检索结果-内蒙古大学图书馆

4th International Conference on Expert Clouds and applications, ICOECA 2024

作者： Palarimath, Suresh Maran, Pyingkodi Thenmozhi, K. Shiny, K.V. Sujatha, T. N.r, Wilfred Blessing College of Computing and Information Sciences University of Technology and Applied Information Technology Department Sciences Salalah Oman Kongu Engineering College Department of Computer Applications Erode India Department of Compute Science Bengaluru India Bharath Institute of Higher Education and Research Department of Computer Science and Engineering Chennai India Sri Krishna College of Engineering and Technology Department of Artificial Intelligence and Data Science Coimbatore India College of Computing and Information Sciences Univesity of Technology and Applied Sciences Information Technology Department Ibri Oman

ISBN: (纸本)9798350385793

Breast cancer poses a significant threat to women's health, being a leading cause of cancer-related mortality among female population. In recent years, machine learning has emerged as a promising approach in medical field, particularly in detection and classification tasks. However, existing algorithms often exhibit suboptimal accuracy, necessitating improved methodologies. This research presents a novel approach using a Modified Support Vector Machine (MSVM) for breast cancer classification into benign and malignant categories. Leveraging the Wisconsin Breast Cancer dataset (WBCD), preprocessing techniques are applied to enhance data quality. Principle Component Analysis (PCA) reduces dimensionality, while linear Discriminant Analysis (LDA) extracts discriminative features crucial for classification. The proposed MSVM classifier achieves exceptional performance, with a classification accuracy of 99.42%, outperforming other existing methods such as Deep Convolutional Neural Networks and Fuzzy Rule-based Systems. These results highlight the efficacy of the MSVM approach in accurately distinguishing between benign and malignant breast cancer cases, showcasing its potential as a reliable tool for medical image analysis and cancer diagnosis. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Channel-wise attention based binarization for CNN Architectures

Channel-wise attention based binarization for CNN Architectu...

引用

Emerging Systems and Intelligent Computing (ESIC), International Conference on

作者： Ipsita Paul Mainak Bandyopadhyay Satya Ranjan Dash Tanjim Taharat Aurpa School of Computer Engineering KIIT D.U. Bhubaneswar India School of Computer Applications KIIT D.U. Bhubaneswar India Department of Data Science Engineering BSMR Digital University Bangladesh

ISBN: (数字)9798331522100

ISBN: (纸本)9798331522117

Attention mechanisms are known to effectively increase the performance of a model by focusing on specific sections of the input while executing a task. Squeeze and Excitation module (SE-Net) and Efficient channel attention module (ECA-Net) are well-known Channel Attention networks that only involve a few parameters to achieve a clear performance gain. In order to further improve the model’s accuracy, Binarized Neural Networks (BNNs) can be introduced in the same. BNNs are deep learning models that use binarized values for activation functions and training weights, instead of fully precised values that leads to much faster computation, occupying less memory and power. Motivated by this, a method of binarization of the convolutional network is proposed in this paper that can enhance the overall model accuracy. In our work, we focused on evaluating the performance of our binarized attention module over the pre-existing ones. Thus, the objective of this work is to design, implement, and evaluate efficient neural network models that balance accuracy and computational efficiency for image classification tasks on datasets with differing complexity levels, such as CIFAR-10 and CIFAR-100. By exploring various backbone architectures (e.g., MobileNetV2 and ResNet50), attention mechanisms (e.g., ECANet and SENet), and binarization techniques, this study aims to understand the impact of these components on model performance and resource requirements. Ultimately, the goal is to develop optimized models that achieve high accuracy with minimal computational overhead, making them suitable for deployment in resource-constrained environments.

关键词： Deep learning Training Attention mechanisms Accuracy Computational modeling Neural networks Transfer learning Convolutional neural networks Image classification Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

DCT-CNN Hybrid Model for High-Capacity and Secure data Concealment in Encrypted Images

DCT-CNN Hybrid Model for High-Capacity and Secure Data Conce...

引用

Advances in Computing, Communication and Applied Informatics (ACCAI), International Conference on

作者： Adithya Pothan Raj V Yogita Dayanand Patil Madhurikkha S V. Srithar Vidhya Department of Computer Science and Engineering Saveetha Institute of Medical and Technical Sciences Department of Engineering Science Vishwakarma University pune Department of Artificial Intelligence & Data Science Jaya Sakthi Engineering College Department of Computer Science and Applications Periyar Maniammai Institute of Science and Technology Department Of Computer Science and Engineering Jeppiaar Engineering College

ISBN: (数字)9798350389449

ISBN: (纸本)9798350389456

This research article presents a revolutionary approach to address the challenges of reversible data embedding in encrypted images within cloud networks. Our pioneering algorithm combines the potency of the Discrete Cosine Transform (DCT) and Convolutional Neural Network (CNN) to introduce a novel DCT-CNN hybrid model, specifically designed for efficient and high-capacity reversible data hiding. Diverging from conventional methods, our approach eliminates the need for trial data embedding during predictor selection. The initial phase involves estimating the optimal predictor using CNN, where training labels are forged through a trial embedding procedure. The selected predictor, providing the highest embedding rate, is assigned as the class label for the corresponding encrypted image. Users secure their images through a three-tier encryption process before transferring them to the cloud. During the testing phase, the trained CNN model processes encrypted images uploaded by users to determine the predictor class with the maximum embedding capacity. data embedding is then executed using the classified predictor. The proposed predictor storage demonstrates impressive results, achieving an accuracy, recall, and precision of $93.9 \%, 92.6 \%$, and $95.3 \%$ in average, respectively, particularly for the BossBase dataset. Additionally, our reversible data embedding algorithm, employing the DCT-CNN paradigm, achieves a commendable embedding rate of 69.1bpp, along with an average PSNR of 38.8 dB and SSIM of 0.93 in average. Evaluations conducted on datasets, including BossBase and BOWS-2, convincingly demonstrate the stoutness and effectiveness of the proposed method. This research introduces a unique perspective to the realm of reversible data embedding in cloud networks, offering a promising solution for secure and high-capacity data concealment within encrypted images.

关键词： Measurement Training Accuracy Computational modeling Prediction algorithms data models Encryption

来源：评论

学校读者我要写书评

暂无评论

A Multimodal Deep Learning Approach for Typhoon Track Forecast by Fusing CNN and Transformer Structures

A Multimodal Deep Learning Approach for Typhoon Track Foreca...

引用

computer Vision, Image and Deep Learning (CVIDL), International Conference on

作者： Ruijie Zhan Jiadong Lu Yuchao Jiang Tongfei Li Guohao Zhong Wei Lv Falcuty of Data Science City University of Macau Macau China School of Aliyun Big Data Applications Zhuhai College of Science and Technology Zhuhai China School of Computer Science Zhuhai College of Science and Technology Zhuhai China

The prediction of typhoon trajectory is essential to protect people and property. However, traditional methods of typhoon track prediction are difficult to guarantee the prediction efficiency and accuracy when dealing with a large amount of complex data. With the improvement of computer computing power and the development of deep learning technology, deep neural networks are gradually applied to the field of meteorology. In this paper, we describe a typhoon trajectory prediction model named TyT (Typhoon technology with Transformer), which effectively uses large-scale multimodal historical data and advanced deep learning techniques to achieve typhoon trajectory forecasting. With the above design, Our TyT can make full use of the implicit correlation of multimodal data to realize the advantages that unimodal data-based methods do not have. Meanwhile, the structure of Transformer enables to establish long-range dependencies by attention mechanism and position encoding. Experiments on historical typhoon track data in the northwest Pacific Ocean show that our TyT has a significant improvement in accuracy compared to previous typhoon track prediction methods. Finally, four different typhoons are randomly selected to plot their tracks to visually demonstrate the prediction performance of our TyT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dimensionality Reduction with DLMNN Technique for Handling Secure Medical data in Healthcare-IoT Model 3

Dimensionality Reduction with DLMNN Technique for Handling S...

引用

3rd International Conference on Artificial Intelligence and Smart Energy, ICAIS 2023

作者： Lalithambigai, M. Kalpana, V. Sasi Kumar, A. Uthayakumar, J. Santhosh, J. Mahaveerakannan, R. Sri Krishna Adithya College of Arts and Science Department of Computer Applications Coimbatore641042 India Vel Tech University India Institute of Engineering and Technology Srinivas University Department of Cloud Technology and Data Science Surathkal Karnataka State Mukka574146 India Dhanalakshmi Srinivasan College of Engineering Department of Ai and Ds Coimbatore India Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9781665462167

Security and maintaining the integrity of sensitive patient information have emerged as major obstacles for healthcare service applications in the wake of IoT's meteoric rise in the healthcare industry. The diagnostic information included in medical photographs is of particular importance, and this research presents a hybrid security strategy to protect against such breaches. Chronic diseases such as Heart Disease (HD), cancer, and chronic respiratory sickness are the main causes of death worldwide. Those who have a heart attack suddenly have a very poor chance of surviving. As a result, this paper proposes a heart disease monitoring scheme, wherein a Deep Learning Modified Neural Network (DLMNN) centred on the Internet of Things is used to aid in the diagnosis and treatment of HD. There are three stages to implementing this strategy: First, there is encryption;second, a combination of information gain (IG) and principle component analysis (PCA) to reduce dimensionality;and third, a classification system. To begin, the patient is fitted with a wearable Internet of Things (IoT) sensor device, which simultaneously uploads its sensor data to a remote server. The sensor data is encrypted using a hybrid encryption scheme that combines the Advanced Encryption Standard (AES) and the Rivest, Shamir, and Adleman (RSA) algorithms. A DLMNN classifier is then used to classify the data after it has been decrypted. There are two types of classification outcomes. It provides information on the patient's heart and notifies the doctor in case of abnormalities. Estimated study results demonstrate that DLMNN is an improvement over previously used algorithms for HD diagnosis. The proposed AES-RSA used to support safe data transfer also yields the highest level of security, i.e. 94.32%, and does so in the quickest time for encryption and decryption. © 2023 IEEE.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

A Cutting Edge Deep Learning Models for Paddy Leaf Disease Detection and Classification

A Cutting Edge Deep Learning Models for Paddy Leaf Disease D...

引用

Artificial Intelligence For Internet of Things (AIIoT), International Conference on

作者： A. Dhanalakshmi K. Ponmozhi A. Ajmal Department of Computer Applications Kalasalingam Academy of Research and Education KrishnanKovil Tamil Nadu India Department of Data Science Vellore Institute of Technology(ICER) Bangalore Karanataka India

ISBN: (数字)9798350372120

ISBN: (纸本)9798350372137

The world’s main grain crop is rice (Oryza sativa). It provides the majority of the world’s population with nourishment and energy. Numerous rice leaf diseases are a major threat to the world’s agricultural output because they deteriorate crop quality in addition to lowering crop yield. Traditional methods of classifying and managing diseases mostly rely on laborious and subjective manual examination procedures. However, recent advancements in computer vision methods have made it possible to construct automated systems that can recognize illnesses from picture and video data. The paper emphasizes the potential application of cutting-edge models like Detectron2 to address issues with agricultural leaf disease detection. Together with other cutting-edge models, Detectron2 provides a promising means of enhancing the accuracy and effectiveness of disease diagnosis and control techniques. The use of automated disease detection systems holds the potential to reduce subjectivity in the evaluation of illnesses, optimize the allocation of resources in agriculture, and reduce dependence on human labour. These systems are able to continually learn from and adapt to changing disease patterns by incorporating complex algorithms and machine learning techniques, ensuring robust and stable agricultural operations.

关键词： Deep learning computer vision Adaptation models Computational modeling Scalability Sociology Agriculture

来源：评论

学校读者我要写书评

暂无评论

Asynchronous Parallel Stochastic Proximal Gradient Methods for Non-Convex Composite Optimization

Journal of Network Intelligence

引用

Journal of Network Intelligence 2025年第2期10卷 638-662页

作者： He, Wen-Wu Gong, Xuan-Jin Cui, Zhuo-Xu School of Computer Science and Mathematics Fujian University of Technology Fuzhou350118 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fuzhou350118 China School of Mathematics and Statistics Wuhan University Wuhan430072 China

This paper considers the parallel stochastic composite optimization for general asynchronous cases where both the objective function and the regularizer are non-convex. In particular, based on the randomized stochastic proximal gradient protocol, an asynchronous parallel algorithm termed ARSPG is proposed which incorporates well the non-convex regularization to obtain the desired oracle property. Theoretical analysis shows that ARSPG has the convergence rate in the order of O(1/ϵ2). Further, a gradient-free version termed ARSPGF is developed to handle cases where only noisy objective function values are available. The analysis shows that ARSPGF has the same order of convergence rate as that of the normal version. Experiments over benchmark data sets validate well theoretical analyses and experimental results also show interesting practical aspects of the proposed algorithms. © 2025 ISSN 2414-8105 (Online).

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis of Deep Learning based Water Potability Prediction

Design and Analysis of Deep Learning based Water Potability ...

引用

2023 International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2023

作者： Arumugam, M. Vijayakumar, P. Kannan, A.C. Velmurugan, J. Arun, G. Rohith Bhat, C. Kongu Engineering College Department of Computer Technology - Pg Perundurai India Kongu Engineering College Department of Master of Computer Applications Tamil Nadu Perundurai638060 India Psna College of Engineering and Technology Department of Electrical and Electronics Engineering Dindigul624622 India Erode Sengunthar Engineering College Department of Artificial Intelligence and Data Science Thuduppathi638057 India Saveetha School of Engineering Simats Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350300857

According to the United Nations, having access to clean water for consumption is a fundamental human right. General Assembly in 2010. The importance of safe drinking water cannot be overstated. Unsafe drinking water access is a significant public health concern, especially in poor nations. In many regions of the world, waterborne illnesses including cholera, typhoid fever, and dysentery are important causes of illness and death. These diseases are especially dangerous for children, who are more vulnerable to their effects. In addition, a lack of access to clean drinking water can result in other health issues like stunted growth and malnutrition. Access to safe drinking-water is also a key component of effective policy for health protection at all levels, whether it is at the national, regional, or local level. Policies aimed at improving access to safe drinking-water can include measures such as water quality testing, water treatment, and the provision of clean water sources. Investments in water supply and sanitation can have a positive economic impact, especially in areas with inadequate access to clean drinking water. The costs of implementing the treatments may be outweighed by the reductions in unfavorable health impacts and medical expenses that may result from these investments. In conclusion, having access to clean drinking water is crucial for encouraging wellness, reducing waterborne illnesses, and raising standard of living in general. The input to the DNN could be the various water quality parameters, such as pH, hardness, chloride content, and total dissolved solids, while the output would be a binary classification indicating whether the water is potable or not. The DNN would need to be trained on a large and diverse dataset of water samples to accurately classify new samples. © 2023 IEEE.

关键词： Potable water

来源：评论

学校读者我要写书评

暂无评论

A new network intrusion detection system based on auto-encoding and variance analysis

A new network intrusion detection system based on auto-encod...

引用

IEEE International Conference on Civil Aviation Safety and Information Technology (ICCASIT)

作者： Dequ Chen Ming Zhang Fujian Provincial Key Laboratory of Big Data Mining and Applications/School of Computer Science and Mathematics Fujian University of Technology Fuzhou China

In today's big data era, ensuring the network security of information technology (IT) communication facilities is one of the most challenging issues. In fact, with progress in technology, hackers have developed increasingly complex and risky network attacks, making malicious access identification a very tired task. Under various threats, the existing analysis methods encounter many challenges in detecting and mitigating these illegal accesses. This work presents a new network intrusion detection system (IDS) which combines deep learning method and mathematical strategy. Indeed, our IDS makes full use of data analysis, mathematical modeling, and deep learning to select and optimize features that are more relevant for classification. We use NSL-KDD dataset to test the performance of the IDS. The experimental results show that our proposed method has better performance compared with traditional deep learning, machine learning and recently proposed advanced methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-level Distance Metric Learning for Few-shot Spoken term classification 7

Multi-level Distance Metric Learning for Few-shot Spoken ter...

引用

2022 7th International Conference on Electronic Technology and Information science, ICETIS 2022

作者： Wu, Yiqi Ma, Zhongchen Mao, Qirong School of Computer Science and Communication Engineering Jiangsu University Jiangsu Zhenjiang212000 China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications Jiangsu Zhenjiang212000 China

ISBN: (纸本)9783800757794

Spoken term classification has attracted great attention of researchers because of its wide application in real life. Traditional methods use a deep neural network trained with tremendous samples to classify a particular keyword which may not be applicable in case of insufficient samples and restrict the system from recognizing new or user-defined keywords. Few-shot learning algorithm is then applied to this speech task since it can use only a few examples to adapt to classifying new classes. Metric learning for few-shot learning aims to learn a metric in episode learning such that the distance between the positive pair of each episode is closed and the distance between the negative pair of each episode is far away. However, due to various pronunciation, speed or intonation, some spoken samples may be extremely dissimilar to its positive sample, but very similar to its negative sample, leading these samples to be ignored or overly influenced in metric learning. Therefore, to cope with this problem we propose a multi-level distance regularized metric learning method for few-shot spoken term classification. It explicitly disturbs a learning procedure by regularizing pairwise distances between embedding vectors into multiple levels. In this way, the degree of similarity between a pair can be fully utilized and the importance of each sample in metric learning is considered in a balanced manner. Multi-level Distance Regularization with simple Prototypical Network achieves the state-of-the-art performance in benchmark dataset: Google Speech Commands dataset. © VDE VERLAG GMBH ∙ Berlin ∙ Offenbach.

关键词： Learning algorithms

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：