检索结果-内蒙古大学图书馆

Improved AI-Generated Multitrack Music with Variational Autoencoders (VAE) for Harmonious Balance Compared to Recurrent Neural Network for Coherence 4

Improved AI-Generated Multitrack Music with Variational Auto...

引用

4th International Conference on Advancement in Electronics and Communication engineering, AECE 2024

作者： Naveen Kumar, R. Surendran, R. Sumathy, K. Saveetha Institution of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Saveetha Institution of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science Engineering Chennai India

ISBN: (数字)9798350364729

ISBN: (纸本)9798350364729

This paper, therefore, proposes the application of the VAEs in enhancing the coherence and the alignment of the multiple track music AI-sync'd above. In our case, we want to take advantage of the feature of VAEs in modelling the complex data distribution. This will help create models that are indeed synthetic in the interconnectivity of the musical aspects. As for the evaluation, our method is designed for the assessment of the methodology of music generation, thus we compare the suggested approach with the baselines, namely, Variational Auto Encoders and Recurrent Neural Networks. The studies that have been discussed above help in a number of ways to AI music generation from the given VAE instrument through an understanding of a capacity to create aesthetically appealing and intricate music. The two high-level algorithmic methodologies were employed on 20 samples but from LPD dataset hence arriving at a total of 40 samples. The first priority used was CAO with reference to the structural integration and suitability of individual musical tracks. The findings that have been established in this paper reveal that a new model which has been developed known as VAE is a better model of synthesizing logical multitrack music compared to the RNN. © 2024 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Predictive Maintenance for Industrial Equipment Optimization 2

Machine Learning-Based Predictive Maintenance for Industrial...

引用

2nd IEEE International Conference on Trends in Quantum Computing and Emerging Business Technologies, TQCEBT 2024

作者： Narayanan, Lakshmi Kanthan Loganayagi, S. Hemavathi, R. Jayalakshmi, D. Vimal, V.R. Saveetha Institute of Medical and Technical Sciences Simats Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Saveetha University Saveetha School of Engineering Department of Cse Thandalam Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Thandalam Chennai India

ISBN: (纸本)9798350384277

Industrial equipment optimization is crucial for industries that want to improve operating efficiency, reduce downtime, and cut maintenance costs. Predictive maintenance is a major strategy to achieving these goals, since it uses advanced data analytics and machine learning techniques to foresee equipment breakdowns and schedule maintenance in advance. This research investigates the use of machine learning-based predictive maintenance in the industrial sector. It discusses the approach for gathering and preprocessing data from various sensors and equipment logs, as well as the critical step of feature engineering to extract useful insights from the data. The selection of relevant machine learning algorithms and the model training method are thoroughly explored. Furthermore, the research emphasizes the importance of anomaly detection approaches in early failure detection, allowing for timely interventions to avoid equipment breakdowns. This research focuses on the creation of predictive maintenance models that estimate equipment's remaining useful life (RUL). The selection of thresholds for maintenance operations based on RUL projections is examined, with the goal of balancing cost-effectiveness and equipment reliability. The report underlines the need of continual monitoring and feedback loops in the real-time implementation of predictive maintenance systems, which will drive continued optimization. Real-world case studies demonstrate the usefulness of predictive maintenance in industrial equipment optimization, resulting in significant cost savings and improved equipment reliability. Challenges and future possibilities in this subject are also discussed, emphasizing the importance of scalable and explainable AI solutions. © 2024 IEEE.

关键词： Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale CNN Architectures for Enhanced Feature Extraction in Image Sentiment Analysis 3

Multi-Scale CNN Architectures for Enhanced Feature Extractio...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Indhumathi, S. Fernandez, F. Mary Harin Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331509675

Imagery sentiment analysis is a complex task, the aim of which is the interpretation of both local and global visual signs in order to correctly classify the emotions ordered by the image. CNNs old architectures commonly have trouble with the proper balance of the tip-oriented extraction and the overall understanding of the context. This research suggests a new multi-scale CNN architecture in order to improve the extraction of features by the hierarchical representations of the visual sentiment cues. The architecture operates by adding convolutional layers of nucleotide scale and pyramid pooling modules to take features from different spatial resolutions. Besides, the attention mechanism is applied to the sentimental areas, thus dealing with the noise from unimportant parts. That is modeling a CNN with multi-scale convolutional layers in the construction of an image where each kernel size will deliver what is a fine signal versus a contextual pattern. A pooling module based on a pyramid structure is collected to the resolution to obtain features from different spatial scales, so the model will have the view of the entire image at a context level. Then, in addition, the proposed attention mechanism that finds and highlights regions with more probability of emotional content is used. The suggested architecture is prepared and tested on a number of datasets, that reflect the real-world sentiment contexts and the evaluation metrics like accuracy, precision, recall, and F1-score, which show the effectiveness of the proposed architecture. The proposed approach seeks to give a more in-depth definition of visual sentiment which, in turn, will lead to more precise classification as well as allow for better understanding with attention-based visualizations. The results are anticipated to drive the image sentiment analysis field further, making it relevant for social media analytics, advertising, and human-computer interaction. © 2025 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Enhancing E-Commerce Predictive Analytics using Ensemble Models for Consumer Behaviour and Market Forecasting 1

Enhancing E-Commerce Predictive Analytics using Ensemble Mod...

引用

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Balaji, S. Manikavelan, D. Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331529246

Predictive analytics is becoming more and more crucial in the fast-changing e-commerce sector, which helps businesses predict consumer behavior, enhance marketing, and optimize operational efficiency. This project aims to improve predictive analytics in e-commerce using machine learning techniques. AI is a fast-developing field that plays a significant role in data analysis and forecasting, allowing businesses to make informed decisions. The research utilizes algorithmic learning that involves ensemble models such as Kernel Support Vector Machine, Kernel Principal Component Analysis, and a Mentor-Learner based Optimization model. The main aim is to understand the potential growth and prospects of online shopping in the future. To achieve this, secondary data on ecommerce valuation was analyzed to generate revenue insights and understand online customer behavior better. Then, Python was applied to predict the sector's contribution from 2024 to 2026. The study also incorporates factors such as the proportion of Indian online consumers and e-commerce revenue to improve market price prediction accuracy. By combining academic research with industry practices, this paper offers valuable recommendations for online shopping managers and executives seeking to implement neural networks for analytical forecasting. The MAPE for KPCA-SVM-MLBO was 0.189%, significantly lower than the MAPE values of 0.769% and 0.547% for PCA-SVM-PSO and SVM-MLBO, respectively. © 2025 IEEE.

关键词： Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

Detection of Brain Stroke by using the Novel Adaboost Classifier Algorithm Classifier Algorithm Compared with Multi-layer Perceptron

Detection of Brain Stroke by using the Novel Adaboost Classi...

引用

2024 IEEE Wireless Antenna and Microwave Symposium, WAMS 2024

作者： Manikanta, P. Kannan, K. Nattar Padmakala, S. Saveetha School of Engineering SIMATS Department of Computer Science and Engineering Saveetha University Chennai India

ISBN: (纸本)9798350358926

Compare Novel Adaboost Classifier Algorithm and MultiLayer Perceptron to improve accuracy. Materials and Methods: Research groups include Novel Adaboost Classifier Algorithm and MultiLayer Perceptron. The 64.4 MB dataset includes 30 healthy and 30 damaged brain images. Kaggle provided CT images for brain stroke detection. Identifying the training dataset requires 500 records-80% for training and 20% for testing. A unique Adaboost method and a multilayer perceptron approach were compared using 10 sets to improve research accuracy. Ten times per iteration, twenty sets were compared. The G power test with α=0.05 and β=0.2 yields approximately 80%. A novel Adaboost classifier algorithm (88.84%) beats MultiLayer Perceptron (83.40%). The independent sample test value is significant at 0.01 (p © 2024 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Texture- and Symptom-Based Coffee Leaf Disease Classification Using CNN and ResNet algorithms 4

Texture- and Symptom-Based Coffee Leaf Disease Classificatio...

引用

4th International Conference on Advancement in Electronics and Communication engineering, AECE 2024

作者： Surendran, R. Sree, C. Pranitha Sumathy, K. Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Saveetha Institution of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science Engineering Chennai India

ISBN: (纸本)9798350364729

This work aims to improve plant disease prediction through the implementation of an intriguing and revolutionary model that combines refined algorithms for machine learning with predictive analytics strategies. The goal is to strengthen utilities' resilience by providing precise and trustworthy forecasts of the potential classification of diseases. This study aims to push the limits of present prediction skills, analyze cutting-edge technology, and test unique features to improve the accuracy and timeliness of plant pathogen prophecies significantly. The ultimate goal in a rapidly evolving technological environment is to contribute to the development of proactive and effective mitigation techniques that reduce the impact of electrical glitches on equipment, infrastructure, and system-wide consistency. Materials required: The core database for the present investigation was obtained from the reputable data-gathering and analytics website Kaggle. The dataset includes a wide range of line voltages and currents for various failure scenarios. In Group 1, the convolutional neural network approach was applied. The statistical power of the 48 sample sizes utilized in the study was 0.8, the alpha value was 0.05, and the beta value was 0.2. ResNet is used by Group 2. Clinical is the method used to compute these figures. To run the accurate prediction software, Google Colab is employed. It analyzes data and displays accuracy as a percentage and in a graphical format for simple interpretation. Result: The convolutional neural network technique yielded an accuracy of 78.65% percent for Group 1, while the ResNet strategy yielded an accuracy of 70.61% for Group 2. SPSS data analysis program is employed for data set statistical analysis and correctness. A two-tailed test is used to appraise to what extent there is a statistically significant discrepancy in accuracy between both sets of data. Conclusion: Convolutional neural networks are more accurate than ResNet algorithms. © 2024 I

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Real Time Vehicle Collision Detection with Alert System 6th

Real Time Vehicle Collision Detection with Alert System

引用

6th International Conference on Information Systems and Management science, ISMS 2023

作者： Jobirin, S. Akshith Nagappan, G. Department of Computer Science and Engineering Saveetha Engineering College Saveetha Nagar Chennai602105 India

ISBN: (纸本)9783031664090

"Accident detection is an essential application in intelligent transportation systems for the safety of drivers and passengers. In recent years, deep learning-based object detection models have been leveraged to achieve significant improvements in real-time object detection. YOLO (You Only Look Once) stands out as one of these models due to its real-time performance and high accuracy. In this paper, we propose an accident detection system using YOLOv5, a state-of-the-art version of YOLO. The system is designed to detect three types of accidents, namely vehicle rollover, rear-end collision, and head-on collision. We have employed a pre-trained YOLOv5 model, initially trained on the COCO dataset, and fine-tuned it using a custom dataset of accident images. The proposed system achieves an average precision of 0.94 for vehicle rollover detection, 0.93 for rear-end collision detection, and 0.92 for head-on collision detection. It also demonstrates promising real-time performance, with an average processing time of 0.03 s per frame on an NVIDIA GeForce GTX 1080 Ti GPU. This system can be seamlessly integrated into intelligent transportation systems to provide real-time accident detection and alerting, significantly enhancing the safety of drivers and passengers on the road." © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Dynamic Crowd Modeling and Anomalous Behavior Prediction Using GMM and Time Series Analysis in Real-Time Smart City Environment 4

Dynamic Crowd Modeling and Anomalous Behavior Prediction Usi...

引用

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

作者： Kanchana, R. Fernandez, F. Mary Harin Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331523923

The Research Concentrates on simulating and investigating dynamic crowd using Gaussian Mixture Models (GMM) and synthetic time-series data in real time smart city environments. A novel approach generates and designs various crowd behaviors, incorporating normal flow, high congestions, and erratic patterns, leveling to detect and predict anomalies that pose safety issues. Mock datasets, imitating real-world situations, are generated using spatial-temporal features such as crowd density, velocity, and movement direction. To cluster these behaviors into distinct operational states, the GMM is employed, while irregularities are recognized as outliers to the learned distributions. The simulation framework introduces temporal tendencies and real-time capabilities, aiding dynamic variance detection and proactive crowd organization. Investigational results prove the efficiency of the proposed approach in clustering behavioral states and detecting anomalies, providing a scalable and computationally efficient result for inner-city protection and resource optimization. The study implements a foundation for deploying real-time crowd monitoring systems in smart cities, addressing challenges in occasion management, transportation, and disaster awareness. © 2025 IEEE.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Review of Web Page Ranking Systems 18

A Comprehensive Review of Web Page Ranking Systems

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Shaffi, S. Samsudeen Jagadeesh, S. Alleema, N. Noor Mahesh, C. Umanesan, R. Muthulakshmi, I. Pet Engineering College Department of Computer Science and Engineering Tirunelveli India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Aiml Chennai India V v College of Engineering Department of Computer Science and Engineering Tuticorin India

ISBN: (纸本)9789380544519

Presently, the majority of people using internet usage in their daily lives There wouldn't be anything on the internet without the existence of the web. On the web the most common thing is searching or querying by the user then it fetches or retrieves the data from various web pages. These web pages produce both material and immaterial data based on the search engine ranking results. In this paper, we evaluate the performance of the major ranking algorithms, we find that the Weighted Page Rank (WPR) algorithm performs the best. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Page ranking Search engines Web Mining Web Structure Web Usage Weighted Page Rank World Wide Web

来源：评论

学校读者我要写书评

暂无评论

Liver Tumor Prediction with Advanced Attention Mechanisms Integrated into a Depth-Based Variant Search Algorithm

引用

computers, Materials & Continua 2023年第10期77卷 1209-1226页

作者： P.Kalaiselvi S.Anusuya Department of Computer Science and Engineering Saveetha School of EngineeringChennaiTamil Nadu602117India Information Technology Saveetha School of EngineeringChennaiTamil Nadu602117India

In recent days,Deep Learning(DL)techniques have become an emerging transformation in the field of machine learning,artificial intelligence,computer vision,and so ***,researchers and industries have been highly endorsed in the medical field,predicting and controlling diverse diseases at specific *** tumor prediction is a vital chore in analyzing and treating liver *** paper proposes a novel approach for predicting liver tumors using Convolutional Neural Networks(CNN)and a depth-based variant search algorithm with advanced attention mechanisms(CNN-DS-AM).The proposed work aims to improve accuracy and robustness in diagnosing and treating liver *** anticipated model is assessed on a Computed Tomography(CT)scan dataset containing both benign and malignant liver *** proposed approach achieved high accuracy in predicting liver tumors,outperforming other state-of-the-art ***,advanced attention mechanisms were incorporated into the CNN model to enable the identification and highlighting of regions of the CT scans most relevant to predicting liver *** results suggest that incorporating attention mechanisms and a depth-based variant search algorithm into the CNN model is a promising approach for improving the accuracy and robustness of liver tumor *** can assist radiologists in their diagnosis and treatment *** proposed system achieved a high accuracy of 95.5%in predicting liver tumors,outperforming other state-of-the-art methods.

关键词： Deep learning convolution neural networks liver tumors CT scans attention mechanism classifier

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：