检索结果-内蒙古大学图书馆

2024 International Conference on Advances in Modern Age Technologies for Health and engineering Science, AMATHE 2024

作者： Srinivasan, V. Prasanna Mohankumar, N. Prabakaran, T. Sairam, A. Elangovan, K. Velmurugan, S. R.M.D. Engineering College Department Of Information Technology Tamil Nadu Chennai India Maharashtra Nagpur India Joginpally B.R. Engineering College Department Of Computer Science And Engineering Telangana Hyderabad India Saveetha School Of Engineering Saveetha Institute Of Medical And Technical Sciences Department Of Computer Science And Engineering Thandalam Tamil Nadu Chennai India Dhanalakshmi Srinivasan Engineering College Department Of Mechanical Engineering Tamil Nadu Chennai India T.J.S. Engineering College Department Of Electronics And Communication Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350371567

To improve customer relations, this research investigates the possibility of using cloud-enabled collaborative filtering with robot waiters in restaurant environments. With the use of innovation, to revolutionize the way people eat out. It suggests using smart robots that can interact with customers and help the wait staff out. Customer preferences are analyzed, order suggestions are streamlined, and service is personalized using cloud-based collaborative filtering algorithms. Test this novel approach in a real-world restaurant setting to view how it changes things for the better in terms of customer happiness, service efficiency, and employee output. It seems that the combination of autonomous waiters and collaborative filtering on the cloud might completely change the way people dine out by making everything more streamlined and personalized to each individual's preferences. To the existing conversation about how robots, cloud computing, and customer service intersect in the restaurant industry, which is important since technology is still playing a major influence on how businesses engage with their customers. © 2024 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

dermoscopic Skin lesion Classification using Color Features Based on Fine-Tuning of Resnet50 and densenet121 Transfer learning Models

Dermoscopic Skin Lesion Classification using Color Features ...

引用

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

作者： Kujani, T. Kumar, V. dhilip Bhuvanya, R. Kavitha, A. Sathya, T. Sathiya Priya, S. Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Sri Ramachandra Institute of Higher Education and Research Sri Ramachandra Faculty of Engineering and Technology Chennai India Government Polytechnic College Computer Engineering Karur India Sri Sairam Engineering College Computer Science and Business Systems Chennai India

ISBN: (纸本)9798350360660

Skin cancer, which stands as the most prevalent form of human malignancy, is primarily identified through visual examination. The procedure for identifying skin lesions typically starts with an initial clinical assessment, which might be followed by dermoscopic analysis, a biopsy, and a subsequent histopathological checkup. Image-based Skin lesion classification presents a significant challenge due to the subtle and intricate variations in their appearance. deep Convolutional Neural Network (dCNN) show promising results in managing diverse and intricate tasks involving a wide array of finely detailed object categories. Skin lesions Classification is shown in this work initially using a six-layered CNN performed on the skin cancer dataset to classify seven classes of lesions with 10015 images. Exploratory data analysis of the dataset is performed to identify any outliers and to verify the balance of samples in each class. It was observed after 50 epochs, the training accuracy was 98.03% and the testing accuracy was 67.40%. To avoid the overfitting observed in the CNN approach, the pre-trained transfer learning models, Resnet50 and densenet121 were finetuned with data augmentation to handle the imbalance of samples present in seven classes. The results obtained prove that the densenet121 model achieves high performance compared with the other Resnet50 model after augmentation. © 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

News-driven Stock Price Forecasting in Indian Markets: A Comparative Study of Advanced deep learning Models 3

News-Driven Stock Price Forecasting in Indian Markets: A Com...

引用

3rd International Conference for Advancement in Technology, ICONAT 2024

作者： Attaluri, Kaushal Tripathi, Mukesh Kumar Reddy, Srinithi Shivendra Software Engineer-Machine Learning and AI Pegasystems India Worldwide Pvt Ltd Hyderabad India Vardhaman College of Engineering Department of Computer Science and Engineering Hyderabad India Vasavi College of Engineering Department of Information Technology Hyderabad India D. K. College Department of Computer Application Bihar Dumraon India

ISBN: (纸本)9798350354171

Forecasting stock market prices is a challenging task for traders, analysts, and engineers due to the myriad of variables influencing stock prices. However, the advent of artificial intelligence (AI) and natural language processing (NlP) has significantly advanced stock market forecasting. AI's ability to analyze complex data sets allows for more informed predictions. despite these advancements, stock price forecasting remains an area where AI has not yet achieved optimal results. In this paper, we forecast stock prices using 30 years of historical data from various national banks in India sourced from the National Stock Exchange. We employ advanced deep learning models, including multivariate multi-step long Short-Term Memory (lSTM), Facebook Prophet with lightGBM and Optuna, and Seasonal Auto-Regressive Integrated Moving Average (SARIMA). Additionally, we analyze news data from tweets and reliable sources like Business Standard and Reuters, recognizing their significant impact on stock price movements. © 2024 IEEE.

关键词： Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Optimal Key Generation for Privacy Preservation in Big data Applications Based on the Marine Predator Whale Optimization Algorithm

引用

Annals of data Science 2025年第2期12卷 539-569页

作者： Jadhav, Poonam Samir Borkar, Gautam M. Department of Computer Engineering Ramrao Adik Institute of Technology D.Y. Patil Deemed to be University Nerul Navi Mumbai400706 India D J Sanghvi College of Engineering Vile Parle Mumbai400056 India Department of Information Technology Ramrao Adik Institute of Technology D.Y. Patil Deemed to be University Nerul Navi Mumbai400706 India

In the era of big data, preserving data privacy has become paramount due to the sheer volume and sensitivity of the information being processed. This research is dedicated to safeguarding data privacy through a novel data sanitization approach centered on optimal key generation. due to the size and complexity of the big data applications, managing big data with reduced risk and high privacyposes challenges. Many standard privacy-preserving mechanisms are introduced to maintain the volume and velocity of big data since it consists of massive and complex data. To solve this issue, this research developed a data sanitization technique for optimal key generation to preserve the privacy of the sensitive data. The sensitive data is initially identified by the quasi-identifiers and the identified sensitive data is preserved by generating an optimal key using the proposed marine predator whale optimization (MPWO) algorithm. The proposed algorithm is developed by the hybridization of the characteristics of foraging behaviors of the marine predators and the whales are hybridized to determine the optimal key. The optimal key generated using the MPWO algorithm effectively preserves the privacy of the data. The efficiency of the research is proved by measuring the metrics equivalent class size metric values of 0.03, 185.07, and 0.04 for attribute disclosure attack, identity disclosure attack, and identity disclosure attack. Similarly, the discernibility metrics value is measured as 0.08, 123.38, 0.09 with attribute disclosure attack, identity disclosure attack, identity disclosure attack, and the Normalized certainty penalty is measured as 0.002, 61.69, 0.001 attribute disclosure attack, identity disclosure attack, identity disclosure attack. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Powered decentralized Resource Allocation and Management for Cloud Computing

Blockchain-Powered Decentralized Resource Allocation and Man...

引用

2024 IEEE International Conference on Recent Advances in Science and engineering Technology, ICRASET 2024

作者： Arun, M. Senthilvel, P. Gururama Muthukrishnan, A. Poongavanam, N. Pushparani, S. Panimalar Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai India Saveetha University Department of Computer Science and Engineering Tamil Nadu Chennai602 105 India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Avadi Tamil Nadu Chennai India Saveetha University Department of Computer Science and Engineering Chennai602105 India Meenakshi College of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai600 078 India

ISBN: (纸本)9798350388602

This research proposes a blockchain based distributed Resource Management and Allocation (dRMA) system for the Cloud Computing environment to overcome the shortcomings, ill prepared security and high cost incurred by the CC based on centralized and monolithic cloud architecture. The proposed system takes advantage of blockchain systems since they are distributed and due to their capability of not being altered once implemented, smart contracts are used to facilitate the distribution of resources. Moreover, the application of the Proof-of-Stake consensus mechanism and dynamic algorithms to distribute resources and prevent resource monopolization allow obtaining a high level of resource utilization together with low fees and high security levels. The implementation utilizes Ethereum's blockchain and evaluate real-world cloud environments' efficiency for resource utilization, transaction throughput, cost and robustness. This paper examines how blockchain has the propensity to redesign the means through which cloud computing resource management while improving its security, efficiency, and scalability. © 2024 IEEE.

关键词： decentralized finance

来源：评论

学校读者我要写书评

暂无评论

latency Reduction In Industrial Iot Using Yolov8 CNN Approach For Real-Time data Processing 15

Latency Reduction In Industrial Iot Using Yolov8 CNN Approac...

引用

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

作者： Nirmala, G. Prasanthi, Yeddula Sajitha, l.P. Ramesh Babu, P. Pratheeksha Hegde, N. laxmipriya, S. R.M.D Engineering College Department of Computer Science and Engineering Chennai India College of Agricultural Engineering Andhra Pradesh Madakasira India R. M. K Engineering College Department of Computer Science and Business Systems Tamilnadu Kavaraipettai India Wollega University College of Engineering and Technology Department of Computer Science Oromia Region Nekemte Ethiopia Nitte Deemed to be University Department of Ise Nmamit Karnataka Udupi India Mgr Educational and Research Institute Department of Civil Engineering Maduravayol Chennai India

ISBN: (纸本)9798350370249

during the era of Industry 4.0, the incorporation of the Internet of Things (IoT) into various industrial processes has become increasingly widespread, resulting in increased levels of production and efficiency. On the other hand, while dealing with the huge amounts of data produced by Industrial Internet of Things (IIoT) devices in real-time, it is particularly difficult to minimise latency in order to guarantee rapid decision-making capabilities. There has been a significant increase in the amount of data generated in industrial settings as a result of the proliferation of IIoT devices. low-latency data processing is something that businesses that rely on timely insights need to achieve in order to improve their operational efficiency, optimise their operations, and prevent failures. Through the application of the Yolov8 Convolutional Neural Network (CNN), this research introduces a novel approach to the processing of data in industrial settings in real time. The goal of this study is to find a solution to this urgent problem. The proposed approach involves utilising the Yolov8 CNN architecture to manage data in real time inside an Internet of Things environment. Through the use of simulated industrial scenarios, the study examines the latency reduction capabilities of Yolov8 in comparison to those of more conventional techniques. When it comes to processing data in real time in an industrial setting, the results demonstrate that the Yolov8 CNN approach is effective in significantly reducing the amount of latency that occurs. © 2024 IEEE.

关键词： Convolutional Neural Network Industrial IoT latency reduction Real-time data Yolov8 CNN

来源：评论

学校读者我要写书评

暂无评论

Ant Colony Optimization for Service Composition in Multi-cloud Environments 15

Ant Colony Optimization for Service Composition in Multi-clo...

引用

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

作者： Maurya, Mahesh Vidhya, G. Akram, Faiz Saravanan, M. Venkata Ramana, K. Rajakumari, S. K.C. College of Engineering Department of Computer Engineering Mith Bunder road Thane East Maharashtra Kopri India Sona College of Technology Department of Computer Science and Engineering Tamilnadu Salem India Jimma Institute of Technology Jimma University Faculty of Computing and Informatics Department of Computer Science Oromia Region Jimma Ethiopia Sri Eshwar College of Engineering Department of Ece Tamilnadu Coimbatore India Qis College of Engineering and Technology Department of Cse Andrapradesh Ongole India R.M.D. Engineering College Department of Mathematics India

ISBN: (纸本)9798350370249

the Ant Colony Optimization (ACO) algorithm is a famous metaheuristic technique that has been successfully applied in various optimization issues. It mimics the foraging conduct of ants to locate the shortest path among meals assets and their colony. Recently, ACO has been increasingly more applied for provider composition in multi-cloud environments. This involves the composition of offerings from different cloud carriers to satisfy the service necessities of a person. By way of using ACO, services can be correctly selected and composed from a couple of carriers, considering elements including cost, excellent, and availability. ACO has proven promising outcomes in enhancing the overall performance and reliability of carrier composition in multi-cloud environments, making it a precious technique in todays tremendously distributed computing landscape. © 2024 IEEE.

关键词： distributed cloud

来源：评论

学校读者我要写书评

暂无评论

Energy Harvesting circuit for digitization of Wiegand Pulse using Buck Converter in discontinuous Conduction Mode 5

Energy Harvesting circuit for Digitization of Wiegand Pulse ...

引用

5th International Conference on Energy, Power, and Environment, ICEPE 2023

作者： Chotai, Janki Thakker, Manish Gujarat Technological University Instrumentation & Control Engineering Department Ahmedabad India L D. College of Engineering Instrumentation & Control Engineering Department Ahmedabad India

ISBN: (纸本)9798350313123

Energy harvesting using Wiegand sensor as self-sustaining sensor is an emerging research area. The Wiegand sensor is a magnetic sensor that relies on the phenomenon of large Barkhausen jumps, generates a triangular voltage pulse upon the application of an alternating magnetic field. Pulse generation occurs regardless of how slowly the magnetic field variation occurs, is an attractive feature which enables its use as an energy harvester even in presence of low-frequency sources. Wiegand sensor as a sensing element have been used in many applications. But Wiegand sensor as energy harvester opens interesting, yet still overlooked possibilities in the energy harvesting field. The major challenge with the Wiegand sensor is energy harvested per pulse in the range of nJ. In this research work, we have proposed the circuit using Wiegand sensor that uses buck converter in discontinuous mode (dCM) mode to generate the digital pulse of 4.5 V and 10 ms at extremely low frequency for each magnetic field reversal without the use of any external power supply. Battery-less digital pulse generation is demonstrated for rotating application in the present study. The operating frequency up to 100 Hz has been considered. The main advantage of the proposed circuit is digitization of triangular shape Wiegand pulse is feasible for extremely slow varying magnetic field which can be used directly by microcontroller unit for further analysis. © 2023 IEEE.

关键词： Energy harvesting

来源：评论

学校读者我要写书评

暂无评论

Improving Beamforming in 5G Networks Using Reinforcement learning

Improving Beamforming in 5G Networks Using Reinforcement Lea...

引用

2024 IEEE International Conference on Communication, Computing and Signal Processing, IICCCS 2024

作者： Mahalakshmi, V. Alabdeli, Haider devi, G Sandhya Kaur, Simranjit Kharya, Asheesh Bhatt, Vimal G. Prince Shri Venkateshwara Padmavathy Engineering College Chennai India The Islamic University College Of Technical Engineering Department Of Computers Techniques Engineering Najaf Iraq The Islamic University Of Al Diwaniyah College Of Technical Engineering Department Of Computers Techniques Engineering Al Diwaniyah Iraq Aditya Engineering College Department of Computer Science & Engineering India Chandigarh Group of Colleges Department of Computer Application Chandigarh Engineering College Punjab Mohali India Ies College of Technology Department of Electronics & Communication Engineering M.P. Bhopal India A. D. Patel Institute of Technology Cvm University Department of It Gujarat India

ISBN: (纸本)9798350390759

This paper presents a study on training of Reinforcement learning (Rl) for balancing of beamforming in 5G network. Major challenges in giving directions in traditional beamforming collapse in dynamic surroundings: Beamforming which plays an essential role in increasing the strength and quality of a signal. Rl provides a solution by allowing system to discover that actions that lead to a favorable outcome in the environment. The research process will involve first having a 5G network emulation, designing a dQN for beamforming, and finally having a comparison with traditional methods or other established algorithms. Effects that are observed on signal-to-noise ratio and throughput, and latencies further showed that Rl based beamforming yield enhanced results. This paper also captures the possibilities of Rl in handling aspects of 5G network and the development of wireless communication. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Advanced Brain Tumor Segmentation Using UNet and Multiple Residual Networks 2

Advanced Brain Tumor Segmentation Using UNet and Multiple Re...

引用

2nd IEEE International Conference on Networking and Communications, ICNWC 2024

作者： Ramya, d. Manigandan, S.K. Velmurugan, J. Vishnukumar, A. Umarani, V. Reddy, P. V. Sai Ram Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Information Technology Chennai India Vel Tech High Tech Dr.Rangarajan Dr.Sakunthala Engineering College Department of Information Technology Chennai India Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Rajalakshmi Engineering College Department of Computer Science and Business Systems Chennai India Saveetha Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350365269

Accurate brain tumors segmentation is essential for precise diagnosis, planning, treatment, and monitoring of the tumor. However, the variations in tumor size, shape, and location, automating this process can be challenging. Segmentation using manual method is both time-taking and can produce inconsistent results. A promising solution to automated brain tumor segmentation is through deep learning approach that use convolutional neural networks. The models that have used U-Net shown considerable promise in enhancing the precision and effectiveness of automated Brain tumor segmentation. Still, there is a scope for improvement in accurate segmentation of brain MRI images. The segmentation of Brain MRI Images greatly helps in earlier diagnosis of Brain tumor effectively. The proposed model using ResNet, ResNext, and Inception as a backbone of U-Net with BraTs 2020 dataset could potentially reduce the workload of radiologists and provide more consistent results across experts. Future research can explore the use of other architectures or hybrid models to enhance brain tumor segmentation performance. © 2024 IEEE.

关键词： Tumors

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：