检索结果-内蒙古大学图书馆

2nd International Conference Computational and Characterization Techniques in Engineering and sciences, IC3TES 2024

作者： Sai Varshith, Pabbisetty Venkata Parthipan, V. Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Big Data and Network Security Tamil Nadu Chennai India

ISBN: (纸本)9798350364699

The purpose of this study is to determine whether the Catboost algorithm is superior to the Extreme Gradient Boosting Classifier (XGBoost) method in terms of its ability to generate predictions about the sorts of clothing based on evaluations from online retailers. This study contains 2 groups: Novel Catboost algorithm and Extreme Gradient Boosting Classifier, where each group is iterated for a sample size of 10 calculated using the ClinCalc software with 0.05 as the alpha value, and a CI of 95%. The e-commerce reviews dataset with a size of 23485 was considered from ***. The novel catboost algorithm accuracy is 92%, which appears to be superior to the XGBoost classifier's accuracy of 89%. It can be concluded that there exists a statistically significant distinction between the CatBoost algorithm and the XGBoost classifier algorithm. This is evidenced by a value of p=0.007 (Independent sample t-test p © 2024 IEEE.

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Intelligent IoT Systems for Real-Time Food Quality Monitoring and Analysis 2

AI-Driven Intelligent IoT Systems for Real-Time Food Quality...

引用

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

作者： Krishnan, Prabhakar Ebenezar, U. Samson Ranitha, R. Purushotham, N. Balakrishnan, T. Suresh Amrita Vishwa Vidyapeetham Center for Cyber Security Systems and Networks Amritapuri campus India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India Care College of Engineering Department of Computer Science and Engineering Tamil Nadu Trichy India Mohan Babu University Department of Computer Science and Engineering Mr.palliAP India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350384277

The system will monitor and analyse food quality along the supply chain in real time. The system has high performance due to the CNN algorithms. In terms of accuracy, CNN has a high performance (95.2%), precision (92.8%), recall (94.5%) and F1 score (93.6 %). These features enable the model to predict food quality under good and poor conditions, thus demonstrating its effectiveness in assessing quality. The accuracy of real-time monitoring was evaluated across the supply chain to prove system reliability. Accuracy ratings for transport, storage and processing were 96.3%, 94.7% and 92.1%. These results show the robustness of this system within dynamic supply chain environments. Further testing evaluated environmental resilience capabilities. Under normal conditions, the accuracy of this system was 95.2%, while it reduced to 92.6% and rises again up to a level of 94.3%. The adaptability of the system under harsh conditions demonstrates that it can be applied to ensure food quality in various cases. This study reveals how proposed AI-based intelligent Internet of Things system may be used for real application using an appropriate dataset selected properly. This approach can help improve the quality assurance of food in an industry that is complex by uniting advanced algorithms with real-time data monitoring. © 2024 IEEE.

关键词： Artificial Intelligence Food Quality Analysis Intelligent IoT Systems Real-Time Monitoring

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis for Prediction of Trending Footwear Classification using DensNet compared with Logistic Regression model 2

Performance Analysis for Prediction of Trending Footwear Cla...

引用

2nd International Conference Computational and Characterization Techniques in Engineering and sciences, IC3TES 2024

作者： Giridhar, E.V. Parthipan, V. Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Tamil Nadu Chennai India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Big Data and Network Security Tamil Nadu Chennai India

ISBN: (纸本)9798350364699

The purpose of this work is to investigate the effectiveness of DensNet and Logistic Regression in terms of accurately predicting the classification of footwear *** this study, there are two groups: the Novel DensNet model and the Logistic Regression model. Each group is being iterated for a sample size of ten, which is being generated with the ClinCalc software. The alpha value is set at 0.05, and the confidence interval is set at 95%. We took into consideration the footwear prediction dataset that was available on *** and had a size of 15854. The statistical analysis reveals a significant difference between the DensNet algorithm and the Logistic Regression model, with a value of p=0.001 (independent sample t-test p © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

A Multichannel CNN-GRU Hybrid Architecture for sEMG Gesture Recognition

A Multichannel CNN-GRU Hybrid Architecture for sEMG Gesture ...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Song, Shouliang Dong, Anming Yu, Jiguo Han, Yubing Zhou, You Jinan250353 China School of Computer Science and Technology Jinan250353 China Big Data Institute Jinan250353 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China Shandong Haikan New Media Research Institute Co. Ltd. China

ISBN: (纸本)9798350337488

Surface electromyography (sEMG) signal is a physiological electrical signal produced by muscle contraction. Different gestures can be effectively recognized from the characteristics of the sEMG signal. Currently, convolutional neural networks (CNNs) have been widely used in sEMG gesture recognition systems due to their capabilities in acquiring spatial features of sEMG signals. However, these classical CNNs are inefficient in extracting temporal correlation that resides in the time serials of sEMG signals, which is definitely important for gesture recognition. To overcome such a drawback of traditional CNN-based gesture recognition methods, we propose a multichannel hybrid deep learning model for gesture recognition by combining the multichannel CNNs with a gated recurrent unit (GRU). Specifically, we use multiple CNNs to preprocess the original multichannel EMG signals in a one-by-one manner to obtain the spatial features in the current observing window. The outputs of the multiple CNNs are concatenated and fed to a temporal-feature extracting module, which is designed by cascading a GRU with an attention mechanism. Through the GRU, the temporal features of successive signal frames can be established, while the attention mechanism is introduced to further focus on the key information in recognizing the gestures, which is beneficial to improve the robustness and accuracy of the model. Experiments show that the recognition accuracy of the proposed method reaches 97.6% and 96.7% on the Ninapro DB2 and Ninapro DB5 datasets, respectively. Compared with the classical CNN method, the performance improvement is 2.9% and xx% higher than that of the traditona CNN model, respectively. © 2023 IEEE.

关键词： attention mechanism gated recurrent unit (GRU) gesture recognition multichannel CNN Surface electromyography (sEMG)

来源：评论

学校读者我要写书评

暂无评论

Prediction Of Student Education Performance Using Googlenet Comparison With Over Alexnet Algorithm 2

Prediction Of Student Education Performance Using Googlenet ...

引用

2nd International Conference Computational and Characterization Techniques in Engineering and sciences, IC3TES 2024

作者： Krishna, Kotte. Venkata Rama Parthipan, V. Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Tamil Nadu Chennai India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Big Data and Network Security Tamil Nadu Chennai India

ISBN: (纸本)9798350364699

An examination of the degree to which GoogleNet and Alexnet are accurate in predicting the academic success of students is the primary objective of this study. Each of the two groups that make up the program contains ten samples, and there are two groups altogether. For the purpose of determining the sample size, a threshold of 0.05%, a G-power pretest of 80%, and a confidence interval of 95% are utilized. We took into consideration the student education dataset that was available on *** and had a size of 66500. The method that was proposed was found to have an accuracy of 94.63% when compared to the existing system, which has an accuracy of only if. Furthermore, it demonstrates that there is a statistically significant difference between GoogleNet and Alexnet, with a value of p=0.001 (independent sample T test p © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

WU-Net++: A novel enhanced Weighted U-Net++ model for brain tumor detection and segmentation from multi-parametric magnetic resonance scans

引用

Multimedia Tools and Applications 2024年第28期83卷 71885-71908页

作者： Das, Suchismita Dubey, Rajni Jena, Biswajit Tsai, Lung-Wen Saxena, Sanjay Department of Computer Science and Engineering International Institute of Information Technology Bhubaneswar India School of Computer Engineering KIIT Deemed to Be University Bhubaneswar India Division of Cardiology Department of Internal Medicine Taipei Medical University Hospital Taipei111031 Taiwan Department of Computer Science and Engineering Institute of Technical Education and Research SOA Deemed to Be University Bhubaneswar India Department of Medicine Research Taipei Medical University Hospital Taipei111031 Taiwan Department of Information Technology Office Taipei Medical University Hospital Taipei11031 Taiwan Graduate Institute of Data Science College of Management Taipei Medical University Taipei11031 Taiwan

Brain tumor detection and segmentation from multi-parametric magnetic resonance (MR) scans are crucial for the prognosis and treatment planning of brain tumor patients in current clinical practice. With recent technological advancements, artificial intelligence-based deep learning has proven its indispensable image analysis capability in the most challenging tasks. This study proposes an automated WU-Net + + deep learning model for brain tumor segmentation using multiparametric structural MR scans obtained from the BraTS 2018 dataset. The model was validated through cross-dataset testing for intracranial hemorrhage (ICH) classification (ATLAS V2.1 dataset) and multi-organ segmentation from abdominal images of TCIA and BTCV datasets. The WU-Net++ model, a novel version of U-Net, was developed by adjusting its pooling operation as a weighted function of max and average pooling for brain tumor segmentation. The proposed model (WU-Net + +) achieved an F1 score of 0.94 ± 0.124, a dice score of 0.91 ± 0.132, and an AUC value of 0.915 for whole tumor segmentation. The model also achieved a high accuracy of 0.9949 ± 0.121 in ICH classification and dice scores of 0.912 ± 0.21, 0.844 ± 0.25, and 0.893 ± 0.17 for spleen, esophagus, and portal and splenic vein segmentation, respectively. Our study revealed that WU-Net + + has significant potential to improve the accuracy of segmentation and could be an effective method in the era of precision medicine. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Predicting LIC Stock Price using Lasso Regression Compared with Random Forest Regression 2

Performance Analysis of Predicting LIC Stock Price using Las...

引用

2nd International Conference Computational and Characterization Techniques in Engineering and sciences, IC3TES 2024

作者： Kumar, Chennupati Charan Parthipan, V. Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Tamil Nadu Chennai India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Big Data and Network Security Tamil Nadu Chennai India

ISBN: (纸本)9798350364699

With regard to the objective of the entire study, the goal is to improve the accuracy of predicting stock price using Lasso Regression in comparison to Random Forest Regression. The Novel K-Nearest Neighbors and Support Vector Machine Algorithm are the two groups that are the emphasis of this research activity. Each of these groups is carried out ten times. For the purpose of calculating samples, the Clincal software was utilized. The alpha value was determined to be 0.05, and the confidence interval was set at 95%. We took into consideration the stock price prediction dataset that was available on *** and had a size of 12617. With a value of p=0.000 (Independent sample t-test p © 2024 IEEE.

关键词： Support vector regression

来源：评论

学校读者我要写书评

暂无评论

REINFORCE Adversarial Attacks on Large Language Models: An Adaptive, Distributional, and Semantic Objective

arXiv

引用

arXiv 2025年

作者： Geisler, Simon Wollschläger, Tom Abdalla, M.H.I. Cohen-Addad, Vincent Gasteiger, Johannes Günnemann, Stephan Department of Computer Science Munich Data Science Institute Technical University of Munich Germany Google Research United States

To circumvent the alignment of large language models (LLMs), current optimization-based adversarial attacks usually craft adversarial prompts by maximizing the likelihood of a so-called affirmative response. An affirmative response is a manually designed start of a harmful answer to an inappropriate request. While it is often easy to craft prompts that yield a substantial likelihood for the affirmative response, the attacked model frequently does not complete the response in a harmful manner. Moreover, the affirmative objective is usually not adapted to model-specific preferences and essentially ignores the fact that LLMs output a distribution over responses. If low attack success under such an objective is taken as a measure of robustness, the true robustness might be grossly overestimated. To alleviate these flaws, we propose an adaptive and semantic optimization problem over the population of responses. We derive a generally applicable objective via the REINFORCE policy-gradient formalism and demonstrate its efficacy with the state-of-the-art jailbreak algorithms Greedy Coordinate Gradient (GCG) and Projected Gradient Descent (PGD). For example, our objective doubles the attack success rate (ASR) on Llama3 and increases the ASR from 2% to 50% with circuit breaker defense.1 © 2025, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Threat Intelligence in Cloud Computing Detecting and Responding to Cyber Attacks

AI-Driven Threat Intelligence in Cloud Computing Detecting a...

引用

2024 International Conference on Intelligent Algorithms for Computational Intelligence Systems, IACIS 2024

作者： Dorothy, A. Beatrice Madhavidevi, B. Nachiappan, Balusamy Manikandan, G. Patjoshi, Pramod Kumar Sindhuja, M. Department of Data Science Tiruchirappalli India Institute of Aeronautical Engineering Department of Computer Science and Engineerin Hyderabad India Technical Lead Prologis DenverCO80202 United States Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Ece Chennai India School of Management Centurion University of Technology and Management Bhubaneswar India St. Martins Engineering College Department of Computer Science and Engineering Secunderabad India

ISBN: (纸本)9798350360660

This research work tackles flaws in typical cloud threat intelligence systems, which often depend on static rules and signature-based detection approaches that are unable to react to changing cyber threats. These constraints highlight the need for a more proactive approach, leading the development of a novel system that incorporates AI-driven approaches. The work goes beyond static rule-based models and proposes an AI-driven method to addressing inadequacies in current systems. Combining anomaly detection and machine learning (ML) techniques enables the system to adapt to changing security threats. The first phases involve gathering and analyzing data from numerous cloud sources to improve the system's capacity to spot problems. Supervised learning with Random Forest classifies known hazards, while unsupervised learning with Isolation Forest detects new abnormalities. Real-time monitoring and response considerably improve the system's threat detection rates (95%), anomaly detection (93%), and other performance indicators. The proposed system surpasses the existing system by 95% accuracy, 93% precision, and 96% recall. These findings demonstrate how effectively the framework enables cloud safety and its capacity to enhance overall digital safety and proactively prevent assaults. © 2024 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

Low-Delay Modified OLSR Scheme for Flying AdHoc networks

Low-Delay Modified OLSR Scheme for Flying AdHoc Networks

引用

2024 Asia Communications and Photonics Conference, ACP 2024 and International Conference on Information Photonics and Optical Communications, IPOC 2024

作者： Xiong, Xiran Zheng, Weibo Wang, Shulei Qu, Yuanzhe Chen, Shiqi Yuan, Yongchun Li, Wentao Hong, Yiming Cao, Bingyao Key Laboratory of Specialty Fiber Optics and Optical Access Networks Shanghai Institute for Advanced Communication and Data Science Shanghai University Shanghai China Engineering No.1 Shanghai Institute of Technical Physics Chinese Academy of Sciences Shanghai China Engineering No.1 Shanghai Institute of Technical Physics Chinese Academy of Sciences University of Chinese Academy of Sciences Shanghai China

We propose a low-delay modified OLSR scheme for FANET. Through hardware testing, compared with the OLSR protocol, EED and RO have decreased by 100 times and 8% respectively, and PDR has increased by 3%. © 2024 IEEE.

ISBN: (纸本)9798350379266

关键词： Delay tolerant 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：