检索结果-内蒙古大学图书馆

4th IEEE Global Conference for Advancement in technology, GCAT 2023

作者： Sinchana, N.S. Jeevitha, K. Kumar Swamy, S. Kodipalli, Ashwini Rao, Trupthi Department of Computer Science and Engineering Global Academy of Technology Karnataka Bangalore India Department of Artificial Intelligence and Data Science and Engineering Global Academy of Technology Karnataka Bangalore India

ISBN: (纸本)9798350305258

Melanoma is a type of cancer known to be the most dangerous and is called the life threatening disease. Every year, there is rise in number of people being diagnosed with melanoma which is more frequent among the males than the females. This type of skin cancer has an uncontrollable growth of cells that can grow really faster, if not treated it can spread all over the body. Hence this disease needs to be detected at the early stages so that the patients can be treated properly. Machine learning approaches were applied to detect skin cancer but the drawbacks were that the performance to identify the cancer was limited. Therefore, we constructed a model by utilizing a Convolution Neural Network of the most advanced deep learning where we conduct investigations for discovering the melanoma skin cancer on the basis of the skin lesion. In this research, using transfer learning techniques ResNet and VGG based models have been brought together for melanoma skin detection. The procedures were applied to train these models using optimizers like RMSprop, Adam, Stochastic Gradient Descent (SGD) and findings were presented with the support of accuracy, confusion matrix, sensitivity, specificity and precision. © 2023 IEEE.

关键词： Convolutional Neural Network (CNN) Deep Learning Melanoma skin cancer Transfer Learning

来源：评论

学校读者我要写书评

暂无评论

Streamlined Data Pipeline for Real-Time Threat Detection and Model Inference 17

Streamlined Data Pipeline for Real-Time Threat Detection and...

引用

17th International Conference on COMmunication Systems and NETworkS, COMSNETS 2025

作者： Singh, Rajkanwar Aravindan, V. Mishra, Sanket Singh, Sunil Kumar VIT-AP University School of Computer Science & Engineering Andhra Pradesh Amaravati India Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Department of Computer Science and Engineering Karnataka Manipal India

ISBN: (纸本)9798331531195

Real-time threat detection in streaming data is crucial yet challenging due to varying data volumes and speeds. This paper presents an architecture designed to manage large-scale, high-speed data streams using deep learning and machine learning models. The system utilizes Apache Kafka for high-throughput data transfer and a publish-subscribe model to facilitate continuous threat detection. Various machine learning techniques, including XGBoost, Random Forest, and LightGBM, are evaluated to identify the best model for classification. The ExtraTrees model achieves exceptional performance with accuracy, precision, recall, and F1 score all reaching 99% using the SensorNetGuard dataset within this architecture. The PyFlink framework, with its parallel processing capabilities, supports real-time training and adaptation of these models. The system calculates prediction metrics every 2, 000 data points, ensuring efficient and accurate real-time threat detection. © 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

Personality Prediction Using Machine Learning 1

Personality Prediction Using Machine Learning

引用

1st International Conference on Computational Intelligence for Information, Security and Communication Applications, CIISCA 2023

作者： Pooja, K. Rakshitha, G.H. Spoorthi, S. Kamal, Shoaib Rao, Trupthi Ashwini, K. Global Academy of Technology Department of Computer Science and Engineering Bangalore India Global Academy of Technology Department of Artificial Intelligence and Data Science Bangalore India

ISBN: (纸本)9798350339727

With the growth of social networks, a wide range of methodologies have been developed to describe users' personalities only based on their language and social media use habits. Persona prediction is very popular these days. It examines consumer behaviour and records the user's ideas, emotions, and so on. There has been a sufficient amount of research in this field over the years. This survey provides an overview of the numerous methods tried to predict personality and behaviour from the use of the social media content. The capacity to anticipate the personality attributes of users can help create a variety of specialised goods or services. The concluding phase then provides the future characteristics and directives. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Machine Learning Algorithms to Predict Water Potability 1

Performance Analysis of Machine Learning Algorithms to Predi...

引用

1st International Conference on Computational Intelligence for Information, Security and Communication Applications, CIISCA 2023

作者： Parnika, J. Devamane, Shridhar B Ramya, C.N. Swarna Laxmi, M.G. Global Academy of Technology Dept. of Computer Science and Engineering Karnataka Bengaluru India

ISBN: (纸本)9798350339727

The survival of all living organisms, industry and agriculture is dependent on freshwater availability. A crucial step in the management of freshwater is the examination of the water's quality. According to the annual report of the World Health Organization, a lack of safe drinking water is resulting in the illness or death of many people, particularly children and pregnant women. Before the water is used for any purpose, including chemical spraying (for pesticides, etc.), or drinking water, it is essential to test its quality. Finding water that is safe to consume can be done to some extent by testing the water's quality. Therefore, water quality testing is essential. In this paper, we have carried out the implementation of 3 machine learning algorithms to check for potability of water after balancing, selecting important features using the Univariate Selection method and standardizing the data. Random Forest Classifier gave the maximum accuracy of 88.75%. The main objective of our work is to increase the accuracy and demonstrate the performance analysis of the considered algorithms' accuracy in this paper along with the existing works. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Towards Mutation Testing of Embedded Software: A Framework and Case Study 35

Towards Mutation Testing of Embedded Software: A Framework a...

引用

35th IEEE International Symposium on Software Reliability engineering Workshops, ISSREW 2024

作者： Jiang, Wei Dong, Sijin Zhang, Jiaming Tang, Jin Zhang, Zichao Sun, Chang-Ai Zhang, Xiaoyi China Electronics Technology Group Corporation Information Science Academy Beijing China University of Science and Technology Beijing School of Computer and Communication Engineering Beijing China

ISBN: (纸本)9798350367041

Embedded software commonly executes safety-critical tasks and thus is expected to be highly reliable, which calls for stronger quality assurance techniques. As a fault-based testing technique, mutation testing is widely recognized to have stronger fault detection capability than those coverage or function-based testing techniques. However, some unique features of embedded software, such as limited hardware resources, real-time requirements, and differences between development and execution environments, pose challenging issues for the application of mutation testing. In this study, we explore the application of mutation testing to embedded software. As a result, we propose a mutation testing framework for embedded software, and evaluate the simulation capability of mutation operators for real-life faults in embedded software. A case study was conducted on a realistic open-source embedded software to evaluate the effectiveness and efficiency of the proposed technique. The experimental results demonstrate that mutation testing is able to detect various faults of embedded software, thus delivering a promising supplement for embedded software testing. © 2024 IEEE.

关键词： Case Study Embedded software Mutation Operators Mutation testing Software testing

来源：评论

学校读者我要写书评

暂无评论

Provably Secure Efficient Key-Exchange Protocol for Intelligent Supply Line Surveillance in Smart Grids

引用

IEEE Internet of Things Journal 2025年第12期12卷 21784-21792页

作者： Ayub, Muhammad Faizan Li, Xiong Mahmood, Khalid Alenazi, Mohammed J.F. Das, Ashok Kumar Wang, Guijuan University of Electronic Science and Technology of China School of Computer Science and Engineering Sichuan Chengdu12599 China National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Yunlin Douliu64002 Taiwan Department of Computer Engineering Riyadh11451 Saudi Arabia International Institute of Information Technology Center for Security Theory and Algorithmic Research Hyderabad500 032 India Korea University College of Informatics Department of Computer Science and Engineering Anam-ro Seoul145 Korea Republic of Ministry of Education Shandong Computer Science Center Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Jinan250353 China Shandong Provincial Key Laboratory of Industrial Network and Information System Security China Shandong Fundamental Research Center for Computer Science Jinan 250353 China

Intelligent supply line surveillance is critical for modern smart grids. Smart sensors and gateway nodes are strategically deployed along supply lines to achieve intelligent surveillance. They collect data continuously and transmit it to the control centre in real-time. It enables real-time monitoring, fault detection, and efficient energy management across distribution networks. This advanced surveillance system ensures continuous monitoring of supply lines, detecting anomalies, and optimizing operations to maintain the stability and reliability of the smart grid. However, the reliance of all participating nodes on public communication channels to transmit supply line surveillance data exposes these systems to critical cyber attacks. These cyber attacks include impersonation, physical tampering, ephemeral secret leakage, and desynchronization attacks. To address these issues, existing key-exchange protocols often fail to ensure robust security while imposing high computation and communication overheads, limiting their practicality for resource-constrained environments. Therefore, we propose a secure and efficient key exchange and tamper-resistant authentication protocol using Elliptic Curve Cryptography (ECC) and Physical Unclonable Functions (PUFs). The PUF mechanism provides robust resistance against physical tampering and cloning attacks, ensuring enhanced physical security for supply line devices. We validate the security robustness of the devised protocol using the Random or Real (ROR) model. Furthermore, informal security analysis demonstrates the protocol's robustness in rigorously resisting various attacks, including physical tampering, impersonation, ephemeral secret leakage and desynchronization. Moreover, we determine the performance evaluation that reveals the protocol's superior efficiency compared to competing protocols, achieving significant reductions of 28.64% in computation overhead and 9.96% in communication overhead. © 2014 IEEE.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

Interpretable Predictions for Crime Categories Using Log Loss Approach for Imbalanced Target Feature 2

Interpretable Predictions for Crime Categories Using Log Los...

引用

2nd IEEE International Conference on Contemporary Computing and Communications, InC4 2024

作者： Manasa, A. Sen, Snigdha Global Academy of Technology Department of Computer Science and Engineering Karnataka Bengaluru India Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Department of Information Technology Manipal India

ISBN: (数字)9798350383652

ISBN: (纸本)9798350383652

Crime indicates activities that infringe laws and regulations constituted by a governing authority. These wrongdoings can range from minor aberrations such as petty theft to more serious crimes like assault, robbery, or murder. Understanding crime patterns, causes, and trends is important for creating effective law enforcement strategies and enforcing policies that facilitate to a risk-free and stable society. This paper explores the interpretability of crime category predictions generated by XGBoost and Random Forest models on San Francisco crime data ranging 12 years. Notably, in comparison to other models, such as k-Nearest Neighbors (KNN), Stochastic Gradient Descent(SGD) and Naïve Bayes, our XGBoost and Random Forest models featured superior predictive excellence, Obtaining competitive log-loss scores of 2.277761 and 2.283956, respectively, to augment interpretability we have employed Local Interpretable Model-agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) to clarify the decision-making processes of these models. This interpretability analysis would definitely add a deeper insight into the contributing factors of model's predictive behavior towards crime rate prediction. Additionally, we have dealt with imbalanced target feature as well. In comparison to existing research in the field, our work stands out by introducing advanced interpretability techniques, LIME and SHAP, enhancing transparency in crime prediction models. This innovative approach surpasses traditional methods, providing a more comprehensive understanding of crime dynamics and achieving superior predictive excellence. Innovation is introduced through the incorporation of advanced interpretability techniques, specifically Local Interpretable Model-agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP). © 2024 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

GRU-Based Winner Subcarrier Detection in Frequency Domain Contention 24

GRU-Based Winner Subcarrier Detection in Frequency Domain Co...

引用

7th International Conference on Information science and Systems, ICISS 2024

作者： Yao, Shumin Zhao, Qinglin Xu, Zezhou Feng, Li Li, Guanghui Tian, Liwei Sun, Yi School of Computer Science and Engineering Macau University of Science and Technology China Department of Broadband Communication Pengcheng Laboratory China School of Artificial Intelligence and Computer Science Jiangnan University China Department of Computer Guangdong University of Science and Technology China Institute of Computing Technology Chinese Academy of Sciences China

ISBN: (纸本)9798400717567

Single-carrier frequency domain contention (S-FDC) is an efficient wireless contention mechanism based on orthogonal frequency-division multiplexing (OFDM). In each round of S-FDC, each node randomly selects and signals on one of the OFDM subcarriers while listening to all subcarriers simultaneously. Each node independently detects the activated subcarrier with the smallest index and regards it as the winner subcarrier. Accurately detecting the winner subcarrier is crucial to ensuring the functionality of the network. However, it is extremely difficult in practice due to power leakage problems that arise from frequency asynchronization among nodes. In this paper, we propose a gated-recurrent-unit (GRU)-based model that incorporates S-FDC’s unique features as domain knowledge to enable accurate winner subcarrier detection. Extensive simulation experiments verify that our DL model is effective and outperforms state of the art. This research highlights the potential of DL in improving wireless communication systems. © 2024 Copyright held by the owner/author(s).

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Analysis of Multi-Class Convolution Neural Network on Garbage Classification System

Analysis of Multi-Class Convolution Neural Network on Garbag...

引用

2023 IEEE International Conference on Network, Multimedia and Information technology, NMITCON 2023

作者： Vikas, K.R. Ullas, P. Sri Sai Teja, M.S. Kumar Swamy, S. Kodipalli, Ashwini Rao, Trupthi Global Academy of Technology Department of Computer Science and Engineering Karnataka Bangalore India Global Academy of Technology Department of Artificial Intelligence and Data Science and Engineering Karnataka Bangalore India

ISBN: (纸本)9798350300826

The buildup of solid waste in metropolitan areas is a major worry that, if not effectively handled, might lead to environmental contamination and be dangerous to human health. To manage a range of waste products, it's crucial to have an advanced/intelligent waste management system. The act of separating garbage into its many components is one of the most crucial parts of waste management, and it is often carried out manually by hand-picking. To simplify this, we suggest a customized architecture for multiclass Convolutional Neural Networks (CNNs). The design includes elements that are individual-specific, enabling the model to adjust to the traits of each class. Extensive evaluation has shown that our CNN architecture, utilising a personalised approach, outperforms traditional CNN models like ResNet50 and VGG16 in multiclass classification situations. The effectiveness and resilience of our suggested architecture are demonstrated by experimental results on our dataset, opening the path for increased classification accuracy of 71.15%. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Customized CNN Model for Alzheimer's Disease Stages Classification and Comparison with Transfer Learning 1

Customized CNN Model for Alzheimer's Disease Stages Classifi...

引用

1st International Conference on Recent Advances in Information technology for Sustainable Development, ICRAIS 2023

作者： Sindhu, B. Prasad, Rishitha Kodipalli, Ashwini Kumar Swamy, S. Rao, Trupthi Global Academy of Technology Department of Computer Science and Engineering Karnataka Bangalore India Global Academy of Technology Department of Artificial Intelligence and Data Science and Engineering Karnataka Bangalore India

ISBN: (纸本)9798350306637

Alzheimer's disease, the predominant form of dementia, progressively worsens over time, initially causing mild memory loss and eventually severely hampering daily tasks and communication abilities. This degenerative condition affects regions of the brain integral to cognition, memory, and language. Due to its intricate nature, symptom experiences and progression can vary among individuals. This study proposes a predictive model to discern Alzheimer's stages. Leveraging 'deep learning' techniques through convolutional neural networks (CNNs), the algorithm is trained on an extensive dataset of brain MRI scans. It learns to recognize pivotal features and correlate them with diverse disease phases. The Customized CNN model's accuracy of 94.37% surpasses alternative machine learning methods, including transfer learning. This precision empowers early prediction, significantly benefiting patient care and therapeutic strategies, thereby enhancing Alzheimer's disease management. © 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

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：