检索结果-内蒙古大学图书馆

An efficient dimensionality reduction based on adaptive-GSM and transformer assisted classification for high dimensional data

引用

International Journal of Information technology (Singapore) 2024年第1期16卷 403-416页

作者： Rajender, N. Gopalachari, M. Venu Department of Computer Science and Engineering University College of Engineering Osmania University Telangana Hyderabad India Department of Information Technology Chaitanya Bharathi Institute of Technology Telangana Hyderabad India

Over the last decade, a surge in multimedia data has significantly impacted research areas like multimedia retrieval, database management, and medical imaging. Traditional machine learning methods often struggle with high-dimensional data due to the “curse of dimensionality.” To address this, we propose a dimensionality reduction technique based on Granular Statistical methods. We rigorously analyze its computational complexity and validate its effectiveness on a standard image dataset. Additionally, we introduce a transformer-based Deep Neural Network (DNN) model that achieves high accuracy in image classification tasks through hierarchical processing and shifted window techniques. Our results demonstrate that our framework outperforms existing methods in both accuracy and efficiency, offering valuable insights for applications like content-based image retrieval and sentiment analysis. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Dimension reduction High dimension data Images classification Statistical machine learning

来源：评论

学校读者我要写书评

暂无评论

Effective Fault Prediction Techniques for the Green Cloud Computing Environment Applying Machine Learning to Enhance Network Management 6th

Effective Fault Prediction Techniques for the Green Cloud C...

引用

6th International Conference on Intelligent Computing and Optimization, ICO 2023

作者： Tamim, Hasnath Ahmed Hossain, Md. Sagor Asif, Md. Asif Uzzaman Uddin, Borhan Reza, Ahmed Wasif Arefin, Mohammad Shamsul Department of Computer Science and Engineering East West University Dhaka Bangladesh Department of Computer Science and Engineering Chittagong University of Engineering and Technology Chattogram Bangladesh

ISBN: (纸本)9783031362453

Network errors are a significant issue in cloud computing. Occasionally, issues with cloud networks may cause productivity to drop considerably. The primary objective of this research is to employ machine learning techniques for predicting failures in Cloud Networks, enabling prompt identification of issues. The author attempted to determine the most accurate method, the Random Forest, that matches our model. We trained our model using gradient boosting, decision trees, K-neighbors, Random forests, SVC, and logistic regression. Then, by analyzing data as performance indicators, resource use, and energy consumption, random forests may be employed in a green cloud computing environment to forecast upcoming flaws. The system can recognize patterns and correlations in data that may indicate an issue and generate predictions for future forecasting based on these patterns, with an accuracy of 80.825479%. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Innovative image interpolation based reversible data hiding for secure communication

引用

Discover Internet of Things 2023年第1期3卷 22页

作者： Punia, Riya Malik, Aruna Singh, Samayveer Department of Computer Science & amp Engineering Dr B R Ambedkar National Institute of Technology Jalandhar Punjab India

In an increasingly digitized world, secure communication plays a pivotal role in safeguarding sensitive information and ensuring the confidentiality of data transmission. Conventional encryption techniques are robust but often result in a loss of data during transmission, making it challenging to achieve both security and image quality simultaneously. To address this issue, an innovative technique for interpolation-based reversible data hiding (RDH) within images is presented in this study. The interpolation scheme considers the Min function of the neighboring pixels and generates the cover image. After that, a data hiding method is applied to the cover image by considering the intensity range of the pixels using the least-significant bit (LSB) substitution method. The suggested embedding approach first encrypts the secret message, and then it encodes the encrypted secret message into interpolated pixels based on pixel intensity range groups. This technique enables the image to be consistently recreated once the data has been extracted. The percentage increment in the embedding capacity and peak signal-to-noise ratio (PSNR) is 40.00 and 8.64% for the proposed method as compared to the existing method. The experimental results indicate that the proposed technique enhanced the embedding capacity for all test pictures and produced higher PSNR values. © The Author(s) 2023.

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

Application of Support Vector Machine to Lassa Fever Diagnosis

Lecture Notes on Data Engineering and Communications Technol...

引用

Lecture Notes on Data engineering and Communications Technologies 2023年 180卷 165-177页

作者： Nwankwo, Wilson Adigwe, Wilfred Umezuruike, Chinecherem Acheme, Ijegwa D. Nwankwo, Chukwuemeka Pascal Ojei, Emmanuel Oghorodi, Duke Department of Computer Science Edo State University Uzairue Nigeria Department of Computer Science Delta State University of Science and Technology Ozoro Nigeria College of Computing and Communication Studies Bowen University Iwo Nigeria Department of Software Engineering Delta State University of Science and Technology Ozoro Nigeria Department of Cyber Security Delta State University of Science and Technology Ozoro Nigeria

Lassa fever is a type of viral hemorrhagic fever with high fatality rate. Precise and prompt diagnosis and successful treatment of this disease is very important in the control and prevention of the spread as unrestricted spread can easily erupt into an epidemic. An insightful decision support system can help make quick and more exact findings on this disease. In this paper, an intelligent model is proposed for predicting Lassa fever is proposed. The Lassa fever dataset was extracted from the clinical records of patients from a known Specialist Teaching Hospital in Southern Nigeria. The relevant feature variables were identified and encoded in a manner appropriate for use in algorithmic analysis. The support vector classifier was used to develop a characterization model for the disease. Assessment and evaluation were based on exactness, accuracy, and affectability. Findings showed that the proposed system could improve and encourage quick decision-making as it utilizes real historical data to effectively characterize Lassa fever spread as well as promote the timely treatment and management of patients. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Transfer Learning-Based Framework for Enhanced Classification of Perceived Mental Stress Using EEG Spectrograms

引用

IEEE Access 2025年 13卷 89266-89286页

作者： Khan, Sheharyar Noorani, Sadam Hussain Frnda, Jaroslav Rauf, Usman Arsalan, Aamir Saeed, Sanay Muhammad Umar University of Engineering and Technology Department of Computer Engineering Taxila47050 Pakistan HITEC University Department of Computer Science Taxila47050 Pakistan University of Žilina Faculty of Operation and Economics of Transport and Communications Department of Quantitative Methods and Economic Informatics Žilina01026 Slovakia Fatima Jinnah Women University Department of Software Engineering Rawalpindi46000 Pakistan

Stress is a significant health concern, impacting both physical and mental well-being. Prolonged exposure to stress can lead to numerous physical health issues, including cardiovascular diseases, and a weakened immune system. This study presents a novel methodology for classifying perceived mental stress using electroencephalography (EEG) signals. By utilizing the publicly available Leipzig Study for Mind-Body-Emotion Interactions dataset, we analyze EEG data collected from 53 participants over a 7-minute resting-state duration. Our approach involves transforming EEG signals into spectrograms using the Short-Time Fourier Transform (STFT), resulting in a time-frequency representation of the input signals. We employ transfer learning to fine-tune three pre-trained deep neural networks i.e., ResNet50, EfficientNetB0, and DenseNet121 for classifying stress into two and three levels. Our findings demonstrate that the ResNet50 model achieves superior classification accuracies of 95.80% and 86.02% for two and three-level stress classification, respectively, outperforming existing state-of-the-art methods. This study is the first to utilize STFT-generated spectrograms and transfer learning for perceived stress classification, highlighting the efficacy of deep learning techniques in quantifying perceived mental stress through non-invasive EEG recordings. Our results indicate that the proposed method can significantly enhance the accuracy of stress classification frameworks, offering potential improvements in mental health assessment and intervention strategies. © 2013 IEEE.

关键词： Noninvasive medical procedures

来源：评论

学校读者我要写书评

暂无评论

Deep Insights of Negative Bias Temperature Instability (NBTI) Degradation

Deep Insights of Negative Bias Temperature Instability (NBTI...

引用

2025 IEEE International Students' Conference on Electrical, Electronics and computer science, SCEECS 2025

作者： Singh, Karan Mahur, Jyoti Noida Institute of Engineering and Technology Department of Information Technology Greater Noida India Noida International University Department of Computer Science and Engineering Greater Noida India

ISBN: (纸本)9798331529833

As the global semiconductor industry moving towards successive generations, the density of Integrated Circuit increased, therefore reliability issues became critically high, among them Negative Bias Temperature Instability is prominent one. NBTI degraded the PMOS transistor's behavior when subjected to inverted gate voltage. The impact of NBTI can be referred to as threshold-voltage adjustment of PMOS, degradation in drain-source current, and reduction in speeds of device. An increase in temperature with negative gate stress is the primary introduction that degrades the Gate Oxide, which in turn causes all these adverse effects. Hence, stress analysis is required for any device before designing circuitry so that when circuits are drawn, high performance of the circuits is ensured. Out of many reliability problems affecting PMOS transistors at the nanoscale level, NBTI occupies center stage. This paper discusses stress-variation-dependent impact of NBTI for 22nm bulk CMOS inverter circuit over the period of 10 years. © 2025 IEEE.

关键词： CMOS integrated circuits

来源：评论

学校读者我要写书评

暂无评论

AI for Smart Agriculture - A Deep Learning Based Turmeric Leaf Disease Detection 9

AI for Smart Agriculture - A Deep Learning Based Turmeric Le...

引用

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Selvaraj, R. Devasena, M. S. Geetha Satheesh, T. Sathishkumar, C. Dr.N.G.P. Institute of Technology Department of Computer Science and Engineering Coimbatore India Sri Ramakrishna Engineering College Department of Computer Science and Engineering Coimbatore India Dr.N.G.P. Institute of Technology Department of Artificial Intelligence and Data Science Coimbatore India Department of Computer Science and Engineering RVS Technical Campus-Coimbatore Coimbatore India

ISBN: (纸本)9798350377972

Plants is one of the major food sources for world population. In addition to that, some plants and their outcomes are used in food preparation. One of the plants which is widely used in foods and having huge medicinal value is turmeric. Curcuma long the botanically named spice turmeric has large anti-inflammatory properties, antioxidants, etc., the tropical perennial plant is cultivated worldwide. Diseases in plant leaves is one of the serious factors that affects the turmeric cultivation. Leaf disease reduces the production and it requires continuous monitoring to avoid total loss. Manual monitoring is challenging when the crop is planted in large fields. Due to industrial revolution and smart agriculture concepts, artificial intelligence- based disease detection procedure is presented in recent times. Thus, in this research work a deep learning-based turmeric leaf disease detection model is presented using AlexNet. The leaf disease classification model is experimented with our own dataset which includes diseases like Leaf Spot Disease, Leaf Blight, Leaf Rot, and Leaf Curl. The experimentation results provide the maximum accuracy of proposed leaf disease classification model as 95.5% which is better than traditional machine learning models. © 2024 IEEE.

关键词： AlexNet classification Deep learning Turmeric Leaf disease

来源：评论

学校读者我要写书评

暂无评论

Voting Classifier and Metaheuristic Optimization for Network Intrusion Detection

引用

computers, Materials & Continua 2023年第2期74卷 3183-3198页

作者： Doaa Sami Khafaga Faten Khalid Karim Abdelaziz A.Abdelhamid El-Sayed M.El-kenawy Hend K.Alkahtani Nima Khodadadi Mohammed Hadwan Abdelhameed Ibrahim Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Science Faculty of Computer and Information SciencesAin Shams UniversityCairo11566Egypt Department of Computer Science College of Computing and Information TechnologyShaqra University11961Saudi Arabia Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt The Department of Civil and Environmental Engineering Florida International UniversityMiamiFLUSA Department of Information Technology College of ComputerQassim UniversityBuraydah51452Saudi Arabia Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt

Managing physical objects in the network’s periphery is made possible by the Internet of Things(IoT),revolutionizing human *** attacks and unauthorized access are possible with these IoT devices,which exchange data to enable remote *** attacks are often detected using intrusion detection methodologies,although these systems’effectiveness and accuracy are *** paper proposes a new voting classifier composed of an ensemble of machine learning models trained and optimized using metaheuristic *** employed metaheuristic optimizer is a new version of the whale optimization algorithm(WOA),which is guided by the dipper throated optimizer(DTO)to improve the exploration process of the traditionalWOA *** proposed voting classifier categorizes the network intrusions robustly and *** assess the proposed approach,a dataset created from IoT devices is employed to record the efficiency of the proposed algorithm for binary attack *** dataset records are balanced using the locality-sensitive hashing(LSH)and Synthetic Minority Oversampling Technique(SMOTE).The evaluation of the achieved results is performed in terms of statistical analysis and visual plots to prove the proposed approach’s effectiveness,stability,and *** achieved results confirmed the superiority of the proposed algorithm for the task of network intrusion detection.

关键词： Voting classifier whale optimization algorithm dipper throated optimization intrusion detection internet-of-things

来源：评论

学校读者我要写书评

暂无评论

Techniques for Resource-Efficient, Lightweight Cryptography in IoT Devices for Smart Environment 6

Techniques for Resource-Efficient, Lightweight Cryptography ...

引用

6th International Conference of Women in Data science at Prince Sultan University, WiDS-PSU 2023

作者： Murtaza, Ghulam Iqbal, Faiza Altaf, Ayesha Rasheed, Ali University of Engineering and Technology Department of Computer Science Lahore Pakistan

ISBN: (纸本)9781665477239

The Internet of Things (IoT) is the result of the expansion of modern technology, which has led to the development of numerous connected devices that are able to communicate with one another and collect vast amounts of data. Consequently, there is a substantial demand for enhanced IoT security. Cryptography is employed for network security for a variety of reasons, including authentication, privacy, data integrity, and robust control. Existing cryptographic methods may not be compatible with certain IoT configurations and protocols. This is because IoT devices have limited access to resources. As a direct result, cryptographers have proposed a large number of condensed cryptography protocols and algorithms. In this paper, we compare the modern lightweight cryptography protocols that are currently in use. Based on the findings of this study, we have utilized the PRESENT block cipher and compared its performance to that of numerous other lightweight cryptography algorithms. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

An Application of Graph Labeling—Cryptographic Technique with Magic Labeling 4th

An Application of Graph Labeling—Cryptographic Technique wi...

引用

4th international conference on Energy Systems, Drives and Automations, ESDA 2021

作者： Prasanna, Nissankara Lakshmi Sudhakar, Nagalla Department of Computer Science and Engineering Vasireddy Venkatadri Institute of Technology Guntur India Department of Computer Science and Engineering Bapatla Engineering College Bapatla India

ISBN: (纸本)9789819936908

Graph theory is an important branch of mathematics which is used to solve variety of problems in computer science by structural models. This structural modeling makes the computer discipline problems to find solution in easier way. Graph labeling is assigning additional information to the graph elements. A lot of research has been surveyed on graph labeling. Magic labeling is a sort of graph labeling. The three types of magic labeling are vertex, edge, and total magic labeling. A lot of research has been surveyed on labeling and its applications in broad. Designing applications over specific labeling algorithm is an interesting and raising domain. Very few authors addressed such applications which can be solved with specific type of labeling. One such application over magic labeling of graphs is addressed here in detail. This article presents a cryptographic technique for data encryption and decryption by using magic labeling of graphs. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Graph theory

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：