检索结果-内蒙古大学图书馆

Knowledge engineering and Communication Systems (ICKECS), International Conference on

作者： A J V MadhuMohan Hemanth Raghu R Priyanka Sonia Maria Dsouza K B Teena Shravya Shetty Department of Machine Learning B.M.S. College of Engineering Bengaluru India Department of ISE Cambridge Institute of Technology Bengaluru Department of AI & ML New Horizon College of Engineering Bengaluru East Point College of Engineering and Technology Bengaluru Artificial Intelligence and Machine Learning New Horizon College of Engineering Bengaluru India

ISBN: (数字)9798350359688

ISBN: (纸本)9798350359695

This research paper presents a comprehensive approach for extracting and classifying text from images using computer vision and deep learning techniques. We demonstrate a step-by-step process of preprocessing, text extraction, and classification with a Multi-Layer Perceptron(MLP). The proposed method is evaluated on a dataset of player images having different kill counts and shows promising results using bounding box algorithm in automated text extraction and classification.

关键词： Measurement Knowledge engineering Deep learning Computer vision Communication systems Weapons Games

来源：评论

学校读者我要写书评

暂无评论

Deep learning: Exploring the Depths of artificial Neural Networks for Advanced Data Analysis and Pattern Recognition 5

Deep Learning: Exploring the Depths of Artificial Neural Net...

引用

5th IEEE Global Conference for Advancement in technology, GCAT 2024

作者： Ravikumar, Rajesh Jagadeesan Ammupriya, A. Devi, P.P. Pandi, V.Samuthira Akula, Akhila Sankar, K. Evernorth Health Services ChattanoogaTN37402 United States St Joseph's College of Engineering Department of Mba Chennai India Vel Tech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology Department of Artificial Intelligence and Machine Learning Avadi Chennai India Chennai Institute of Technology Centre for Advanced Wireless Integrated Technology Tamil Nadu Chennai India Mlr Institute of Technology Department of Ece Hyderabad India Rajalakshmi Engineering College Department of Biomedical Engineering Chennai India

ISBN: (纸本)9798350376685

This research provides a comprehensive exploration of LSTMs, CNNs, and RNNs, with a focus on their application in advanced data analysis and pattern recognition. We begin by examining the theoretical underpinnings of each architecture, highlighting their unique features and the mechanisms by which they process and learn from data. In the process of collecting long-term relationships in sequential data, LSTMs have been demonstrated to perform exceptionally well, making them an excellent choice for applications such as language modeling and time series prediction. CNNs are discussed in the context of their ability to extract hierarchical features from spatial data, rendering them particularly effective for image and video analysis. RNNs, with their inherent ability to process sequences of varying lengths, are analyzed for their applications in speech recognition and machine translation. Following this, the research begins to conduct a comparative examination of different architectures, examining how well they perform on benchmark datasets as well as challenges that are encountered in the real world. We assess their strengths and limitations, considering factors such as accuracy, computational efficiency, and scalability. Additionally, we explore the challenges associated with training deep neural networks, including the need for extensive data preprocessing, the risk of overfitting, and the importance of hyperparameter tuning. Finally, we discuss the implications of these findings for future research and practical applications in data analysis and pattern recognition. The study concludes that while each architecture has its niche, the combination of LSTMs, CNNs, and RNNs offers a powerful toolkit for tackling complex problems across diverse domains. The research underscores the potential of deep learning to unlock insights from data at unprecedented scales and complexities, paving the way for innovative solutions in fields ranging from healthcare to finance. © 2024 IE

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Enabled Federated learning Systems with Explainable AI: A Review 2

Blockchain-Enabled Federated Learning Systems with Explainab...

引用

2nd International Conference on machine learning and Autonomous Systems, ICMLAS 2025

作者： Potdukhe, Nayan Gourshettiwar, Palash Zade, Sujal Waghale, Atharva Datta Meghe Institute of Higher Education and Research Sawangi Meghe Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Maharashtra Wardha442001 India Datta Meghe Institute of Higher Education and Research Sawangi Meghe Computer Science and Medical Engineering Faculty of Engineering and Technology Maharashtra Wardha442001 India

ISBN: (纸本)9798331505745

The convergence of Blockchain with Federated learning (FL) technology and Explainable artificial intelligence (XAI) serves as a new framework to solve privacy protection problems, security issues, and interpretability needs. Model training collaborations supported by FL technology allow different entities to develop models while safeguarding raw data from exposure during training processes, thus addressing privacy needs in healthcare and finance. The combined challenges of model vulnerability to malicious attacks, data poisoning vulnerabilities, and explainability issues block broad industrial adoption. Blockchains strengthen FL security systems by providing decentralised solutions that produce unchangeable audit trails through their proof of transparency, immutability, and distributed consensus models. By enabling model interpretability, XAI methods build stakeholder trust and ensure system accountability. The study combines the technologies to analyse current systems and identify gaps that integrated systems should resolve. A detailed review examines explainable blockchain models and privacy preservation methods to tackle performance and implementation limitations within the framework. Combining these technologies builds a transformative process to create secure AI systems that maintain interpretability functions and protect data privacy during system development as researchers develop frameworks for wider application deployment. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Custom Transformer-Based Approach for Enhanced Bengali Automatic Speech Recognition 1

Custom Transformer-Based Approach for Enhanced Bengali Autom...

引用

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

作者： Deepa, R. Jayalakshmi, V. Thilakavathy, P. Manikandan, G. Surendran, R. SRM Institute of Science and Technology School of Computing Department of Computing Technologies Chennai India SRM Institute of Science and Technology Department of Computer Science and Applications Ramapuram Chennai India Vels Institute of Science and Engineering Vels Institute of Science Technology and Advanced Studies Chennai India Anna University St. Joseph's College of Engineering Department of Artificial Intelligence and Machine Learning Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Chennai India

ISBN: (数字)9798350376517

ISBN: (纸本)9798350376517

Automated speech recognition (ASR) systems struggle with Bengali, which is the fifth most spoken language. Bengali has a varied morphology, many dialects, and limited high-quality annotated voice data. Traditional voice recognition techniques work well however struggle with Bengali phonetics and syntax. This method eliminates the need for large amounts of tagged data and the difficulties of differentiating sounds in different languages, both issues are addressed by this procedure. The research in this paper offers an Intellectual Bengali Speech Recognition System using Deep learning Techniques (IBSRS-DLT). The model in this system uses transformer architecture and attention processes to manage Bengali speech pattern long-range dependencies. The IBSRS-DLT outperforms standard models in recognition accuracy using a pre-trained transformer model modified for phonetic and lexical correctness and fine-tuned on Bengali datasets. After training on a vast Bengali speech corpus, real-world datasets and rigorous simulations confirm the system. IBSRS-DLT can be used for automatic transcription, voice-controlled devices, and Bengali virtual assistants, such applications are efficient and accessible. The simulation showed a considerable boost in recognition speed and a decrease in keyword mistakes compared to current methods. This paper shows that deep learning can solve linguistic issues in ASR systems, enabling scalable regional language detection. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Empowering Early Diagnosis: Optimizers Revolutionizing Breast Cancer Detection with DenseNet 3

Empowering Early Diagnosis: Optimizers Revolutionizing Breas...

引用

3rd International Conference on Technological Advancements in Computational Sciences, ICTACS 2023

作者： Pranati, V. Khatri, Narendra Sharma, Harish Shukla, Praveen Kumar Manipal Institute of Technology Manipal Academy of Higher Education Department of Biomedical Engineering Manipal576104 India Manipal Institute of Technology Manipal Academy of Higher Education Department of Mechatronics Manipal576104 India School of Computer Science and Engineering Manipal University Jaipur Department of Artificial Intelligence and Machine Learning Jaipur India School of Computer and Communication Engineering Manipal University Jaipur India

ISBN: (纸本)9798350342338

Breast cancer, a highly lethal disease with a significant global impact, requires early detection to reduce its mortality rate. The emergence of pre-trained Deep learning (DL) algorithms, commonly utilized for object detection, image classification, and image segmentation, has advanced early breast cancer detection. Several researchers have explored early breast cancer detection using pre-trained DL algorithms in conjunction with classifiers or other existing methods. However, existing research lacks a thorough examination of optimizers and their potential influence on the behaviour of these pre-trained algorithms. This study aims to comprehensively investigate the behaviour of the pre-trained DenseNet201 model under various optimizer and learning rate configurations. The analysis reveals that the DenseNet model achieved superior performance (100% accuracy) with the SGD (Stochastic Gradient Descent), and RMSProp optimizers at a learning rate of 10-2 and 10-3, respectively. However, at a learning rate of 10-4, the Adam optimizer demonstrated the highest accuracy of 99%. © 2023 IEEE.

关键词： Breast Cancer Detection DenseNet201 learning Rates Optimizers Pre-trained DL algorithms

来源：评论

学校读者我要写书评

暂无评论

Con-Fog: Consensus-Driven Fog Node Selection in FU-Serve Platform for IoT Applications

引用

IEEE Internet of Things Journal 2025年

作者： Imandi, Raju Roy, Arijit Sethi, Kamalakanta Pavan, Kumar Guizani, Mohsen Indian Institute of Information Technology Computer Science and Engineering Group Sri City India Indian Institute of Technology Department of Computer Science and Engineering Patna India Mohamed bin Zayed University of Artificial Intelligence Machine Learning Department Abu Dhabi United Arab Emirates

The rapid expansion of Internet of Things (IoT) devices and applications necessitates the need for more efficient computational and data management strategies. The Fog-enabled UAV-as-a-Service (FU-Serve) platform addresses these demands by integrating fog computing to enhance the operational efficiency of UAVs in IoT environments. Despite its advantages, the FU-Serve platform faces significant challenges, including data transmission latency, resource allocation, and energy management, contributing to the underutilization of UAVs and fog nodes. To address these challenges, this paper introduces a consensus-driven approach, Con-Fog, that optimizes the selection of fog nodes for UAVs within the FU-Serve platform. Con-Fog evaluates potential fog nodes within the communication range by computing utility values based on geographical distance, link quality, available computational resources, and residual energy. UAVs rank these nodes according to their utility values and select the most suitable ones through a consensus-based approach, ensuring alignment with the operational demands of IoT devices. Additionally, we apply an optimal best-fit algorithm to refine fog node allocation, maximizing resource utilization while keeping it below each node’s capacity threshold (T%). Our simulation results show that Con-Fog significantly enhances key IoT performance metrics. Transmission time and the number of unassigned UAVs decrease by 10%-30% and 20%-40%, respectively, while residual energy increases by 30%-50% compared to existing systems. These improvements enhance the management of UAV and fog node resources, thereby advancing the effectiveness of IoT applications within the FU-Serve platform. © 2014 IEEE.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

Research on Graphic Design Image Processing technology Based on Newton's method in Photoshop 2

Research on Graphic Design Image Processing Technology Based...

引用

2nd International Conference on Smart Technologies for Smart Nation, SmartTechCon 2023

作者： Al-Fatlawy, Mohammed Hussien Yadav, Santosh Kumar Gopalakrishnan, S. Sahaya Sheela, M. Srinivasan, V. Uma Reddy, N.V. College of Technical Engineering The Islamic University Najaf Iraq Department of Electronics & Communication Engineering IES College Of Technology MP Bhopal462044 India Tamil Nadu Kelambakkam India Tamil Nadu Chennai India New Prince Shri Bhavani College Of Engineering And Technology Tamilnadu India Department of Artificial Intelligence & Machine Learning New Horizon College of Engineering Bellandur Post Bengaluru560103 India

ISBN: (纸本)9798350305418

The term "computer graphics and image processing technology" refers to a technology that is based on computers and makes use of software to process graphics and images in a comprehensive manner. Since its introduction, it has been the subject of extensive research and practical use, and as a result, it has steadily evolved into a fully formed and flawless technical system. Image editing, image composition, color correction, the generation of functional color effects, and other related tasks are among the primary features included in Photoshop. The title bar, the menu bar, the picture editing window, the status bar, the toolbox, the control panel, the drawing mode, the file format, the file size, the color setting, shortcut keys, and the color mode are all components of the operational interface. Studying the image processing technology used in graphic design based on NM (Newton's technique) in Photoshop platform is the focus of this research project. Using NM as a foundation, construct a graphic design image processing model. in order to make the global convergence better and reduce the goal function as much as possible. To verify that the goal function is moving in the desired direction, the modified global criterion of NM is applied. According to the findings, the new and improved algorithm has a running time that is 3.67 percent and 2.25% less than that of the NM and the inexact Newton method respectively. The root-mean-square error of the reconstructed image of the cross-section with a diameter of 19mm is controlled to be approximately 5.03%. This error decreases as the amount of Gaussian noise increases. Even if there is significant interference from Gaussian noise when the algorithm reconstructs sections of varying diameters, the quality of the reconstructed image of the improved NM has only a little amount of impact on the reconstructed image. © 2023 IEEE.

关键词： Graphic design Image processing Newton's method Photoshop

来源：评论

学校读者我要写书评

暂无评论

IoT-Enabled Weather Monitoring and Rainfall Prediction using machine learning Algorithm 2

IoT-Enabled Weather Monitoring and Rainfall Prediction using...

引用

2nd International Conference on Augmented intelligence and Sustainable Systems, ICAISS 2023

作者： Indhumathi, S. Aghalya, S. Smitha, J.A. Aarthi M, Presitha Sphoorthy Engineering College Department of Cse - Artificial Intelligence and Machine Learning Telangana Hyderabad India St. Joseph's College of Engineering Department of Electronics and Communication Engineering Tamil Nadu Chennai India Sri Sairam College of Engineering Department of Computer Science and Engineering Karnataka Bengaluru India Shree Sathyam College of Engineering and Technology Department of Computer Science and Engineering Tamilnadu Salem India

ISBN: (纸本)9798350325799

The proposed weather monitoring system utilizes the Internet of Things (IoT) to make real-time data accessible to everyone. Various sensors are deployed to gather weather-related information such as temperature, humidity, wind speed, rainfall, and atmospheric pressure. The collected data is transmitted to a cloud server through the IoT, where it is stored and processed. Web page users from any global location may view the uploaded information. Support Vector machine (SVM) then analyzes the data and predicts rainfall patterns based on historical records and current weather conditions. The data is then represented graphically and displayed for the user. Integrating machine learning algorithms enhances the accuracy of rainfall predictions, allowing for better preparation and planning in various sectors such as agriculture, weather stations, water resource management, marine industries, and disaster response. For improving weather forecasting systems, enabling more informed decision-making and proactive measures in various domains impacted by weather conditions. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

machine learning with Monarch Butterfly Optimization for Prediction of Emergency Patient Admission Status 5

Machine learning with Monarch Butterfly Optimization for Pre...

引用

5th IEEE International Conference on Electrical, Computer and Communication Technologies, ICECCT 2023

作者： Vijayarangam, S. Vasundhara, S. Beherac, Nihar Ranjan Das, Shyamali Chandre, Shanker Rajagopal, R. Sri Indu College of Engineering and Technology Department of Computer Science and Engineering Telangana Hyderabad India G.Narayanamma Institute of Technology and Science Department of Humanities and Mathematics Telangana Hyderabad India Swiss School of Business and Management Geneva Petit-Lancy1213 Switzerland CMR Institute of Technology AECS Layout Department of Artificial Intelligence and Machine Learning Karnataka Bangalore India SR University Department of Computer Science & Artificial Intelligence Telangana Warangal India Alliance College of Engineering & Design Department of Computer Science & Engineering Alliance University Karnataka Bengaluru India

ISBN: (纸本)9781665493604

Emergency admission is one of the most important resources of healthcare expenditure. The accessibility of predictive methods is support to recognize the admission status of arriving patients and the patient mix that supports managing downstream resources and decreasing overpopulation at emergency department (ED) by restriction boarding delays. In recent times, machine learning (ML) techniques are well enhanced and executed in several applications like health protection, cancer detection, and hospital operations. But, most difficult problem with ML is that each technique has parameter and without optimizing the parameter, attaining a higher accuracy method develops very complex. This study introduces machine learning with Monarch Butterfly Optimization for Prediction of Emergency Patient Admission Status (MLMBO-PEP A) technique. The presented MLMBO-PEP A technique can predict the admission status of the emergency patient. In the presented MLMBO-PEP A technique, data normalization is initially performed to scale the medical data. For predictive process, the MLMBO-PEP A technique uses Dendritic Neuron Model (DRN). The MBO technique is used to optimize the forecasting outcomes of the DRN model. A widespread simulation study is performed for ensuring the better performance of the MLMBO-PEP A technique. The resultant values implied the improved efficacy of the MLMBO-PEP A technique under different evaluation metrics. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

machine learning-Enhanced Self-Management for Energy-Effective and Secure Statistics Assortment in Unattended WSNs

引用

SN Computer Science 2025年第2期6卷 1-10页

作者： Biswas, Preesat Mishra, Aishwarya Dixit, Rinku Sharma Dwivedi, Abhishek Choudhary, Shailee Lohmor Tiwari, Shweta Chakravarthi, M. Ayyappa Electronics & Telecommunications Government Engineering College C. G Jagdalpur India Department of Computer Science & Engineering IES College of Technology M.P Bhopal India Department of Artificial Intelligence and Machine Learning New Delhi Institute of Management Delhi India Department of Data Science and Engineering School of AIML IoT & IS CCE DS and Computer Applications Manipal University Jaipur Jaipur Rajasthan India Department of Computer Science and Engineering Gyan Ganga Institute of Technology and Sciences M.P Jabalpur India Department of CSE-Data Science KKR and KSR Institute of Technology and Sciences Guntur India

Unattended Wireless Sensor Networks (UWSNs) operate without human supervision and have limited resources. In a conventional WSN with a fixed sink for data collection, nodes one hop away from the sink consume more energy, causing a hotspot issue. This leads to network fragmentation and reduced sensing efficiency. To address this, a mobile sink is proposed. This study details the development and implementation of Secure MRL, focusing on legitimate message communication to the mobile sink via convex nodes. By using these convex nodes as data collection points, the mobile sink avoids traversing the entire network. We employ an enhanced system to generate keys and authenticate messages, assessing its resilience against various attacks, including sleep deprivation, snooze, network substitution, and modification. Findings indicate that Secure MRL maintains consistent performance across different node counts and significantly reduces energy consumption by 84%, improving the speed of attack detection. This improvement is achieved by monitoring the digital signature and residual energy of nodes. The proposed SVM-based network training establishes a residual energy cut-off, while convex nodes mitigate synchronization issues among other sensor nodes in Secure MRL. Additionally, convex nodes manage the availability checks for the mobile sink. The proposed approach demonstrates a 92% improvement in packet delivery ratio (PDR) and an 89% reduction in end-to-end delay, highlighting its efficacy in enhancing network performance. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Duty-cycled UWSN MRL Sec-MRL SEC-TMP SVM UWSN

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：