检索结果-内蒙古大学图书馆

2024 International Conference on computer, Electronics, Electrical engineering and their Applications, IC2E3 2024

作者： Upadhyay, Deepak Sharma, Kunj Bihari Gupta, Mridul Graphic Era Hill University Dept. of Computer Science and Engineering Dehradun India Graphic Era deemed to be University Dept. of Computer Science and Engineering Dehradun India Dept. of Electronics and Engineering Dehradun India

ISBN: (纸本)9798350388534

This study had conducted an intensive exploration of the possibilities of VGG-16 and VGG-19 Convolutional Neural Network models for picture categorisation. Using a thorough method comprising substantial training and severe testing, we may observe both steady loss decrease and significant model accuracy improvements. It is assumed that the models may appropriately keep track of subtle variations in data to which they are adversarial while identifying regular patterns they may generalize. The VGG models' architecture is quite sophisticated, but as seen above, they give strong classification accuracy, with performance in nearly ideal 99 percent in many trials. This integration proves that extremely advanced deep learning instruments are competent to handle and complete even very sophisticated picture recognition assignments. Additionally, our experiments identify a few essential aspects of model adjustment and tuning identifying important techniques considerably enhancing CNN outcomes in application scenarios. This study is pioneering for the automatic picture identification discipline since it provided a strong understanding of the generality and model quicker than many real-world models. Additionally, it exhibits that the CNN structures enhance artificial intelligence's power to recognize visual input and could improve many sectors like the surveillance and health systems. The findings defined here may now open the door to more progress in deep learning and picture process analyses while reiterated the importance of CNN in modern technology. © 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

SMART HOME ENVIRONMENT MODELLED WITH A MULTI-AGENT SYSTEM

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical engineering and computer Science 2023年第1期85卷 365-376页

作者： Rasras, Mohammad Marin, Iuliana Radu, Șerban Dept. of Engineering in Foreign Languages University POLITEHNICA of Bucharest Romania Dept. of Computer Science University POLITEHNICA of Bucharest Romania

A smart home can be considered a place of residence that enables the management of appliances and systems to help with day-to-day life by automated technology. In the current paper is described a prototype that simulates a context-aware environment, developed in a designed smart home. The smart home environment has been simulated using three agents and five locations in a house. The context-aware agents behave based on predefined rules designed for daily activities. Our proposal aims to reduce operational cost of running devices. In the future, monitors of health aspects belonging to home residents will sustain their healthy life daily. © 2023, Politechnica University of Bucharest. All rights reserved.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing Spam Email Detection with a Soft Voting Ensemble of Optimized Machine Learning

Enhancing Spam Email Detection with a Soft Voting Ensemble o...

引用

2024 IEEE International Conference on Computing, Applications and systems, COMPAS 2024

作者： Tazwar, Asif Daiyan, Md Mahir Jiabul Hoque, Md Saifuddin, Mohammed Khaliluzzaman, Md. International Islamic University Chittagong Dept. of Computer and Communication Engineering Chittagong Bangladesh Fse International Islamic University Chittagong Dept. of Computer and Communication Engineering Chittagong Bangladesh Fse International Islamic University Chittagong Dept. of Computer Science and Engineering Chittagong Bangladesh

ISBN: (纸本)9798331529765

Spam email detection is crucial for cybersecurity, as it protects user privacy and reduces security risks. The persistent presence of spammers necessitates continuous improvements in spam filtering measures. To address this challenge, this study employs Grid Search Optimizer to fine-tune the parameters of four distinct classifiers: Support Vector Machine (SVM), Random Forest, Naive Bayes, and XGBoost. Soft Voting serves as the final classifier, enhancing overall accuracy by integrating results from optimized classifiers to detect and classify spam emails across the Spam Mails Dataset and Enron1 Dataset. The experimental study compared the proposed model with relevant works and found that hyperparameter tuning and Soft Voting significantly enhanced its performance compared to existing approaches. The proposed ensemble model outperformed individual classifiers, achieving accuracies of 99.32% and 99.12%, respectively. Also, the ensemble model demonstrated an AUC of 1.00 on both datasets, indicating its effectiveness in distinguishing between spam and ham emails. This approach surpasses prior studies in accuracy, generalization, and robustness by innovatively combining Grid Search and Soft Voting. The constructed model exhibits high effectiveness and efficiency in the detection of spam emails. © 2024 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Attaining Peak Performance through an Interference-Aware Joint Channel Assignment Scheme for Wireless Mesh Networks 15

Attaining Peak Performance through an Interference-Aware Joi...

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Mulla, Tahseen Shikalgar, Anisa Dept. of Computer Engineering Vasantdada Patil Pratishthan's College of Engineering & Visual Arts Sion Mumbai India Dept. of Computer Science & Engineering Walchand College of Engineering Sangli India

ISBN: (纸本)9798331300579

Wireless Mesh Networks (WMNs) have witnessed a remarkable surge in popularity across a diverse spectrum of applications, encompassing military networks and public wireless infrastructures. These networks, emerging as the cornerstone of numerous wireless communication systems, offer expansive wireless connectivity to a substantial user base. Despite these advancements, the inherent challenge of interference among nodes poses a significant hurdle, resulting in diminished performance for WMNs. The prevalence of interference within WMNs is a critical concern, adversely affecting their operational efficiency. The need to address this challenge is underscored by the imperative to optimize WMN performance. A pivotal step in this direction involves the development of channel assignment algorithms that are not only efficient but also effective in mitigating interference issues. Efforts to enhance WMN performance through advanced channel assignment strategies are paramount. By devising algorithms that intelligently allocate channels and manage interference, we can significantly elevate the overall efficiency of WMNs. This imperative undertaking is fueled by the overarching goal of ensuring seamless connectivity and robust performance in the face of escalating demands from various application domains. In summary, the increasing prominence of WMNs in diverse sectors necessitates a proactive approach in overcoming performance limitations. Through the implementation of sophisticated channel assignment algorithms, we can fortify WMNs, ensuring their continued role as a reliable backbone for wireless communication systems. © Grenze Scientific Society, 2024.

关键词： Wireless mesh networks (WMN)

来源：评论

学校读者我要写书评

暂无评论

Simplifying Digital Streaming: An Innovative Cross-Platform Streaming Solution 15

Simplifying Digital Streaming: An Innovative Cross-Platform ...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Muduli, Debendra Sahoo, Saroj Kumar Mishra, Jayanta Kumar Pradhan, Debasish Sharma, Santosh Kumar C.V Raman Global University Dept. of Computer Science Engineering Odisha Bhubaneswar India Centurion University of Technology and Management Dept. of Computer Science Engineering India GITA Autonomous College Dept. of Computer Science Engineering Odisha Bhubaneswar India

ISBN: (纸本)9798350370249

Our research aims to investigate how reinforcement learning methods can be applied to develop a movie recommendation system. We frame the issue of interactive recommendation as a contextual multi-armed bandit, where the system learns user preferences by suggesting new movies and receiving feedback. Through reinforcement learning, we address challenges such as balancing exploitation and exploration and tackling the coldstart problem. Additionally, we incorporate the novelty factor of movies into our model. We evaluate both content-based and collaborative filtering approaches which achieved accuracy 72.33(%), both of which demonstrate effective recommendation outcomes. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Efficiency Redefined: The Document Scanner App for Precise Entity Identification with Customized NER 3

Efficiency Redefined: The Document Scanner App for Precise E...

引用

3rd IEEE Delhi Section Flagship Conference, DELCON 2024

作者： Javid, Sajid Saim, Mohammad Islam, Saiful Indraprastha Institute of Information Technology Delhi Dept. of Computer Science & Engineering Delhi India University of Cincinnati Dept. of Computer Science & Engineering CincinnatiOH United States Zakir Husain College of Engineering & Technology Aligarh Muslim University Dept. of Computer Engineering Aligarh India

ISBN: (纸本)9798331518592

In the era of rapid advancements in technology, the efficient digitization of paper-based documents remains a crucial challenge across various domains. The traditional approach to document scanning often struggles with accurate extraction of critical information from unstructured or diverse document formats. This paper presents the development of a web-based document scanner application that leverages Named Entity Recognition (NER) to extract entities from scanned business cards efficiently. The study aims to address the challenge of digitizing and organizing physical documents, with a focus on precise entity extraction. The methodology involves creating a custom dataset of scanned business cards, preprocessing the data, and training an NER model using machine learning techniques. The application is built using the Flask framework and integrates OpenCV for text extraction and SpaCy for NER. The key findings include the model's high F1 score in identifying entities such as names, organizations, designations, emails, and contact details. The application streamlines document digitization by automatically extracting and tagging relevant metadata, minimizing the need for manual data entry. This research contributes to enhancing document management and demonstrates broader applicability for other document types apart from business cards. The implications highlight improvements in workflow automation, data accuracy, and the potential for integrating with larger document management systems. © 2024 IEEE.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Exploring Climate Change Prediction Dynamics Using Machine Learning Approach: A Review 1

Exploring Climate Change Prediction Dynamics Using Machine L...

引用

1st International Conference on Computing, Sciences and Communications, ICCSC 2024

作者： Tiwari, Shashank Verma, Shikha Chauhan, Rosey Gupta, Neha Sharda Unviersity Dept. of Computer Science Gerater Noida India ABES Engineering College Dept. of Computer Science UP Ghaziabad India

ISBN: (纸本)9798350353648

Climate refers to the long-term weather patterns of a region. Variations in the weather have a lot of implications on our daily lives. Explore the application of deep learning techniques in climate prediction and related fields. It focuses on Long Short-Term Memory (LSTM) models for forecasting air quality, greenhouse temperature control, and urban flood water accumulation using Gradient Boosted Decision Trees (GBDT). The analysis concludes that deep learning, particularly LSTM, offers promising accuracy for various climate-related predictions. Challenges such as data scarcity, non-stationarity, and high dimensionality are addressed, highlighting the need for advanced models to capture complex climate system dynamics and human influences. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

COVID-19 Image Retrieval Using Siamese Deep Neural Network and Hashing Technique 14

COVID-19 Image Retrieval Using Siamese Deep Neural Network a...

引用

14th International Conference on Information and Knowledge Technology, IKT 2023

作者： Boroujeni, Farsad Zamani Afshari, Doryaneh Hossien Mahmoodi, Fatemeh Science and Research Branch Dept. of Computer Engineering Tehran Iran Branch Dept. of Computer Engineering Isfahan Iran

ISBN: (纸本)9798350349412

Medical images are crucial for early diagnosis and are increasingly important in modern medicine. This study presents a medical image retrieval system using a Siamese neural network with 13 layers. The system uses the Minimum Redundancy Maximum Relevance (mRMR) technique to extract deep features from the Siamese, and then uses binary hashing to retrieve similar images using Hamming distance. The experimental results on Covid-19 dataset show that the proposed method improves lung image retrieval by over 6% compared to previous methods, achieving an average accuracy of 93.83% and 92.73% in 5 and 10 retrieved images, respectively. © 2023 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Privacy-Enhanced Image Restoration in Remote Sensing via Federated Learning 12

Privacy-Enhanced Image Restoration in Remote Sensing via Fed...

引用

12th International Symposium on Digital Forensics and Security, ISDFS 2024

作者： Jahanzeb Khan, M. Rath, Suman Zaib, Muhammad Hassan University of Nevada Reno Dept. of Computer Science and Engineering Reno United States Air University Dept. of Computer Science Islamabad Pakistan

ISBN: (纸本)9798350330366

This research addresses the dual challenges of image restoration quality and data privacy in optical remote sensing. Traditional restoration methods often fall short due to the complex nature of remote sensing images, and data privacy concerns further complicate the use of advanced techniques. By integrating the Deep Memory Connected Neural Network (DMCN) with the Data-Decoupled Federated Learning (DDFL) framework, our approach enables significant improvements in image restoration without requiring direct access to sensitive raw data. This method not only enhances data privacy by leveraging federated learning principles but also incorporates advanced techniques like Gaussian image denoising to maintain high restoration quality despite potential noise introduced by the federated process. The performance of the federated DMCN, particularly on the UCMERCED dataset, demonstrates minimal accuracy degradation, even in the presence of noise, while the strategic use of Downsampling Units within DMCN optimizes computational efficiency. Our comprehensive evaluations reveal the effectiveness of this approach in balancing data privacy with the need for high-quality image restoration, suggesting a promising direction for future advancements in remote sensing applications. © 2024 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

AGS: Arabic GPT Summarization Corpus 4

AGS: Arabic GPT Summarization Corpus

引用

4th International Conference on Electrical, Communication and computer engineering, ICECCE 2023

作者： Atef, Abdelrahman Seddik, Fahd Elbedewy, Abdulrahman Dept. of Computer Engineering Nile University Giza Egypt Dept. of Computer Engineering Cairo University Giza Egypt

ISBN: (纸本)9798350369694

This paper presents a novel method for abstractive summarization of Arabic text using a large-language model (LLM), GPT-3.5 Turbo. We introduce AGS, the first publicly available dataset consisting of 142,000 pairs of articles and summaries with an average compression ratio of 70% written in Modern Standard Arabic (MSA) generated by an LLM. We proposed a baseline model that achieves high scores on ROUGE-L, similarity score, and compression ratio, while capturing the main points and details of the original articles. We fine-tuned mT5 on our dataset reaching a compression ratio of 62%, and similarity score of 82.65%. We release the AGS dataset to the research community, hoping to advance the field of Arabic natural language processing (NLP) and facilitate the development of effective abstractive summarization systems for Arabic text. © 2023 IEEE.

关键词： Large datasets

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：