检索结果-内蒙古大学图书馆

5th International Conference on Data science, Machine Learning and Applications, ICDSMLA 2023

作者： Mahender, Udutala Arivalagan, S. Sathiyasuntharam, V. Sudhakar, P. Annamalai University Tamilnadu Chidambaram India Department of Computer Science and Technology Annamalai University Tamilnadu Chidambaram India Department of Cyber Security CMR Engineering College Hyderabad India Department of Computer Science and Engineering Annamalai University Tamilnadu Chidambaram India

ISBN: (纸本)9789819780426

Major Depressive Disorder (MDD) is a significant global mental health concern predicted to become the leading mental health condition by 2030. It is characterised by persistent sadness, hopelessness, and a lack of interest in daily activities. The current diagnostic procedures for MDD are often unreliable, subjective, and prone to biases, emphasising the urgent need for accurate prediction methods. Predicting MDD is crucial for various reasons: it enables early detection, including identifying milder forms of depression, facilitating timely interventions and preventing the condition from worsening. Additionally, accurate prediction contributes to a deeper understanding of the disorder's neurobiological and psychological underpinnings, potentially leading to more effective treatments. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Fake News Detection on Social Media Using a Stacking Model 5th

Fake News Detection on Social Media Using a Stacking Model

引用

5th International Conference on computer and Communication Technologies, IC3T 2023

作者： Ramesh, G.S. Supriya, K.H.S. Akash, P. Rukmananda Reddy, A. Tejaswini, V. Dharmireddi, Srinivasarao Department of Computer Science and Engineering VNR VJIET Telangana Hyderabad India Department of Cyber Security MasterCard St. LouisMO63304 United States

ISBN: (纸本)9789819997060

Fake news has existed since long before the Internet was invented. It can be defined as "fictitious articles deliberately fabricated to deceive readers". While some news may have a grain of truth, it frequently lacks any contextual information. They may not contain any sources which can be verified. Some of the reports may contain straightforward factual statements, but they are intentionally worded in an inflammatory sense, often omitting crucial information, or just give one point of view. We tried to understand the nuances in fake news in this research paper by its language characteristics. Initially the news articles content was pre-processed using techniques like Lemmatization and TF-IDF. The data was then classified using a Stacking Classifier, using Naïve Bayes, SVM, and Decision Tree is used as the base models and Logistic Regression is used as Metamodel. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Detection using Domain-Adversarial Training (DANN) with Invariant Risk Minimization (IRM) Hybrid Approach 3

Breast Cancer Detection using Domain-Adversarial Training (D...

引用

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

作者： Akash, K.V. Daniel, Esther Seetha, S. Durga, S. Karunya Institute of Technology and Sciences Division of Computer Science and Engineering Coimbatore India Cmr Institute of Technology Department of Information Science & Engineering India Amrita Vishwa Vidyapeetham Tifac Core in Cyber Security Amrita School of Engineering India

ISBN: (纸本)9798331509675

The breast cancer detection performs a key function in the health care network. The precise and early detection of cancer in the breast could aid to save life of the sufferer. The traditional machine learning methods struggle due to the data used to train is different from data used later this is known as Domain shifts. This project uses a hybrid model known as Domain-Adversarial Training of Neural Networks (DANN) with Invariant Risk Minimization (IRM) Hybrid Method to identification of the tumor in the breast. Through integrating the (DANN) and IRM works perfectly among the various type of data and also with the various image from the various sources. This model is more precise and reliable than any other older *** that this model act as an effective tool for detecting the breast cancer in the early stages. © 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

Deformable Dual Graph Aggregation Transformer Convolutional Networks with Spider Wasp Optimizer for Ovarian Tumor Classification Using Magnetic Resonance Imaging

Biomedical Materials and Devices

引用

Biomedical Materials and Devices 2025年 1-19页

作者： Shanmugaveni, V. Jotheeswari, M. Abarnaswara, R. VijayaKumar, M. Manojanani, A. Department of Computer Science and Engineering (Cyber Security) Dr. Mahalingam College of Engineering and Technology Tamil Nadu Pollachi India Department of Computer Science and Engineering PSNA College of Engineering and Technology Tamil Nadu Dindigul India Department of Artificial Intelligence & Data Science Dr. Mahalingam College of Engineering and Technology Tamil Nadu Pollachi India Department of Computer Science and Engineering RVS Technical Campus Tamil Nadu Coimbatore India

The diagnosis of Ovarian Tumor (OT) remains a significant challenge as there is presently no practical non-invasive technique to determine true benign or malignant lesions before treatment. This study proposes a unique Deformable Dual Graph Aggregation Transformer Convolutional Network (DeDGATCNet) with Spider Wasp Optimizer (SWO) for the classification of ovarian tumors acquired from magnetic resonance imaging (MRI). In contrast to traditional deep learning models, DeDGATCNet + SWO directly integrates bending graph-based forming transformer convolutional learning and improves representation for better classification. The SWO is combined to optimize the parameters of the network, thereby improving its performance. The procedures include pre-processing the MRI data from the study of ovarian tumor TCGA-OV datasets with an Adaptive Bilateral Texture Filter (ABTF) for removing artifacts and normalization of intensity, accompanied by a segment using a Masked-Attention Mask Transformer (MAMT). Feature extraction is achieved through a One-Dimensional Quaternion Discrete Fourier Transform (1D-QDFT), which captures features from both the spatial and frequency domains. DeDGATCNet + SWO performance is way ahead and sets a new accuracy record of 99.9% for state-of-the-art models. This research introduces a new type of hybridization between deformable graph transformers, quaternion-based spectral analysis, and nature-inspired optimization techniques, setting non-invasive OT at a new height for classification and improving early diagnosis. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Adaptive bilateral texture filter Deformable dual graph aggregation transformer convolutional networks Masked-attention mask transformer One-dimensional quaternion discrete fourier transform

来源：评论

学校读者我要写书评

暂无评论

Smart Water-Powered Renewable Energy System with IoT Integration

Smart Water-Powered Renewable Energy System with IoT Integra...

引用

2024 International Conference on Decision Aid sciences and Applications, DASA 2024

作者： Ahmed, Amjed Abbas Najim, Ali Hamza Ibraheem, Ahmed Salman Ali Alheeti, Khattab M. Mohd Satar, Nurhizam Safie Abdallah Hashim, Aisha Hassan Universiti Kebangsaan Malaysia Center for Cyber Security Faculty of Information Science and Technology Bangi Malaysia Department of Computer Techniques Engineering Baghdad Iraq Department of Computer Technical Engineering Al-Diwaniyah Iraq Department of Computer Technical Engineering Baghdad Iraq College of Computer and Information Technology Computer Networking Systems Department University of Anbar Anbar Iraq Center for Cyber Security Faculty of Information Science and Technology Bangi43600 Malaysia International Islamic University Malaysia Faculty of Engineering Department of Electrical and Computer Engineering Selangor Malaysia

ISBN: (纸本)9798350369106

An advanced hybrid renewable energy collecting and storage system prototype that utilizes water flow as its primary power source. Additionally, the system incorporates an energy monitoring system based on the Internet of Things (IoT) technology. The device effectively harnesses energy from the movement of water, storing it for future use in low-voltage applications. It demonstrates a maximum daily energy capture capacity of about 100Wh. The energy monitoring system, based on the Internet of Things (IoT), enables the real-time and remote monitoring of energy harvesting and usage. We thoroughly assessed the energy harvesting component across different situations to identify the crucial parameters that impact energy output. The results of our study demonstrate that several elements, including the spatial separation 'between the energy harvester and the water source, Water flow' speed, sensor orientation, and sensor density, all play significant roles in determining the quantity of energy collected. This research shows that it is possible to integrate IoT technology with hydropower renewable energy systems. It provides significant perspectives on enhancing energy extraction efficiency in practical scenarios. © 2024 IEEE.

关键词： harvesting renewable energy IoT storage energy water flow energy

来源：评论

学校读者我要写书评

暂无评论

Multi-Layer Perceptrons and Convolutional Neural Networks Based Side-Channel Attacks on AES Encryption

Multi-Layer Perceptrons and Convolutional Neural Networks Ba...

引用

2023 International Conference on engineering Technology and Technopreneurship, ICE2T 2023

作者： Ahmed, Amjed Abbas Hasan, Mohammad Kamrul Center for Cyber Security Faculty of Information Science and Technology Bangi 43600 Malaysia Department of Computer Techniques Engineering Baghdad Iraq

ISBN: (纸本)9798350304107

Side - channel attacks (SCA) exploit vulnerabilities introduced by insecure implementations in order to get information about the data that is being processed or the data itself via device leakages. The majority of modern attack techniques use AES systems, and several studies have exploited side-channel leakages. Exploiting leakages for the first and final rounds, often known as outer rounds, is frequently the foundation of the strategy. There is a possibility that outer round leakages cannot be attacked due to inadequate countermeasures or device design. The attacker has to focus their attention on the inner rounds. Deep learning side-channel attacks, whether they include profiling or not, have the potential to recover secret keys stored in cryptographic devices that use masked AES. Mask value profiling is being used in more recent techniques for the extraction of secret keys. The objective of our research is to defeat masked AES by deep learning methods like as multi-layer perceptrons and convolutional neural networks are used. In an environment when profiling is not taking place, we extract sensitive information using DDLA. The HW (Hamming Weight) model is used by our approach in order to carry out DDLA by means of an innovative binary labeling strategy. Using the ChipWhisperer power traces and the ASCAD dataset, we show profiling and non-profiling attacks. The accuracy of key recovery is at its maximum when the AES implementation is either masked or unmasked. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning of non-additive joint steganographic embedding costs with attention mechanism

引用

science China(Information sciences) 2023年第3期66卷 273-286页

作者： Weixuan TANG Bin LI Weixiang LI Yuangen WANG Jiwu HUANG Institute of Artificial Intelligence and Blockchain Guangzhou University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen Institute of Artificial Intelligence and Robotics for Society School of Computer Science and Cyber Engineering Guangzhou University

Image steganography is the art and science of secure communication by concealing information within digital images. In recent years, the techniques of steganographic cost learning have developed rapidly. Although the existing methods can learn satisfactory additive costs, the interplay of different pixels' embedding impacts has not been considered, so the potential of learning may not be fully exploited. To overcome this limitation, in this paper, a reinforcement learning paradigm called Jo Po L(joint policy learning) is proposed to extend the idea of additive cost learning to a non-additive situation. Jo Po L aims to capture the interactions within pixel blocks by defining embedding policies and evaluating contributions of embedding impacts on a block level rather than a pixel level. Then, a policy network is utilized to learn optimal joint embedding policies for pixel blocks through interactions with the environment. Afterwards,these policies can be converted into joint embedding costs for practical message embedding. The structure of the policy network is designed with an effective attention mechanism and incorporated with the domain knowledge derived from traditional non-additive steganographic methods. The environment is responsible for assigning rewards according to the impacts of the sampled joint embedding actions, which are evaluated by the gradient information of a neural network-based steganalyzer. Experimental results show that the proposed non-additive method Jo Po L significantly outperforms the existing additive methods against both feature-based and CNN-based steganalzyers over different payloads.

关键词： information hiding non-additive steganography steganalysis cost learning image processing

来源：评论

学校读者我要写书评

暂无评论

Literature Review on Packet Sniffing: Essential for cybersecurity & Network security

Literature Review on Packet Sniffing: Essential for Cybersec...

引用

Intelligent Communication Technologies and Virtual Mobile Networks (ICICV), International Conference on

作者： Ranju Shaw Suraiya Parveen Department of Computer Science Engineering with specialization in Cyber Forensic & Information Security Jamia Hamdard University Delhi India Department of Computer Science Engineering Faculty at Jamia Hamdard University SEST Delhi

In the realm of cybersecurity and network security, the significance of monitoring and analyzing network traffic cannot be overstated Network packet sniffing, a technique employed to capture and inspect data packets traversing a network, has emerged as an imperative tool for understanding network behavior, identifying vulnerabilities, and enhancing overall security. This study analyzes packet sniffing by exploring its role in modern cybersecurity practices. By analyzing packet sniffing mechanisms, including its methodologies and potential applications, this res earch sheds light on its effectiveness as a proactive security solution. Furthermore, the study examines the ethical considerations surrounding packet sniffing, addressing concerns related to user privacy and data protection. It also investigates the legal aspects that govern the use of packet sniffing techniques, ensuring compliance with regulations while maximizing its benefits. Through case studies and real-world examples, this research illustrates how packet sniffing can be leveraged to detect network anomalies, thwart malicious activities, and fortify network infrastructures. By presenting a comprehensive overview of packet sniffing's capabilities and limitations, this study equips cybersecurity practitioners with the knowledge needed to make informed decisions about its integration into their defensive strategies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Auto-scalable and fault-tolerant load balancing mechanism for cloud computing based on the proof-of-work election

引用

science China(Information sciences) 2022年第1期65卷 131-146页

作者： Xiaoqin FENG Jianfeng MA Shaobin LIU Yinbin MIAO Ximeng LIU School of Cyber Engineering Xidian University State Key Laboratory of Cryptology Shaanxi Key Laboratory of Network and System Security Xidian University College of Mathematics and Computer Science Fuzhou University

Load balancing mechanism in technologies such as cloud computing has provided a huge opportunity for the development of large-scale projects. Although the conventional view is to build mechanisms that adopt a dynamic load balancing strategy, existing strategies cannot automatically scale platform(network) servers(nodes) to adapt for dynamic requests, but only guarantee load balancing for the pre-deployed nodes, thereby increasing resource consumption and decreasing networks' efficiency. We contend that existing load balancing mechanisms are inadequate for deploying dynamic applications. In this regard, we first adopt both load balancing and cloud computing virtualization technologies to modularly design a load balancing mechanism that provides a dynamically auto-scalable solution for large-scale and dynamic computing scenarios. Furthermore, we adopt the proof-of-work consensus, for a novel use during the lifecycle of master nodes in case of system failure caused by a failed master node, to demonstrate a fault-tolerant load balancing mechanism. We theoretically evaluate the security requirement of our mechanism and analyze its performance. Experimental results show that the mechanism supports auto-scalability and has a better performance compared to existing mechanisms such as the ordinary cluster.

关键词： cloud computing load balancing auto-scalable proof-of-work fault-tolerant

来源：评论

学校读者我要写书评

暂无评论

HCL-Net: A Single Image Rain Removal Algorithm Based on Channel Attention and Multi-scale Feature Fusion 6

HCL-Net: A Single Image Rain Removal Algorithm Based on Chan...

引用

6th IEEE International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2023

作者： Huang, Jin He, Pei Guangzhou University School of Cyberspace Security Guangzhou China Guangzhou University School of Computer Science and Cyber Engineering Guangzhou China

ISBN: (纸本)9798350325485

The investigation of rain removal from pictures has always been a pivotal matter in the domain of computer vision. Nevertheless, the majority of existing algorithms employ encoder-decoder structures that have been trained on artificially synthesized datasets, without taking into account the harm that heavy rain can cause to actual images. Batch normalization is unsuitable for low-level computer vision duties, and skip connections in encoder-decoder architectures are not always appropriate for rain removal. This has resulted in setbacks in relevant domains. In this article, we propose a groundbreaking single-image rain removal algorithm that is founded on channel attention and multi-scale feature fusion. Initially, we build a contextualized dilated restoration block to restore the rain-Affected image during the feature extraction phase. Secondly, we create a half-instance normalization residual block to conserve more scale information and to augment the modeling capacity of the model, without sacrificing performance while hastening model convergence. Finally, in response to the view that simple skip connections may not always be advantageous, we have constructed a LeakyReLU channel attention block to aggregate information and enhance the effectiveness of skip connections. Our comprehensive experiments on authentic rain datasets and images provide evidence that our model can more proficiently remove rain streaks and accumulations from pictures, in contrast to the existing methods. © 2023 IEEE.

关键词： Image reconstruction

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：