检索结果-内蒙古大学图书馆

Informatica (slovenia) 2025年第13期49卷 143-162页

作者： Mohiuddin, Mohd Hasan Tamilselvan, Latha Department of Computer Science and Engineering B.S. Abdur Rahman Crescent Institute of Science &Technology Vandalur Chennai600048 India Department of Information & Technology B.S. Abdur Rahman Crescent Institute of Science &Technology Vandalur Chennai600048 India

Image deduplication is becoming increasingly important for cloud storage infrastructures to handle the increasing amount of multimedia material. Through increased storage efficiency, effective picture deduplication may optimize resources and save expenses. It also improves performance by facilitating quicker access, utilizing less bandwidth, and enhancing data integrity. Although heuristic-b.s.d classical deduplication techniques work well in various storage infrastructures, they cannot keep up with the dynamic nature of cloud storage resources. This study presents IDedupNet, a revolutionary DL-b.s.d framework that improves infrastructure performance in cloud computing by efficiently detecting duplicate and near-duplicate photos. Our approach leverages MobileNetV3 for feature extraction and CNN-b.s.d encodings for image deduplication, enabling it to manage duplicate photos in highly dynamic contexts efficiently. Additionally, we provide a Learning-b.s.d Image Deduplication (LbID) approach that improves deduplication performance by extending the use of the IDedupNet model. Experimental evaluation demonstrates a high accuracy of 98.68% on benchmark datasets, consistently outperforming existing models. The underlying technique and deep learning framework may be easily integrated into real-time cloud storage systems to increase customer satisfaction and infrastructure efficiency. © 2025 slovene society Informatika. All rights reserved.

关键词： Cloud storage

来源：评论

学校读者我要写书评

暂无评论

Convolutional-Neural Network b.s.s speaker Emotion Detection b.s.d on Human-computer Interaction 1

Convolutional-Neural Network Bases Speaker Emotion Detection...

引用

1st International Conference on Advances in computer science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Nithya, b. saranya, R. Joseph, Mary Josphineleela, R. Thirunagalingam, Arunkumar Kodali, Arun Kumar B.S. Abdur Rahman Crescent Institute of Science and Technology Dept of Computer Science and Engineering Chennai India V.S.B. Engineering College Department of Computer Science and Engineering Karur India St. Joseph's Institute of Technology OMR Department of IT Chennai119 India Panimalar Engineering College Department of Computer Science and Engineering India Mckesson Corporation United States Mphasis Corporation

ISBN: (纸本)9798331518578

The present investigation proposes a Convolutional Neural Network (CNN)-b.s.d method for human-computer interaction (HCI) speaker emotion identification. Optimising the user experience through clearer and sympathetic connections is made possible by emotional knowledge. Conventional techniques for detecting emotions depend on manually created characteristics, which are frequently laborious and less resilient to speech variability. by using CNNs' automatic feature extraction capabilities, the suggested system analyses speech signal spectrograms and extracts crucial emotional indicators. The method obtains notable gains in emotion classification accuracy by retraining the system on a varied collection of emotional speech samples. Important emotional states like happiness, anger, sadness, and neutrality are all successfully distinguished using the CNN model. This study demonstrates how deep learning can help develop emotion-sensitive HCI systems and promote more organic and contextually aware human-machine interactions. Applications in customer service, healthcare, and virtual assistants can benefit from the technique's adaptability and versatility. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

bubble Prediction in stock Markets: Leveraging sVM and Technical Indicators for High Accuracy 3

Bubble Prediction in Stock Markets: Leveraging SVM and Techn...

引用

3rd International Conference on Electronics and Renewable systems, ICEARs 2025

作者： Yuvaraj, s. Chenni Kumaran, J. Manogar, E. Doss, P.Lourdu Mahimai Gunasekaran, M. Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering TamilNadu Chennai India B.S. Abdur Rahman Crescent Institute of Science and Technology Department of Computer Applications Chennai India

ISBN: (纸本)9798331509675

Predicting stock market bubbles is indispensable for risk control and refinement of trading strategies. Therefore, this study presents a Machine-Learning Framework to detect price bubble formations b.s.d on support Vector Machine (sVM) and through important technical indicators. Among these are momentum indicators, such as the Relative strength Index (RsI), and the Moving Average Convergence Divergence (MACD) histogram, which are complemented with volatility measures from bollinger bands and with normalized volume indicators, all to improve predictive accuracy. Recent historical stock data were fed to the model during training and testing, yielding exceptional accuracy: 98.54% on the test set and 98.95% on the training set. The performance evaluation was carried out b.s.d on Classification Reports, Confusion Matrices, Receiver Operating Characteristic (ROC) curve, and Precision-Recall metrics, thus confirming the performance efficiency of the developed framework. With this approach, bubbles' early detection allows traders and analysts a powerful tool to make informed decisions in risk mitigation or strategic enhancement. © 2025 IEEE.

关键词： support vector machines

来源：评论

学校读者我要写书评

暂无评论

Triboost and beyond: Advanced Machine Learning Approaches for Diabetes Risk Prediction 3

TriBoost and Beyond: Advanced Machine Learning Approaches fo...

引用

3rd International Conference on Electronics and Renewable systems, ICEARs 2025

作者： Katlariwala, soham biren Gandhi, Vaibhav C. Patel, Nirav Parmar, Devendra Desai, Ayushi Indian Institute of Technology Madras B.S. Data Science and Applications Chennai India University Department of Computer Engineering Mbit Anand India Parul University Parul Institute of Technology Vadodara India

ISBN: (纸本)9798331509675

Diabetes is a tremendous world health issue and, in its management, and complications prevention, proper screening is vital. This paper examines the improvement of accurate diabetes risk prediction by some advanced machine learning methods. The study compares various models such as;Random Forest, Adaboost, support Vector Machine, Catboost, Decision Tree, Ls-sVM, Logistic Regression, Naïve bayes, k-Nearest Neighbors, LightGbM, XGboost, and neural networks. Most emphasis is put on Triboost that is a novel ensemble model which integrates XGboost, Catboost, and LightGbM. Lastly, the effectiveness of a model is determined using measures such as ROC AUC and accuracy. Evaluation of the results has shown that the proposed Triboost had the highest accuracy at 94% and ROC AUC of 91% thereby outcompeting the use of individual classifiers as well as other ensemble methods. The results of the study confirm adequacy and possibilities of ensemble learning to enhance predictive precision and stability and their applicability for early detection of diabetes in clinics. Further work shall seek to increase the variability of the dataset, integrate fresh clinical data, and increase computational effectiveness for practical use. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Harmonized Integration of GWO and J-sLnO for Optimized Asset Management and Predictive Maintenance in Industry 4.0

引用

sensors 2025年第9期25卷 2896-2896页

作者： Arularasan, A.N. Ganeshkumar, P. Alkhatib, Mohammad Albalawi, Tahani Department of Computer Science and Engineering B.S. Abdur Rahman Crescent Institute of Science and Technology VandalurTamil Nadu Chennai600 048 India Riyadh11432 Saudi Arabia

Highlights: What are the main findings? The study shows that, in terms of execution speed, cost-effectiveness, and energy usage, GWO and J-sLnO perform better than conventional scheduling algorithms. Compared to GWO, J-sLnO performs predictive maintenance activities with greater accuracy and stability. What is the implication of the main finding? In Industry 4.0, the suggested optimization strategies improve the effectiveness of predictive maintenance and asset management. J-sLnO is a dependable option for practical industrial applications that demand endurance and excellent prediction accuracy. The study encompasses the application of two different advanced optimization algorithms on asset management and predictive maintenance in Industry 4.0—Grey Wolf Optimization and Jaya-b.s.d sea Lion Optimization (J-sLnO). Using this derivative, the authors showed how these techniques could be combined through resource scheduling techniques to demonstrate drastic improvement in the level of efficiency, cost-effectiveness, and energy consumption, as opposed to the standard MinMin, MaxMin, FCFs, and Round Robin. In this sense, GWO results in an execution time reduction between 13 and 31%, whereas, in J-sLnO, there is an execution time reduction of 16–33%. In terms of cost, GWO shows an advantage of 8.57–9.17% over MaxMin and Round Robin, b.s.d on costs, while J-sLnO delivers a better economy for the range of savings achieved, which is between 13.56 and 19.71%. both algorithms demonstrated tremendous energy efficiency, according to the analysis, which showed 94.1–94.2% less consumption of energy than traditional methods. Moreover, J-sLnO was reported to be more accurate and stable in predictability, making it an excellent choice for accurate and more time-trusted applications. J-sLnO is being increasingly recognized as a powerful yet realistic solution for the application of Industry 4.0 because of efficacy and reliability in predictive modeling. Not only does this research valid

关键词： Asset management

来源：评论

学校读者我要写书评

暂无评论

Convolutional-Neural Network b.s.s speaker Emotion Detection b.s.d on Human-computer Interaction

Convolutional-Neural Network Bases Speaker Emotion Detection...

引用

Advances in computer science, Electrical, Electronics, and Communication Technologies (CE2CT), International Conference on

作者： Nithya b.s.ranya R Mary Joseph R. Josphineleela Arunkumar Thirunagalingam Arun Kumar Kodali Dept of Computer Science and Engineering B.S. Abdur Rahman Crescent Institute of Science and Technology Chennai Department of Computer Science and Engineering V.S.B. Engineering College Karur Department of IT St. Joseph's Institute of Technology OMR Chennai Department of Computer Science and Engineering Panimalar Engineering College Data and Operations Mckesson Corporation Mphasis Corporation Data Architect

ISBN: (数字)9798331518578

ISBN: (纸本)9798331518585

关键词： Human computer interaction Emotion recognition Virtual assistants Medical services Feature extraction User experience Convolutional neural networks Robots system analysis and design spectrogram

来源：评论

学校读者我要写书评

暂无评论

bubble Prediction in stock Markets: Leveraging sVM and Technical Indicators for High Accuracy

Bubble Prediction in Stock Markets: Leveraging SVM and Techn...

引用

Electronics and Renewable systems (ICEARs), International Conference on

作者： Yuvaraj.s Chenni Kumaran.J Manogar.E P.Lourdu Mahimai Doss M.Gunasekaran Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai TamilNadu India Department of Computer Applications B.S. Abdur Rahman Crescent Institute of Science and Technology Chennai India

ISBN: (数字)9798331509675

ISBN: (纸本)9798331509682

关键词： support vector machines Training Renewable energy sources Accuracy Volume measurement Machine learning Receivers stock markets Testing Risk mitigation

来源：评论

学校读者我要写书评

暂无评论

Triboost and beyond: Advanced Machine Learning Approaches for Diabetes Risk Prediction

TriBoost and Beyond: Advanced Machine Learning Approaches fo...

引用

Electronics and Renewable systems (ICEARs), International Conference on

作者： soham biren Katlariwala Vaibhav C. Gandhi Nirav Patel Devendra Parmar Ayushi Desai B.S. Data Science and Applications Indian Institute of Technology Madras Chennai India Department of Computer Engineering MBIT The Charutar Vidya Mandal (CVM) University Anand India Parul Institute of Technology Parul University Vadodara India

ISBN: (数字)9798331509675

ISBN: (纸本)9798331509682

Diabetes is a tremendous world health issue and, in its management, and complications prevention, proper screening is vital. This paper examines the improvement of accurate diabetes risk prediction by some advanced machine learning methods. The study compares various models such as; Random Forest, Adaboost, support Vector Machine, Catboost, Decision Tree, Ls-sVM, Logistic Regression, Naïve bayes, k-Nearest Neighbors, LightGbM, XGboost, and neural networks. Most emphasis is put on Triboost that is a novel ensemble model which integrates XGboost, Catboost, and LightGbM. Lastly, the effectiveness of a model is determined using measures such as ROC AUC and accuracy. Evaluation of the results has shown that the proposed Triboost had the highest accuracy at 94% and ROC AUC of 91% thereby outcompeting the use of individual classifiers as well as other ensemble methods. The results of the study confirm adequacy and possibilities of ensemble learning to enhance predictive precision and stability and their applicability for early detection of diabetes in clinics. Further work shall seek to increase the variability of the dataset, integrate fresh clinical data, and increase computational effectiveness for practical use.

关键词： support vector machines Renewable energy sources Accuracy sensitivity Predictive models stability analysis Diabetes Ensemble learning Decision trees Random forests

来源：评论

学校读者我要写书评

暂无评论

Applying convolutional attention mechanisms and Human Memory search for effective English-Urdu translation

引用

engineering Applications of Artificial Intelligence 2025年 155卷

作者： Jayasakthi Velmurugan, K. Faheem Nikhat, H. suresh, K. Hemavathi, s. Kavitha, V. Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamilnadu India Department of Computer Science and Engineering B.S. Abdur Rahman Crescent Institute of Science & Technology Vandalur Tamilnadu 600 048 India Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur Tamilnadu Chennai603203 India Department of Computing Technologies School of Computing SRM Institute of Science and Technology Kattankulathur Tamilnadu Chennai603203 India

In recent decades, machine translation has become a prominent area of research, with the primary objective of overcoming language barriers. Early approaches primarily centered on word-for-word translation between source and target languages. However, there has been a shift towards data-driven models, such as neural machine translation and statistical methods, driven by advancements in Artificial Intelligence (AI), communication and computing technologies. This paper introduces a novel Convolutional Attention Mechanism-b.s.d Human Memory search (CAM-HMs) algorithm for translating English into Urdu, to achieve high-quality and effective machine translation. The proposed model consists of several key phases, including pre-processing, sentence padding, word embedding, encoding, decoding, and target text generation. A new spider web-b.s.d search strategy is also incorporated to enhance the translation process in neural machine translation. The performance is evaluated using a UMC005 English-Urdu dataset, Parallel corpus for English & Urdu language, and the Roman Urdu to English Translation Dataset. Various automatic evaluation metrics such as the bilingual Evaluation Understudy (bLEU), National Institute of standards and Technology (NIsT), Word Error Rate (WER), Accuracy, Precision, Recall, and F-Measure are used to assess the model's efficiency, and its output is compared to that of Google Translate. The proposed model achieves an average bLEU score of 82.14 %, NIsT of 79.51 %, WER of 2.77 %, Accuracy of 98.99 %, Precision of 98.95 %, Recall of 98.90 %, and F-Measure of 98.92 %, demonstrating its effectiveness in producing high-quality machine translation results. © 2025

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Handwritten optical character recognition using TransRNN trained with self improved flower pollination algorithm (sI-FPA)

引用

Multimedia Tools and Applications 2024年 1-23页

作者： Devi, s. Nandhini Fatima, N. sabiyath Department of Computer Science and Engineering B.S. Abdur Rahman Crescent Institute of Science & ampTechnology Chennai India

The difficulty of successfully scanning handwritten text arises from variances in style, size, and orientation, which affect handwriting optical character recognition (OCR). This study provides a novel strategy that incorporates innovative techniques for effectively addressing these difficulties. Initially, preprocessing steps involve Gaussian blur to reduce noise and CLAHE to enhance contrast, improving the visibility of text regions. Canny Edge Detection is then utilized for segmentation, followed by text localization using the Efficient and Accurate scene Text (EAsT) algorithm. Next, features are extracted via Inception V3 to capture both low-level and high-level information. From the collected characteristics, Long short-Term Memory (LsTM) networks are used to extract chronological data. Then, with the help of the self-Improved Flower Pollination Algorithm (sI-FPA), features are selected using Optimized Principal Component Analysis (PCA). Finally, a combination of Transformer and Recurrent neural networks (RNNs) is used to perform text recognition, maximizing the benefits of each network’s advantages in processing sequential and contextual data. Experiments on MNsT dataset with validation using different optimization algorithms show the effectiveness and resilience of the suggested method in different optimization scenarios. The combination of these methods results in a sophisticated OCR system that can recognize handwritten characters with accuracy, even under difficult conditions. © The Author(s), under exclusive licence to springer science+b.s.ness Media, LLC, part of springer Nature 2024.

关键词： Principal component analysis

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：