检索结果-内蒙古大学图书馆

1st International Conference on Innovations in Communications, Electrical and computer engineering, ICICEC 2024

作者： Rajalakshmi, P. Dhivya, K. Anitha, D. Sandhya, Potturi Gnanavel, N. Muthulekshmi, M. Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tami Nadu Chennai India SRM Institute of Science and Technology Department of Electronics and Communication Engineering Tamil Nadu Chennai India Department of Information Technology Tamil Nadu Namakkal India Department of Computer Science and Engineering Andhra Pradesh Bhimavaram India Department of Computer Science and Engineering Tamil Nadu Salem India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Biomedical Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350376517

This research introduces a new method for home gardening that uses neural networks to analyze plant development, cloud-connected plant care, and robotic help. The goal of combining these technologies is to make home gardening more efficient and productive while also allowing for remote management and monitoring. To understand how plants develop, our system collects data in real-time from a variety of sensors that measure things like temperature, humidity, and light levels, and then runs that data through neural networks. To further alleviate homeowners' workloads and guarantee plants get ideal care, robotic assistance is used to automate activities like watering, fertilizing, and pest management. Connecting to clouds allows customers to manage their garden from anywhere, get alerts when certain conditions are met, and get maintenance advice based on data. Through a series of battery tests, it can be observed that the proposed technique is superior to conventional gardening practices in terms of plant development and health. For eco-conscious green thumbs and busy gardeners, our system is the next big thing in smart home gardening, providing a practical and long-term solution to their problems. © 2024 IEEE.

关键词： Automation Plant health Remote monitoring Robotic assistance Sustainable gardening

来源：评论

学校读者我要写书评

暂无评论

Framework for Logistics During Hajj Using Autonomous Mobile Robots 1

Framework for Logistics During Hajj Using Autonomous Mobile ...

引用

1st International Conference on Logistics, ICL 2024

作者： Nasti, Shoaib Mohd Chishti, Mohammad Ahsan Central University of Kashmir Department of Information Technology Ganderbal India National Institute of Technology Department of Computer Science and Engineering Srinagar India

ISBN: (纸本)9798331518844

Every year, Muslims worldwide travel to Saudi Arabia to Perform Hajj. Both government and private organizations provide various services and facilities to support these pilgrims and resolve any difficulties they may face. There is a scope for improvement in high-quality and smart logistical services for pilgrims. Smart logistic services have emerged as a practical solution to the growing complexity and volume of logistical operations. Artificial Intelligence, Internet of Things, and Robotics are all helping logistical operations to function more smoothly and efficiently. This paper briefly describes the background of the holy pilgrimage. Then, it contributes to the literature by introducing logistics services using autonomous mobile robots. Finally, the theoretical framework for the smart logistic system using an autonomous mobile robot is illustrated, which summarizes our survey on using the autonomous mobile robot for logistic services during the Hajj season. © 2024 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Masked Siamese Prompt Tuning for Few-Shot Natural Language Understanding

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第2期5卷 624-633页

作者： Ni, Shiwen Kao, Hung-Yu Chinese Academy of Sciences Shenzhen Institute of Advanced Technology Shenzhen518000 China National Cheng Kung University Department of Computer Science and Information Engineering Tainan701401 Taiwan

Recently, prompt-based learning has shown excellent performance on few-shot scenarios. Using frozen language models to tune trainable continuous prompt embeddings has become a popular and powerful methodology. For few-shot natural language understanding, even if we freeze the parameters of the pretrained language model, the learned pseudo-prompts might still be overfitted. In this article, we propose a novel masked Siamese prompt tuning (MSP-tuning) to improve few-shot natural language understanding. Concretely, MSP-tuning masks randomly out part of the prompt tokens to get a pair of masked Siamese prompts for each sample. Each training sample is then fed to the model twice with the masked Siamese prompts. Finally, MSP-tuning minimizes the Jensen-Shannon-divergence (JSD) between the two output probability distributions of the pretrained language model to regularize the model further. Experiment results on the few-shot GLUE benchmark and SuperGLUE benchmark show that MSP-tuning outperforms previous approaches. Numerically, our MSP-tuning achieves an average improvement of 1.79% (BERT-base) and 1.39% (BERT-large) of the GLUE benchmark and 1.90% (RoBERTa-base) and 1.71% (RoBERTa-large) of the SuperGLUE benchmark compared to state-of-the-art method P-tuning. Our method facilitates applying large pretrained language models in natural language understanding. © 2023 IEEE.

关键词： Bit error rate

来源：评论

学校读者我要写书评

暂无评论

The integration of IoT in learning environments: Assessing the impact of educational empowerment and addressing its challenges 4

The integration of IoT in learning environments: Assessing t...

引用

4th International Conference on Innovative Practices in technology and Management, ICIPTM 2024

作者： Rajora, Ricky Rajora, Aarju Sharma, Bhanu Aggarwal, Priyanshi Thapliyal, Siddhant Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Chandigarh Engineering College Department of Computer Science & Engineering Mohali India Computer Science & Engineering Graphic Era Hill University Uttarakhand Dehradun India Computer Science & Engineering Graphic Era Deemed to Be University Uttarakhand Dehradun India

ISBN: (纸本)9798350307757

This article explores the diverse impact of the Internet of Things (IoT) on education. This research investigation examines the possible uses of the IoT in several educational domains, with a particular focus on the significant impact of IoT on student engagement, learning methodologies, and administrative efficacy. While explaining the considerable advantages, this discourse also acknowledges the significant obstacles pertaining to integration, security, and privacy. The study finishes by presenting a forward-looking model for smart campuses, providing a holistic viewpoint on the IoT impact on transforming education. The article examines the impact of the IoT on educational practices and emphasizes the significance of institutional adaptation to effectively incorporate this technological paradigm shift. The article presents an elaborate framework for the prospective development of intelligent campuses and higher education institutions. This article offers a comprehensive guide for effectively using the whole capabilities of the IoT within the realm of education. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Edge Computing for Distributed and Cooperative Media Algorithms in Connected Networks 15

Edge Computing for Distributed and Cooperative Media Algorit...

引用

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

作者： Grace, V. Lilly Gupta, Anchal Giri, Rakesh Kumar Dhope, Tanuja Satish Vittapu, Mani Sarma Dhabliya, Dharmesh G. Pullaiah College of Engineering and Technology Department of Computer Science and Engineering Andhra Pradesh Kurnool India Chitkara University Centre of Research Impact and Outcome Punjab Rajpura India Sunrise University Computer Science & Engineering Alwar India College of Engineering Electronics and Communication Maharashtra Pune India Mallareddy Engineering College and Management Sciences Kistapur Village Computer Science and Engineering Medchal Telangana Hyderabad India Vishwakarma Institute of Information Technology Department of Information Technology Maharashtra Pune India

ISBN: (纸本)9798350370249

Side Computing is a rising technique used for connected networks' allotted and cooperative media algorithms. Part Computing refers to processing operations being carried out near the source of the facts, generally close to the edge of the network, in place in a centralized cloud. It allows information to be processed quickly, securely, and reliably in remote or low-connectivity locations, allowing dispensed computing operations inside connected networks. This distributed machine enables latency when working with significant facts sets and enhances security and reliability. Cooperating media algorithms, including laptop vision, audio processing, or natural language processing, are frequently optimized using aspect Computing in related networks. The advantages of facet Computing allow for progressed scalability, green helpful resource utilization, and better latency performance, mainly in areas that suffer from restrained or negative networking situations and bandwidth. Moreover, aspect computing enables enhanced privacy, protection, and personal revel when handling sensitive information and data stored within the cloud. © 2024 IEEE.

关键词： Computing Distributed Handling Networking Performance Scalability

来源：评论

学校读者我要写书评

暂无评论

Collaborative Filtering of Malicious Information from the MULTimedia Data Using s 1

Collaborative Filtering of Malicious Information from the MU...

引用

1st International Conference on computer science and Emerging Technologies, CSET 2023

作者： Parasuraman, Manikandan Abirami, G. Arockia Raj, A. Krishnan, Batri Munnangi, Ashok Kumar Kumaresan, M. School of Computer Science and Engineering Jain Deemed to Be University Bengaluru India Sathyabama Institute of Science and Technology Department of Computer Science Chennai India Madanapalle Institute of Technology and Science Department of Computer Science and Engineering - Data Science Madanapalle India Velagapudi Ramakrishna Siddhartha Engineering College Vijayawada India

ISBN: (纸本)9798350341737

Due to high proliferation of unsolicited information in the text, image and video files, the social media analytics engine suffers from losing its user, user privacy and others. The unsolicited information is been a huge threat to the service provides as it affects the reputations of the services provided and hence it is necessary to develop an intelligent model. Modern machine learning techniques are applied to identify and filter unsolicited information. However, some of the conventional methods are designed in an insecure way while processing all the text file, image and video files. © 2023 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Multilevel Discrete Cosine Transform and CNN-Based Image Steganography 3

Multilevel Discrete Cosine Transform and CNN-Based Image Ste...

引用

3rd International Conference on Intelligent Systems, Advanced Computing, and Communication, ISACC 2025

作者： Subburaj, Brindha Sai, Aditya Shantanu, Shantanu Won, Daehan Vellore Institute of Technology School of Computer Science and Engineering Chennai India Binghamton University Department of Systems Science and Industrial Engineering United States

ISBN: (纸本)9798331523893

This paper investigates the growing role of steganography in cybersecurity and presents a hybrid implementation called Multi-level Discrete Cosine Convolution (MDCC) that applies a Multi-level Discrete Cosine Transform (MDCT) and a Convolutional Neural Network (CNN). Steganography provides some advantages compared to cryptography, mainly its invisibility, but there are weaknesses in information capacity and resistance to attacks in traditional techniques. The paper suggests solving these difficulties with a new steganography method using deep learning. The proposed MDCC method provides an opportunity to encrypt large amounts of data in realistic images that are beyond human visual perception. The system is trained on the ImageNet dataset by using a loss function to balance the quality of the cover image and the information it conceals within it. The MDCC model proposed yields accurate results for all metrics since PSNR, SSIM, and bits per pixel come out to be 80.13dB, 0.9918, and 12.5 bpp, respectively. © 2025 IEEE.

关键词： Discrete cosine transforms

来源：评论

学校读者我要写书评

暂无评论

Decentralized Intrusion Detection in Peer-to-Peer Networks using Stacking Ensemble Model 1

Decentralized Intrusion Detection in Peer-to-Peer Networks u...

引用

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

作者： Devi, R. Renuga Riadhusin, Rame Anu, D. Swarnateja, R. Revathi, R. 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 Artificial Intelligence and Data Science Bengaluru India Dhanalakshmi Srinivasan College of Engineering and Technology Department of Information Technology Mamallapuram India New Prince Shri Bhavani College of Engineering and Technology Department of Electrical and Electronics Engineering Chennai India

ISBN: (纸本)9798331529246

In recent years, due to the rise in Peer to Peer (P2P) networks has brought a significant way in which the data is shared and services are offered over the internet. These P2P networks make use of decentralized architecture in which nodes directly interact and exchange resources. However, due to the use of decentralized architecture, the P2P networks are exposed to various security threats such as data breaches, and other malicious attacks. In this research, Stacking Ensemble Model (SEM) is proposed for network intrusion detection in P2P networks. Initially, the data is considered from network intrusion detection dataset and then preprocessed with data imputation and min-max normalization effectively handles the missing values and rescales the data into significant range. After that, Recursive Feature Elimination (RFE) is incorporated to select optimal features from preprocessed data based on feature importance. Finally, the proposed SEM effectively detects the intrusion in P2P networks which enhances the security. From the results, the proposed SEM model obtained a better outcome in terms of accuracy, precision, recall, and F1-score compared to the existing K-Nearest Neighbor (KNN) by accomplishing 97.20%, 94.71%, 96.62%, and 95.65%, respectively. © 2025 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Exploring The Synergy of Convolutional Neural Network For Enhancement Image Classification 2

Exploring The Synergy of Convolutional Neural Network For En...

引用

2nd IEEE International Conference on Trends in Quantum Computing and Emerging Business Technologies, TQCEBT 2024

作者： Suguna, R. Valantina, G. Mary Kanna, Rajesh Lakshmi, D. Muneeshwari, P. Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering AvadiTamil Nadu Chennai India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Tamil Nadu Chennai India Amet Deemed to Be University Department of Petroleum Engineering Chennai India Panimalar Engineering College Department of Computer Science and Engineering Tamil Nadu Chennai India Rajalakshmi Engineering College Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350384277

This study explores the synergy of Convolutional Neural Networks (CNNs) for enhancing image classification through a comprehensive series of experiments. Four main aspects of our investigation include model architectures, the impact of loss functions, hyperparameter tuning, and data augmentation strategies. We conducted these experiments on a diverse and representative image dataset. In the first set of experiments, we evaluated various CNN architectures. The baseline CNN (CNN-1) achieved a training accuracy of 95% and validation accuracy of 91%, with a test accuracy of 90%. Introducing attention mechanisms (CNN-2) and residual blocks (CNN-3) yielded improved results, with test accuracies of 91% and 92%, respectively. The EfficientNet-B0 architecture outperformed others, achieving a test accuracy of 93%. In the second set of experiments, we examined the impact of different loss functions. While the standard Cross-Entropy loss achieved a test accuracy of 88%, the Focal Loss and Adversarial Loss improved accuracy to 90% and 89%, respectively. Our customized loss function further enhanced performance, achieving a test accuracy of 91%. In the third set of experiments, we conducted hyperparameter tuning. We tested various combinations, and the best-performing hyperparameter set included a learning rate of 0.0003, a batch size of 128, and a dropout rate of 0.25, resulting in a test accuracy of 93%. Finally, in the fourth set of experiments, we explored different data augmentation strategies. Rotation & Scaling and Translation & Cropping yielded the highest test accuracies of 92% and 93%, respectively, while Color Augmentation achieved 91%. The absence of data augmentation resulted in a test accuracy of 88%. © 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

Big Data Analytics for Quality Control in The Pharmaceutical Industry 10

Big Data Analytics for Quality Control in The Pharmaceutical...

引用

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Malathi, P. Jansi, S. Prabhakaran, M.V. Senbagam, K. Sujatha, M.P. Sadaieswaran, R. Saveetha College of Liberal Arts and Sciences Saveetha Institute of Medical and Technical Sciences Department of Data Analytics Tamil Nadu Chennai India Acharya college of Engineering and Technology Department of Computer science and Engineering Achariyapuram Puducherry India Dhanalakshmi Srinivasan College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Mamallapuram India Agni College of Technology Department of Computer Science and Engineering Chennai Thalambur India Tagore College of arts and science Department of Computer Applications Chennai Chromepet India

ISBN: (纸本)9798350384369

In order to ensure the safety and manufacturing efficiency of pharmaceuticals, rigorous quality control measures are necessary. However, existing quality control systems often struggle with industrial process complexity and regulatory requirements. The proposed study highlights the need for a revolutionary strategy to overcome the limitations of existing systems. Quality control systems in existing systems have limitations such as real-time monitoring, insufficient data analysis for pattern identification, and limited predictive capabilities. These limitations have an impact on the industry's ability to recognize and manage quality concerns, posing a danger to medicine manufacturing. For addressing these issues, a novel approach to maintain quality control in the pharmaceutical sector using big data analytics is proposed. Advanced analytics are used for real-time monitoring, data analysis and predictive modeling in the proposed system. The results and analysis through extensive comparisons shows proposed big data analytics system achieves 95% fault detection, 40% downtime reduction, and 35% waste reduction in pharmaceutical manufacturing. The proposed system's ability to handle massive datasets allows it to identify complicated patterns and abnormalities, enabling proactive quality control. The implementation exceeds industry standards, addressing data privacy and security concerns. © 2024 IEEE.

关键词： Data quality

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：