检索结果-内蒙古大学图书馆

3rd IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2023

作者： Sekar, R. Harikrishnan, P.R. Acharjya, Kalyan Presidency University Department of Electronics and Communication Engineering Karnataka Bangalore India Department of Computer Science and Information Technology Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India

ISBN: (纸本)9798350343274

Improvement methods based on picture segmentation are commonly employed in medical image analysis. Pixels are commonly put together in groupings of varied sizes to generate an image. The available pixel intensities in an image allow for the separation of distinct image regions. Edge-based and boundary-based segmentation methods are the two primary classifications of this type of analysis. The boundary-based segmentation technique is the more widespread of the two. The image of the tumor needs to be segmented into numerous fragments, each of which can then be analyzed separately. It can annotate data and locate locations of interest in medical image processing. The issues with the existing paper are addressed in the suggested study. Feature extraction using GLCM has been used for classification of tumor images. Analysis of data in segments is routine. The CNN classifier's segments are labelled by an analytical procedure. The proposed method boosts information quality and reduces error-prone training in MRI brain tumor pictures by increasing the learning coefficient of the back propagation layer in the neural network. As a result, the current CNN Shallow Net architecture achieves a higher classification rate of 99.61% thanks to its increased specificity (98.56%) and sensitivity (98.12%). The deep web achieves a segmentation accuracy of 99.58 percent, with an additional diagnostic accuracy of 98.5 percent in identifying cancerous spots. © 2023 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Examination of Cloud-Enabled Frameworks for Power Management Systems: Current State, Challenges, and Forward-Looking Guidance in Big Data Analytics

A Comprehensive Examination of Cloud-Enabled Frameworks for ...

引用

2023 International Conference on System, Computation, Automation and Networking, ICSCAN 2023

作者： Singh, Vaishali Dass, Sandhya Prakash, Febin Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Presidency University Department of Electronics and Communication Engineering Karnataka Bangalore India Department of Computer Science and Information Technology Bangalore India

ISBN: (纸本)9798350315127

A Comprehensive Examination of Cloud-Enabled Frameworks for Power Management Systems: Current State, Challenges, and Forward-Looking Guidance in Big Data Analytics' examines cloud-enabled power management system frameworks in depth. This article provides a thorough evaluation of cloud-enabled power management system frameworks. This article examines the present state of power management systems from a range of perspectives. It emphasizes the importance of shifting away from traditional, locally focused methodologies and toward big data analytics-driven, cloud-based solutions. In this study, we look at the wide-ranging implications that cloud-enabled frameworks have had on a variety of sectors, including smart grids and data centers. It is hard to exaggerate the significance of these frameworks in handling the exponential expansion of data while also improving efficiency, scalability, and adaptability. This research acknowledges the relevance of data security and privacy, the necessity for interoperability and standardization in this rapidly expanding environment, and the difficulty in managing the huge volumes of data created by contemporary energy systems. This is achieved while stressing the numerous benefits of cloud-hosted data centers and intelligent grids. The paper also underlines how advantageous cloud-based data centers and smart grids are to their respective users. The essay proposes potential solutions to these difficulties in the form of future recommendations. © 2023 IEEE.

关键词： Data Analytics

来源：评论

学校读者我要写书评

暂无评论

Grocery Purchase through Blockchain System 7

Grocery Purchase through Blockchain System

引用

7th IEEE Pune Section International Conference, PuneCon 2024

作者： Kumar, Boddu Manoj Rajeswari, G. Thanush, B.V. Krishna, Vamsi Sree, E. Divija Balakrishnan, Arunkumar Sathyabama Institute of Science and Technology School of Computer Science Engineering with Blockchain Technology Tamil Nadu Chennai600119 India Sathyabama Institute of Science and Technology School of Computer Science Engineering Tamil Nadu Chennai600119 India VIT-AP University School of Computer Science Engineering India Crm Institute of Technology School of Computer Science Engineering Karnataka Bengaluru India Sree Vidyanikethan Engineering College Rangampeta School of Computer Science Engineering with Artificial Intelligence Tirupati517102 India Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Department of Information Technology Manipal India

ISBN: (纸本)9798331527822

The integration of blockchain technology into the grocery purchasing process offers a transformative approach to enhancing transparency, security, and efficiency. This paper presents a comprehensive framework for a blockchain-based grocery system, detailing each step from user registration and identity verification to product listing, smart contract creation, and real-time inventory management. Consumers can place orders with confidence, knowing that payments are securely processed and supply chain logistics are fully transparent. The use of IoT devices ensures quality control during transportation, while smart contracts automate delivery and receipt confirmation. Additionally, the system supports consumer feedback and dispute resolution through immutable records and predefined arbitration mechanisms. This innovative application of blockchain technology aims to revolutionize the grocery sector, fostering trust and accountability among all stakeholders involved. Future research will explore the potential for AI integration and address scalability and interoperability challenges. © 2024 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Developing Novel Approaches for Implementing Machine Learning in Medicine 3

Developing Novel Approaches for Implementing Machine Learnin...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Mercilin Raajini, X. Inamdar, Fatima M. Kannagi, A. Agrawal, Trapty Vishnoi, Manish Yuvaraj, K. Prince Shri Venkateshwara Padmavathy Engineering College Department of Electronics and Communication Engineering Chennai India Vishwakarma Institute of Information Technology Department of Information Technology Pune India Department of Computer Science and Information Technology Karnataka Bangalore India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Vivekananda Global University Department of Civil Engineering Jaipur India Karpagam Academy of Higher Education Department of Computer Science Coimbatore India

ISBN: (纸本)9798350319125

Recent advances in computing hardware and software program have enabled the improvement and deployment of state-of-the-art system getting to know (ML) models in diverse scientific domain names. ML has the capacity to leverage large volumes of affected person facts to generate insights and actionable answers, allowing unique prognosis and treatment choices. In spite of promising ability, enforcing ML in medicine has been hard because of numerous realistic problems, inclusive of records bias and series technology, lack of robust evaluation frameworks, and ethical and privacy worries. To cope with these demanding situations, researchers have begun to expand novel methods to allow green and powerful ML deployment in medical practice. these tactics contain leveraging novel records resources such as wearable's and glide cytometry, the use of federated studying algorithms for privacy-preserving version development, and incorporating multi-level evaluation metrics which include explain ability and fairness. Together, these novel methods provide a roadmap for correctly and safely deploying ML in medication to higher help and enhance patient care. © 2023 IEEE.

关键词： computing generate improvement medication patient

来源：评论

学校读者我要写书评

暂无评论

Leveraging Deep Learning Techniques for Profiling and Categorizing Lung and Pancreatic Tumors

Leveraging Deep Learning Techniques for Profiling and Catego...

引用

2023 International Conference on Recent Advances in Science and engineering technology, ICRASET 2023

作者： Jeelani, Azra Vaishnawi, Chittamuru Yadav, Rakesh Kumar Presidency University Department of Electronics and Communication Engineering Karnataka Bangalore India Department of Computer Science and Information Technology Bangalore India Maharishi University of Information Technology Maharishi School of Engineering & Technology Uttar Pradesh India

ISBN: (纸本)9798350306927

The study provides a unique strategy for "Leveraging Deep Learning Techniques for Profiling and Categorizing Lung and Pancreatic Tumors."The suggested technique incorporates Convolutional Neural Networks (CNNs) for image analysis, Recurrent Neural Networks (RNNs) for temporal modeling, and Transfer Learning to fine-tune pre-trained models. It aims to improve tumor classification precision by tackling the particular challenges given by pancreatic and lung cancers. The outcomes of our investigation show that the proposed strategy outperforms existing methods in numerous key areas. F1 was 0.85, specificity was 0.87, recall was 0.82, accuracy was 0.85, precision was 0.88, and area under the curve was 0.92, according to the results. These values routinely exceed six original conventional approaches, including CNNs, RNNs, Transfer Learning, Autoencoders, Support Vector Machines (SVMs), and Reinforcement Learning. The confusion matrix measurements further underscore the superiority of the suggested strategy with more true positives and true negatives, and fewer false positives and false negatives. In conclusion, the suggested strategy improves the accuracy and objectivity of lung and pancreatic tumor profiling by harnessing the power of deep learning and a multi-faceted approach. It offers a more tailored, efficient, and data-driven approach to the arduous issue of tumor classification. The data clearly illustrate its superiority over traditional approaches, making it a potential innovation in the field of cancer. © 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

A UAV-Based Remote Sensing Image Automatic Monitoring System Empowered by Artificial Intelligence

A UAV-Based Remote Sensing Image Automatic Monitoring System...

引用

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

作者： Liu, Tao Zhang, Bohan College of Computer Science and Technology Heilongjiang Institute of Technology Harbin China School of Information Engineering China University of Geosciences Wuhan Wuhan China State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan China

ISBN: (纸本)9798350360660

In this study, an automatic monitoring system based on convolutional neural network (CNN) is proposed to address the automation and accuracy of remote sensing image processing. With the maturity and wide application of remote sensing and UAV technologies, efficient and accurate image analysis methods have become particularly important. We developed this system through in-depth research on multiple stages of data preprocessing, feature extraction and model training. In the experimental stage, through the comparison experiments with Support Vector Machine (SVM) and Random Forest (RF) models, it is found that the CNN model has significant advantages in processing speed, anti-interference ability and accuracy. Especially in the processing of urban remote sensing images, CNN exhibits up to 90% accuracy, showing its wide applicability and excellent cross-domain application capability. Overall, this study not only successfully develops an efficient and accurate automatic monitoring system for remote sensing images, but also provides strong theoretical and experimental support for future optimization of CNN architecture in natural environments, improvement of real-time data processing capability, and extension to practical applications such as disaster monitoring and environmental protection. © 2024 IEEE.

关键词： Environmental monitoring

来源：评论

学校读者我要写书评

暂无评论

Optimal Location Based Fuzzy Logic Model for Underwater Communications 5th

Optimal Location Based Fuzzy Logic Model for Underwater Comm...

引用

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

作者： Agrawal, Jaishree Kalaiarasan, C. Agarwal, Trapty Ojha, Ananta Department of Computer Science and Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Navgaon Manduwala Dehradun India School of Computer Science and Engineering Presidency University Karnataka Bengaluru India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Karnataka Bangalore India

ISBN: (纸本)9789819780426

The most beneficial location based totally fuzzy good judgment model for Underwater Communications is an advanced and innovative solution for conditions consisting of underwater navigation and verbal exchange, which requires cautious attention of various environmental factors. This version combines 3 special procedures for finding underwater items: the bushy C-method (FCM) technique for clustering, a fuzzy mapping method for locating and tracking gadgets, and a fuzzy common sense method for controlling. The FCM approach is used to create wonderful clusters of objects primarily based on attributes such as salinity, water temperature, and so forth. After which the bushy mapping technique is used to decide the nearest cluster to an object. Sooner or later, the bushy good judgment technique uses input from those clusters to generate top-rated navigation paths for the item being tracked. All 3 elements of this approach paintings together to allow more than one gadgets being tracked on the same time, and it can also make certain the item is constantly headed in the direction of the most fulfilling navigation path. This version gives stepped forward efficiencies in underwater communications and can help provide real-time situational recognition. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Obfuscated Malware Detection using Multi-class Classification 11

Obfuscated Malware Detection using Multi-class Classificatio...

引用

11th IEEE International Conference on Cloud Computing in Emerging Markets, CCEM 2023

作者： Sharmila, S.P. Tiwari, Aruna Chaudhari, Narendra S. Computer Science and Engineering Indian Institute of Technology Madhya Pradesh Indore India Information Science and Engineering Siddaganga Institute of Technology Karnataka Tumakuru India

ISBN: (纸本)9798350360059

Providing security for information is highly critical in the current era with devices enabled with smart technology, where assuming a day without the internet is highly impossible. Fast internet at a cheaper price, not only made communication easy for legitimate users but also for cybercriminals to induce attacks in various dimensions to breach privacy and security. Cybercriminals gain illegal access and breach the privacy of users to harm them in multiple ways. Malware is one such tool used by hackers to execute their malicious intent. Development in AI technology is utilized by malware developers to cause social harm. In this work, we intend to show how Artificial Intelligence and Machine learning can be used to detect and mitigate these cyber-attacks induced by malware in specific obfuscated malware. We conducted experiments with memory feature engineering on memory analysis of malware samples. Binary classification can identify whether a given sample is malware or not, but identifying the type of malware will only guide what next step to be taken for that malware, to stop it from proceeding with its further action. Hence, we propose a multi-class classification model to detect the three types of obfuscated malware with an accuracy of 89.07% using the Classic Random Forest algorithm. To the best of our knowledge, there is very little amount of work done in classifying multiple obfuscated malware by a single model. We also compared our model with a few state-of-the-art models and found it comparatively better. ©2023 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Researches on millimeter-wave wide-angle scanning phased array for future communication applications 11

Researches on millimeter-wave wide-angle scanning phased arr...

引用

11th IEEE Asia-Pacific Conference on Antennas and Propagation, APCAP 2023 - Proceedings

作者： Yang, Wanchen Hohai University College of Computer and Information Nanjing China South China University of Technology School of Electronic and Information Engineering Guangzhou China

ISBN: (纸本)9798350326277

With the rapid development of information technology, millimeter-wave communication applications have received more and more attentions. Phased array is one of the key technologies of millimeter-wave wireless system. It has the ability of beam agility, beam synthesis and decomposition. It can realize multi-beam scanning in azimuth- and pitch-planes to meet the needs of multi-target communication and tracking detection. However, the current millimeter-wave phased arrays face some problems, especially how to achieve high-isolation and wide-angle scanning in the case of covering 5G n257/n258/n261 and future B5G/6G band, or satellite communication band is a big challenge. To this end, we has carried out a series of researches in increasing the scanning angle and improving the channel isolation of the phased arrays, etc. The developed millimeter-wave phased array antennas have the excellent performance of large bandwidth, high isolation and large scanning angle, providing a good solution for millimeter-wave phased array antennas in future communication applications. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Ensemble Learning Techniques for Brain Tumor Classification

引用

Informatica (Slovenia) 2024年第20期48卷 41-50页

作者： Sharif, Rehman Azam, Muhammad Ali, Arshad Hashmi, Muhammad Usman Uzair, Muhammad Department of Mathematics & Physics The Superior University Lahore54000 Pakistan Department of Computer Science & Information Technology The Superior University Lahore54000 Pakistan Faculty of Computer and Information Systems Islamic University of Madinah Al Madinah Al Munawarah Saudi Arabia Faculty of Engineering Islamic University of Madinah Al Madinah Al Munawarah Saudi Arabia

For the evaluation of our work, we used a brain tumor MRI dataset obtained from Kaggle for the experimental analysis. Our study investigates the performance of ensemble learning techniques for brain tumor classification. This study focuses on comparing the efficacy of homogenous ensemble classifiers, exemplified by the Random Forest (RF) algorithm, against heterogeneous ensemble classifiers like Voting and Stacking, this study embarks on a thorough evaluation journey. Our evaluation is not limited to accuracy measures only;instead, it surrounds recall, ROC AUC, precision, and F1-score, for better assessment of classifiers’ performance. Our findings demonstrate that the Random Forest classifier achieved an accuracy of 99%, an F1 score of 0.99%, and AUC of 0.99%, outperforming other ensemble techniques like Voting and Stacking classifiers. Building upon an observed assessment performed on an appropriately selected brain tumor dataset, we provide solid empirical support demonstrating that RF not only performs better than base classifiers but also outperforms the heterogeneous ensemble methods in terms of many different performance measures. Furthermore, we discuss the specific reason that makes RF outperform other algorithms in this dataset and discuss the robustness and flexibility of this method. By unscrambling these insights, this paper addresses to fill gaps in the existing knowledge regarding the ensemble learning techniques in medical imaging, particularly for brain tumor classification diagnostics. © 2024 Slovene Society Informatika. All rights reserved.

关键词： Random forests

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：