio polymers or other sustainable matrix materials, has emerged as a more eco-friendly alternative offering strength, light weight, and sustainability. This article explores the viability of using these natural fiber composites for various 3d printing techniques such as fused deposition modeling, direct ink writing, and stereo lithography. It analyzes the strengths and limitations of each method for fabricating natural fiber composite parts. Potential applications span industries like automotive, aerospace, construction, and consumer goods, where these materials can serve as environmentally-friendly replacements for traditional plastics. The environmental and economic benefits of 3d printing with natural fiber composites are highlighted, including lower emissions, utilization of renewable resources, and support for local economies. While challenges like moisture sensitivity, uneven fiber distribution, and limited bio polymer choices are acknowledged, the article underscores the urgent need for further research to improve the functionality and print ability of these materials. Integrating natural fiber composites into 3d printing represents a significant stride towards sustainable manufacturing, presenting an opportunity to minimize environmental impact while producing high-performance components across diverse industries. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Hemp fibers

来源：评论

学校读者我要写书评

暂无评论

NMF based Speech Enhancement using CNN 15

NMF based Speech Enhancement using CNN

引用

15th International Conference on Advances in Computing, Control, and Telecommunication technologies, ACT 2024

作者： Jessintha, d. Palas, P. Bini Berakhah, F. Stanley Kumar, r. Jeen retna Easwari Engineering College Department of Electronics and Communication Engineering Chennai India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Computer Science Engineering Chennai India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Electronics and Communication Engineering Chennai India

ISBN: (纸本)9798331300579

Convolutional Neural Networks (CNNs), are adept at learning complex patterns in data and can effectively denoise speech signals by mapping noisy spectrograms to clean ones. NMF, on the other hand, is a signal processing technique that can decompose a spectrogram into additive components, including a noise profile. By estimating the noise profile from the noisy speech spectrogram, NMF enables the separation of noise from the desired signal. Combining deep learning with NMF leverages the strengths of both approaches, allowing for robust and efficient speech enhancement even in challenging noisy environments. First, noisy and clean speech samples are loaded and pre-processed, including trimming or padding to a fixed length and computing magnitude spectrograms. A CNN-based deep learning model is then defined and compiled, with two convolutional layers for feature extraction from input spectrograms followed by dropout layers for regularization. This model is trained using the noisy spectrograms as input and their corresponding clean spectrograms as target output. Meanwhile, NMF is applied to estimate the noise profile from the magnitude spectrogram of the noisy speech signal, separating noise from the signal. Finally, the trained model is used to denoise the spectrogram, and the enhanced audio is reconstructed and saved. This approach combines the strengths of CNNs for learning complex mappings and NMF for noise estimation, resulting in improved speech enhancement performance. © Grenze Scientific Society, 2024.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Green Information Centric Networking for Future Wireless Communications

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile technologies 2024年第23期18卷 149-158页

作者： Girirajan, S. Vinoth Kumar, S. Karthick, M. Saju raj, T. Ponnaian, Geetha Department of Computing Technologies School of Computing SRM Institute of Science and Technology Kattankulathur Tamil Nadu India Department of CSE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Tamil Nadu Chennai India Department of Computer Science and Engineering Nandha College of Technology Tamil Nadu Erode India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Tamil Nadu Chennai India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Tamil Nadu Chennai India

Energy-efficient green information-centric networking (EEGICN) is proposed in this paper for advancing future wireless communication networks by addressing the challenge of energy consumption. This model can adapt the power consumption of network nodes to optimized values according to the associated link utilization. The model aimed to reduce energy consumption and increase network performance and stability. The EEGICN model incorporates efficient routing mechanisms, content caching strategies, and energy-intelligent communication protocols to improve resource utilization across the network infrastructure. EEGICN minimizes large data transmission, reduces power consumption, and reduces network congestion. Popular resources are cached in key network locations, and proximity data is exchanged to achieve this. The model also includes dynamic power management algorithms that adapt to changing traffic demand and network conditions to provide consistent performance across a variety of operational scenarios. In comparison to current wireless network systems that employ various forms of cache, the evaluation findings demonstrated that EEGICN can increase network efficiency by dramatically lowering the number of hops and energy consumption. Future networks may find this application to be a quick and easy way to transmit content. © 2024 by the authors of this article.

关键词： energy efficiency (EE) future wireless communications green information-centric networking information-centric networking (ICN) wireless network

来源：评论

学校读者我要写书评

暂无评论

Suicidal risk Prediction Using Catboost Classifier: A Comparative Study of Six Machine Learning Classifiers 1

Suicidal Risk Prediction Using Catboost Classifier: A Compar...

引用

1st International Conference for Women in Computing, InCoWoCo 2024

作者： Prasher, Shikha Nelson, Leema Pappa, Kanmani Chitkara University Institute of Engineering & Technology Punjab India Vel Tech Rangarajan R&D Institute of Science and Technology Department of Electronics and Communication Engineering Chennai India

ISBN: (纸本)9798331518943

This study employs machine learning classifiers, including Logistic regression, random Forest Classifier, Extra Trees Classifier, XGB Classifier, LGBM Classifier, and CatBoost Classifier, to predict suicidal mental health. By employing a thorough methodology, this research endeavours to ascertain the classifier that is most efficient in performing this crucial duty. CatBoost Classifier demonstrated superior performance among the classifiers that were assessed, attaining a training accuracy of 84% and a testing accuracy of 73%. The findings highlight the effectiveness of the classifier in reliably differentiating between cases of depression and Suicide, showcasing its potential usefulness in initiatives aimed at preventing suicide. Although there was a marginal decline in test accuracy when compared to the accuracy achieved during training, the CatBoost Classifier still exhibited robust predictive capabilities, underscoring its dependability in practical situations. The results of this research make a valuable contribution to the field of mental health predictive modelling and underscore the criticality of employing machine learning methods in the realm of suicide prevention. Additional investigation is necessary in order to verify the CatBoost Classifier's scalability and efficacy across a wide range of populations and contexts. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

VLSI Architecture for Modulating Nerve Activity in Parkinson's disease Using STFT Transformation Methods 11

VLSI Architecture for Modulating Nerve Activity in Parkinson...

引用

11th International Conference on Bio Signals, Images, and Instrumentation, ICBSII 2025

作者： Karthick, S. devarasu, Neelamegam Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai India

ISBN: (纸本)9798331513863

The progressive neurodegenerative condition known as Parkinson's disease (Pd) mostly impairs motor control and appears as bradykinesia, stiffness, and tremors. The abnormal neural activity that underlies these symptoms is frequently not sufficiently treated by existing medicines, despite tremendous advancements in therapy. It could render traditional signal processing methods unsuitable for continuous, long-term use in implanted or wearable medical devices. The research suggests a novel VLSI (Very Large-Scale Integration) design that uses Short-Time Fourier Transform (STFT) transformation techniques to modulate neural activity in Pd. To analyze and modify nerve activity, it makes use of a dataset of electroencephalogram (EEG) signals that show neural activity in Pd patients. The dataset includes time-series data and time-frequency characteristics. A band-pass filter was used to preprocess the EEG data in order to eliminate noise and unnecessary frequencies, maintaining the emphasis on the pertinent neural activity. The STFT was then used to extract features, which produced time-frequency representations that capture the EEG signals' phase and amplitude information for additional examination. A Convolutional Neural Network (CNN) is used to determine if a person has Pd or not. The CNN uses its capacity to identify intricate patterns to interpret the retrieved STFT characteristics from the EEG data and make precise predictions. The performance for the proposed method is analyzed by accuracy, throughput, latency, and power consumption. The technology can precisely detect and alter the oscillatory patterns linked to Pd by applying STFT+CNN to neural signals, thereby providing a way to implement more individualized and successful treatment approaches. © 2025 IEEE.

关键词： Convolutional Neural Network (CNN) Electroencephalogram (EEG) Parkinson's disease (Pd) Short-Time Fourier Transform (STFT) Very Large-Scale Integration) (VLSI)

来源：评论

学校读者我要写书评

暂无评论

An Improved Multiscale Faster r-CNN Based Lung Cancer detection System

An Improved Multiscale Faster R-CNN Based Lung Cancer Detect...

引用

2024 International Conference on System, Computation, Automation and Networking, ICSCAN 2024

作者： Arikaran, N. Sathishkumar, r. Poojitha, B. dharanya, S. Kanchana, M. Mohamed Appa, M.A.Y Peer Manakula Vinayagar Institute of Technology Department of Computer Science and Engineering Puducherry India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India

ISBN: (纸本)9798331510022

Lung cancer is a leading cause of cancer-related deaths, making early and accurate detection crucial. This project develops an automated detection system using Convolutional Neural Networks (CNN) to improve the identification of malignant nodules in lung CT scans. The process involves collecting a large dataset from public repositories, followed by preprocessing steps like normalization and augmentation to enhance input quality. The CNN architecture is designed to capture complex features of lung nodules, with training on expertly annotated data. techniques such as dropout and batch normalization are used to prevent overfitting. The model's performance is evaluated using metrics like accuracy and rOC curve analysis, showing significant improvement over traditional methods. The findings suggest that CNNs offer a promising approach to early and accurate lung cancer detection, with potential for clinical application and future integration with other diagnostic tools. At the stage of diagnosis our major aim is to reach the higher level accuracy and efficiency. The improved model, based on lung cancer increases the performance, by combining the properties of various network structures. The proposed model achieved 96.2 % ACC, 94.7% Spec, 93.5% recall, 98% Prec, and 98.5 % F1-Score. In addition to helping medical professionals with patient care and monitoring, the enhanced model may more accurately detect lung cancer, lower the possibility of incorrect and delayed diagnoses resulting from physician personal reasons, and enhance the overall evaluation and treatment process. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

review: Machine Learning based Lung diseases Classification by Using Chest X-ray Image

Review: Machine Learning based Lung Diseases Classification ...

引用

2025 International Conference on Visual Analytics and data Visualization, ICVAdV 2025

作者： Imam Basha, S.K. Jana, S. Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Ece Tamil Nadu Chennai600 062 India

ISBN: (纸本)9798331521394

Lung disorders are quite harmful, especially in an emerging and low-income countries where the millions of people were exposed to the air pollution and live in poverty. According to World Health Organization (WHO), indoor air pollution-related diseases like pneumonia and asthma result in over four million avoidable deaths annually. With diseases including pneumonia, TB, lung-cancer, & COVId-19 contributing to high rates of morbidity and mortality, lung diseases continue to pose a serious threat to world health. Chest X-rays (CXrs) are among the most popular and economical imaging modalities, and traditional diagnostic approaches frequently depend on clinical evaluations and imaging procedures. New approaches to increasing the precision and effectiveness of lung disease classification using CXr image have been made possible by recent developments in machine learning (ML) and deep learning (dL). This paper examines current advancements for common lung disorders, the use of imaging modalities, and machine learning models. Additionally, the study investigates a number of publicly accessible datasets that are utilized for well-known lung conditions. © 2025 IEEE.

关键词： Indoor air pollution

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of a High-Frequency PLL with a 20.70 GHz VCO and Low-Phase Noise 8

Performance Evaluation of a High-Frequency PLL with a 20.70 ...

引用

8th International Conference on Electronics, Communication and Aerospace technology, ICECA 2024

作者： Shiyamala, S. Priya, P.A. Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology School of Electrical and Communication Avadi Chennai600062 India

ISBN: (纸本)9798350367904

The evaluation of the performance of a Phase-Locked Loop (PLL) proposed to produce a Voltage-Controlled Oscillator (VCO) frequency of 20.70 GHz is presented in this paper. Phase noise measurements at a 1 MHz offset from the carrier frequency show a final phase noise of - 1 05.50 ~ d B c / H z. The system's Figure of Merit (FOM), which shows how well the PLL performs in terms of phase noise to power consumption, is -38.38 dBc / Hz at an offset of 100 kHz and -108.51 dBc / Hz at an offset of 1 MHz. The results presented emphasize the PLL's applicability for high-frequency applications where low-phase noise and high-frequency. © 2024 IEEE.

关键词： Phase locked loops

来源：评论

学校读者我要写书评

暂无评论

An experimental study of abrasive waterjet deep hole drilling on Inconel 718

引用

Materials Today: Proceedings 2023年 92卷 92-97页

作者： rathinasuriyan C. Bharani Chandar J. Siva r. Vijayan r. Department of Mechanical Engineering Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology Avadi Chennai-62 India Department of English Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai-62 India Department of Mechanical Engineering Chennai Institute of Technology Kundrathur Chennai India

Inconel 718 is the most dominant alloy to manufacture 50% of aerospace components due to its excellent oxidation resistance, and good corrosion and erosion resistance across a wide range of temperatures. These aerospace components require small and micro-holes with high aspect ratios for specific functions. Among all the modern manufacturing processes, Abrasive Waterjet Machining (AWJM) is gaining popularity to produce such holes with its superior potential to machine all kinds of materials in the absence of heat and with minimum damage to the work surfaces. This research work attempted to study the output responses, namely material removal rate, kerf geometry, and surface roughness viz constant water pressure, varied Stand-Off distance (SOd), and Abrasive Mass Flow rate (AMFr). This research reveals that AWJM has excellent potential to make deep holes on Inconel 718 with the following outcomes; the material removal rate has been increased with increased mass flow rate and the kerf angle and surface roughness of the drilled holes have been decreased with the increased mass flow rate. © 2023

关键词： Abrasive Waterjet Machining (AWJM) Kerf geometry Material removal rate (Mrr) Superalloy

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：