检索结果-内蒙古大学图书馆

In Search of a Suitable Epoch Value for the Optimum Result in Image Captioning 3

In Search of a Suitable Epoch Value for the Optimum Result i...

3rd International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies, ICAECT 2023

作者： Dinda, Sourav Pal, Alok Ranjan Pal, Antara College of Engineering and Management Kolaghat Department of Computer Science and Engineering Kolaghat India National Institute of Technology Durgapur Department of Computer Science and Engineering Durgapur India

ISBN: (纸本)9781665494007

The proposed work is carried out on retrieving the content of an image using machine learning based approach. In order to gain a deeper insight of this topic, the current state-of-the-art image caption generation technique has been considered as the baseline. The goal of this work is to find a suitable Epoch value during the training phase which can maximize the performance of a system. The proposed model is composed of six major components: 1) Data pre-processing unit;2) Convolutional Neural Network (CNN) as an encoder;3) At-tention mechanism;4) Recurrent Neural Network (RNN) as a decoder;5) Beam search to find most optimal caption;and 6) Sentence Generation and evaluation. The model is trained to maximize the likelihood of the description sentence of a given training image. Experiments on the test dataset show the accuracy of the model and the fluency of the language it learns solely from image descriptions. The challenges of this work are mentioned in detail at the last of this paper. © 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

Automatic Ship Detection and Classification from Imagery Dataset MASATI Using Deep Learning Framework 5th

Automatic Ship Detection and Classification from Imagery Dat...

引用

5th International Conference on Advances in Information Communication technology and Computing, AICTC 2024

作者： Patel, Krishna Bhatt, Chintan Department of Computer Science & Engineering Devang Patel Institute of Advance Technology and Research Charotar University of Science and Technology Changa India Gandhinagar India

ISBN: (纸本)9789819761029

A significant challenge is the automatic detection and classification of ships from aerial images for maritime safety and surveillance. There are two techniques, image processing and computer vision, used before the traditional supervised classifiers to extract the features from the images and classify them. The framework proposed in this paper is You Only Look Once (YOLOv8), which was recently developed and implemented for object detection and classification on the COCO dataset. The authors used the framework with some preprocessing and augmentation on the satellite image to detect and classify ships, which helps maritime organizations locate the objects. The MAritime SATellite Imagery dataset (MASATI) of more than 7000 images is used in this paper. The proposed method is tested with two different preprocessing steps, auto-orient and mosaic augmentation, in version 1 and version 2;the preprocessing step includes auto-orient and grayscale along with the augmentation as crop, shear, blur, and mosaic. The framework generates mAP of 57.8% and 63.7% for version 1 and version 2, respectively. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Satellite imagery

来源：评论

学校读者我要写书评

暂无评论

Leveraging XGBoost based GBM for Proactive Detection of Man-in-the-Middle Cyber Attacks

Leveraging XGBoost based GBM for Proactive Detection of Man-...

引用

2024 Asian Conference on Intelligent Technologies, ACOIT 2024

作者： Manjaragi, Shivanand V. Asrani, Deepak Kumar, Arvind Sandesh, R. Maindola, Meenakshi Sai, Aarush Department of Computer Science and Engineering Hirasugar Institute of Technology Karnataka Nidasoshi591236 India Department of Computer Science and Engineering MIET Uttar Pradesh Greater Noida India SCA MRIIRS Haryana Faridabad India Department of Computer Science and Engineering ATME College of Engineering Karnataka Mysuru India Department of Computer Science Engineering Graphic Era Deemed to be University Uttarakhand Dehradun India Department of CSBS Gyan Ganga Institute of Technology and Sciences Madhya Pradesh Jabalpur India

ISBN: (纸本)9798350374933

Man-in-the-Middle (MitM) cyber-attacks provide a substantial risk to network security, since they allow hostile individuals to intercept and alter communications between two parties. Conventional detection approaches frequently fail to recognize these complex threats, requiring the creation of more resilient and precise solutions. This study introduces a model called XGBoost-based Gradient Boosting Machine (GBM) to identify MitM attacks in advance. The system employs extensive datasets from Kaggle, namely CICIDS 2017 and UNSW-NB15, for the purpose of training and evaluating the model. By carefully preparing the data, selecting relevant features, and doing thorough cross-validation with hyperparameter optimization, the suggested model attains exceptional performance metrics. The assessment findings indicate an accuracy of 0.98, precision of 0.97, recall of 0.96, F1-Score of 0.965, and a remarkable ROC-AUC score of 0.99. Our model regularly outperforms existing technologies like as Random Forest and Traditional GBM in identifying MitM attacks, achieving higher performance metrics across the board. This research demonstrates the effectiveness of the XGBoost-based GBM model in improving cybersecurity defenses and suggests that it might serve as a standard for future advancements in cyber-attack detection systems. The suggested system's exceptional accuracy and resilience make it an invaluable tool for proactively detecting and reducing MitM attacks. © 2024 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Exploring the Future of Key Management and Authentication in Public Key Infrastructures

Exploring the Future of Key Management and Authentication in...

引用

2024 International Conference on Communication, computer sciences and engineering, IC3SE 2024

作者： Aswini, Kilaru Rajalakshmi, B. Singh, Navdeep Suman, Bashetty Rana, Ajay Al-Allak, Mustafa Abdulhussein Institute Of Aeronautical Engineering Department Of Computer Science And Engineering Telangana Hyderabad India New Horizon College Of Engineering Department Of Computer Science Engineering Bangalore India Lovely Professional University Phagwara India Mlr Institute Of Technology Department Of Computer Science And Engineering Telangana Hyderabad India Amity University Greater Noida India College Of Medical Technology The Islamic University Najaf Iraq

ISBN: (纸本)9798350366846

The five-algorithm design in this study covers authentication, advanced key management, post-quantum security, and integrating blockchain. The Lifecycle Management Model Algorithm uses a cyclical process to make encryption keys. This process is built on rotating keys and updating parameters to keep things flexible. Lattice-based encryption is used by the Post-Quantum Encryption Integration Algorithm to protect against quantum threats. For post-quantum security, it is always changing to use technology that is not affected by quantum mechanics. To make a dynamic and reliable authentication system, the Advanced Authentication Protocols Algorithm collects physiological data, looks at behavioral trends, and uses quantum-resistant authentication protocols. Proof of Work and quantum-resistant protections are used by the Blockchain-based Key Management Algorithm to build decentralized trust in key transfers. Lastly, the Scalable PKI Infrastructure Algorithm makes sure that it can grow as needed, respond to new technical settings, and register entities dynamically by combining many technologies. As part of the ablation study, each program was taken apart. Key rotation, behavioral analytics, Proof of Work, and quantum-resistant integration were the main topics of the works. These algorithms keep cryptographic systems safe from new threats and give today's complicated digital ecosystems a flexible base. © 2024 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Cybersecurity Threat Detection in Smart Cities using Box Plot Sampling Isolation Forest 1

Cybersecurity Threat Detection in Smart Cities using Box Plo...

引用

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Shankari, S. Uma Mohameed, Haeedir Kulkarni, Megha Aravindh, S. Purushotham, N. Srm Institute of Science and Technology Department of Computer Science and Applications Ramapuram India The Islamic University of Al Diwaniyah College of Technical Engineering Department of Computers Techniques Engineering Al Diwaniyah Iraq Nitte Meenakshi Institute of Technology Department of Civil Engineering Bengaluru India New Prince Shri Bhavani College of Engineering and Technology Department of Mechanical Engineering Chennai India Mohan Babu University Department of Computer Science and Engineering Tirupati India

ISBN: (纸本)9798331529246

Now a days, the standard of living in urban areas is advanced by leveraging technologies such as Cyber-Physical Systems (CPS) and Internet of Things (IoT) with physical infrastructures. However, smart cities highly rely on digital ecosystems, which makes them vulnerable to various cyber threats such as Distributed Denial of Service (DDoS) which leads in violations of privacy and threats to safety of citizens. To develop an effective and efficient system for detection of cybersecurity threats, Box plot Sampling Isolation Forest (BSIF) is proposed. Initially, the data was collected from the Botnet Traffic attack in Internet of Things (BoT-IoT) dataset which contains various normal traffic and Botnet traffic data. After that, Label Encoding (LE) was used for preprocessing the data, which assigns numerical labels to each category in the dataset. Furthermore, Recursive Feature Elimination (RFE) technique was utilized for iterative extraction and selection of features based on their weights is performed by Decision Tree (DT). Finally, the proposed BSIF model is used for detection of cybersecurity threats associated with smart cities, by leveraging box plot sampling method. The proposed obtain better results with 99.74% Precision, 99.92% Accuracy, 99.87% Recall and 99.84% F1-score, compared with Smart Attacks Learning Machine Advisor (SALMA) respectively. © 2025 IEEE.

关键词： Bot (Internet)

来源：评论

学校读者我要写书评

暂无评论

Analysis of Magnetic Resonance images for the detection of Alzheimer's 4

Analysis of Magnetic Resonance images for the detection of A...

引用

4th IEEE Asian Conference on Innovation in technology, ASIANCON 2024

作者： Patil, Harshal Swati Kamala, L. Chaturvedi, Arpana Veeranjaneyulu, Rayavarapu Vekariya, Vipul Maharashtra Pune India Graphic Era Deemed to be University Department of Computer Science & Engineering Uttarakhand Dehradun248 002 India Gitam School of Technology Department of Computer Science and Engineering Karnataka Bengaluru561203 India New Delhi Institute of Management Department of IT/AI/ML New Delhi110062 India Pace Institute of Technology & Sciences Department of Computer Science and Engineering Andhra Pradesh Ongole523272 India Parul University Parul Institute of Engineering and Technology Department of Computer Science and Engineering Post Limda Gujarat 391760 India

ISBN: (纸本)9798350354218

This study aims to design a CAD tool for Alzheimer's disease (AD) detection using linear SVM classifiers on MRI scans. Existing approaches often face challenges with high-dimensional feature spaces and limited data accessibility from repositories like ADNI. To overcome these, three SVM-based classifier proposals were explored. Results demonstrated promising accuracy, sensitivity (Se), and specificity (Sp), particularly with cross-validation techniques. Notably, classifiers trained with image histograms showed superior performance in differentiating between AD, cognitively normal (CN), and mild cognitive impairment (MCI). Despite successes, initial approaches encountered difficulties, necessitating alternative methods. Challenges in data access and processing highlight the need for improved data management tools. Moving forward, refinements such as feature selection and testing with larger datasets could enhance classifier performance. Exploring deep neural networks as an extension may offer further insights into AD detection methodologies for early diagnosis and intervention. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Time Series Analysis of National Stock Exchange: A Multivariate Data science Approach 11th

Time Series Analysis of National Stock Exchange: A Multivari...

引用

11th International Conference on Soft Computing for Problem Solving, SocProS 2022

作者： Venkata Manish Reddy, G. Iswarya Kumar, Jitendra Choubey, Dilip Kumar School of Advanced Sciences Vellore Institute of Technology Tamil Nadu Vellore India Department of Computer Science and Engineering Indian Institute of Information Technology Bhagalpur Bihar Bhagalpur India

ISBN: (纸本)9789811965241

Stock price prediction attracts individual decisions to invest in share market and may encourage the common people to become active in share trading. Stock trading gives us direct monetary benefit under prevalent uncertainties. Factors like political developments at state, national and international levels, conservative, diverse and complex social conditions, natural disasters, famine, pandemics, economic trade cycle (recession, boom and recursion) and many others have great effects on share prices and stock cost. The present work is based on secondary data sources acquisitioned from various public and private data portals accessed freely. There have been various efforts made in the past to predict the trends of the stock prices on the basis of secondary data. The predicted confidence estimates may enable the common investors to make a profit despite large risk of loss at different point of time under the dynamics of market fluctuations. The present work is based on an inferential methodology, which has been found to be instrumental and particularly suitable to the financial time series analysis. Time series modelling and forecasting have fundamental importance in stock market prediction and analysis. Further, with the application of multivariate methods and regression modelling, we expect better forecast accuracy. The implementation of the proposed approach has been incorporated on real-time data set on daily basis. The software used for various computations is Python, SPSS, MS Excel and MS Solver. The current work is relevant in prediction and analysis of the stock market prices and also seems to be useful to a large number of peoples engaged in day to day trading. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Commerce

来源：评论

学校读者我要写书评

暂无评论

Unmanned Aerial Vehicles and Low-Flying Drones: A Review of Classification 2

Unmanned Aerial Vehicles and Low-Flying Drones: A Review of ...

引用

2nd DMIHER International Conference on Artificial Intelligence in Healthcare, Education and Industry, IDICAIEI 2024

作者： Pagrut, Shrijeet Jawandhiya, Pradip Shri Sant Gajanan Maharaj College of Engineering Department of Computer Science and Engineering Maharashtra Shegaon India Pankaj Laddhad Institute of Technology and Management Studies Department of Computer Science and Engineering Maharashtra Buldhana India

ISBN: (纸本)9798331528713

Nowadays Research and Development of Novel and Efficient drones becomes the core part of strategic practices of every nation. There is a growing need of using a variety of Unmanned Aerial Vehicles with significant capabilities in Civilian, Military and Commercial Applications. UAVs flight patterns such as Vertical Takeoff Landing and Horizontal Takeoff Landing, its maximum altitude capacity, range are discussed. Designing of Low Flying drones are classified into Small, Micro and Nano-Pico-SmartDust(NPSD) categories. Use and Impact of different materials like Titanium alloy in design is provided. Additionally, current activities in the market related to small drones and future research direction in the field of utility and applications drones are discussed. © 2024 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Analysis of Various Deep Learning Based Multi Class Plant Disease Classification Techniques 1

A Comprehensive Analysis of Various Deep Learning Based Mult...

引用

1st International Conference on Pioneering Developments in computer science and Digital Technologies, IC2SDT 2024

作者： Kala, Deepika Punia, Divya Sikka, Geeta Sikka, Kushagra National Institute of Technology Delhi Department of Computer Science and Engineering Delhi India National Institute of Technology Delhi Department of Electronics and Communication Engineering Delhi India University of Florida Gainesville Department of Information Science and Engineering Gainesville United States

ISBN: (纸本)9798350365016

In modern agriculture, deep learning has become increasingly essential to identify plant diseases in the field of plant disease identification with leaf images, where convolutional neural networks (CNN) are garnering a lot of interest. Plant disease iden-tification and prevention are essential for producing healthy crops and maintaining farmers' livelihoods. This study uses leaf images to examine the effectiveness of deep learning (DL) algorithms for multiclass plant leaf disease classification. The training data was expanded using data augmentation techniques, which eliminated the need for further image collecting. This paper uses three models namely InceptionV3, VGG16, and EfficientNetB0 that have been compared using the plantVillage data set. The three models that achieved the highest accuracy were EfficientNetBO (98.51 %), InceptionV3 (97.78%), and VGG16 (95.37%) for plant detection, and EfficientNetBO (97.58%), InceptionV3 (96.83%), and VGG 16 (94.35 %) for plant detection. Notably, EfficientNetBO performed better for disease classification than the other two algorithms. Farmers are able to take prompt action to stop the disease's spread and reduce crop losses since the technology can deliver fast and precise results. © 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

Feature-enhanced deep learning technique with soft attention for MRI-based brain tumor classification

引用

International Journal of Information technology (Singapore) 2024年第3期16卷 1617-1626页

作者： Mohanty, Bipin Ch. Subudhi, P.K. Dash, Ratnakar Mohanty, Bidyadhar Department of Electronics and Communication Engineering BPUT Odisha Rourkela 769015 India Department of Electronics and Communication Engineering Nalanda Institute of Technology Odisha Bhubaneshwar 754005 India Department of Computer Science and Engineering National Institute of Technology Odisha Rourkela 769008 India

Brain tumor classification using Magnetic Resonance Imaging (MRI) is a pivotal area in medical diagnostics, with the potential to influence early detection and subsequent treatment strategies. Over the years, various machine learning and deep learning models have been proposed to enhance the accuracy of MRI-based tumor detection. In this evolving landscape, this paper introduces a distinctive deep-learning model that harnesses the power of a soft attention mechanism. We employ a meticulously designed Convolutional Neural Network (CNN) comprising four convolution layers. One of the significant innovations in our approach is the method of feature extraction. Instead of extracting features solely from the final layer, as is common in many models, our approach aggregates and combines features from all layers. This ensures that the vital characteristics intrinsic to each layer are not lost but rather amalgamated into a robust and comprehensive feature vector. The incorporation of a soft attention mechanism at the terminal stages ensures that the most salient and clinically relevant features are emphasized, enhancing classification accuracy. To validate the efficacy of our proposed model, we employed standard datasets for training and testing. A comparative analysis with existing state-of-the-art models affirms the superiority and potential of our approach in the realm of MRI-based brain tumor classification. © 2024, The Author(s), under exclusive licence to Bharati Vidyapeeth's institute of computer Applications and Management.

关键词： Brain tumor CNN Deep learning MRI Soft-attention

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：