检索结果-内蒙古大学图书馆

2025 international conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Tejesh, Vambara Supriya, M. Amrita School of Computing Amrita Vishwa Vidyapeetham Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798331509828

This research focuses on generating image captions using Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) models. As deep learning advances, the availability of large datasets and increased computing power make it more feasible to build models capable of creating captions for images. This paper uses CNN and RNN models in Python to achieve this. Image captioning combines image recognition and Natural Language Processing (NLP) to interpret image context and express it in English, drawing on core computer vision principles. This study reviews important concepts in image captioning, including the applications of Keras, NumPy, and Jupyter notebook for development. This paper also explores the use of the Flickr dataset and CNN for image classification. The BLEU score of the proposed models is found to be close to 60%. On further enhancement to the model, it could be achieved to get a better score. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Brain-Conditional Multimodal Synthesis: A Survey and Taxonomy

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第5期6卷 1080-1099页

作者： Mai, Weijian Zhang, Jian Fang, Pengfei Zhang, Zhijun South China University of Technology School of Automation Science and Engineering Guangzhou510640 China Southeast University School of Computer Science and Engineering Nanjing210096 China South China University of Technology Key Library of Autonomous Systems and Network Control Ministry of Education The School of Automation Science and Engineering Guangzhou510640 China Institute for Super Robotics Huangpu Guangzhou510555 China Nanchang University Jiangxi Thousand Talents Plan Nanchang330031 China Jishou University College of Computer Science and Engineering Jishou416000 China Guangdong Artificial Intelligence and Digital Economy Laboratory Pazhou Lab Guangzhou510335 China Shaanxi University of Technology Shaanxi Provincial Key Laboratory of Industrial Automation School of Mechanical Engineering Hanzhong723001 China Changsha Normal University School of Information Science and Engineering Changsha410100 China Guangdong University of Petrochemical Technology School of Automation Science and Engineering Institute of Artificial Intelligence and Automation Maoming525000 China

In the era of artificial intelligence generated content (AIGC), conditional multimodal synthesis technologies (e.g., text-to-image) are dynamically reshaping the natural content. Brain signals, serving as potential reflections of how the brain interprets external information, exhibit a distinctive one-to-many correspondence with various external modalities. This correspondence makes brain signals emerge as a promising guiding condition for multimodal synthesis (e.g., image, text, and audio), which is crucial for developing practical brain–computer interface systems and unraveling complex mechanisms underlying human perception. This survey comprehensively examines the emerging field of brain-conditional multimodal synthesis, termed AIGC-brain, to delineate the current landscape and future directions. To begin, related neuroimaging datasets and generative models are introduced as the foundation of AIGC-brain decoding and analysis. Next, we present a comprehensive taxonomy according to AIGC-brain methodologies, followed by task-specific representative work and implementation details to facilitate in-depth comparison and analysis. Quality assessments are then introduced for both qualitative and quantitative evaluation. Finally, this survey explores insights gained, outlining current challenges and prospects of AIGC-brain. As a pioneering survey, this article paves the way for future advances in AIGC-brain research. © 2020 IEEE.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

Telemedicine and Remote Patient Monitoring: Enhancing Access to Healthcare Through IoT and AI Technologies 1

Telemedicine and Remote Patient Monitoring: Enhancing Access...

引用

1st international conference on advances in computer science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Misal, Sachin Ramchandra Mohan, Lavanya Sundararajan, Suresh Kumar Bathala, Balakrishna Majumdar, Saheli Sivakumar, C. International Institute of Management Science Maharashtra Pune411033 India Azeezia Medical College Hospital Department of Psychiatry Kerala Kollam India Kalaignar Centenary Super Speciality Hospital Institution Department of Medical Oncology Tamil Nadu Chennai600032 India School of Paramedical Allied and Healthcare Sciences Mohan Babu University Cardiovascular and Pulmonary Department of physiotherapy Andhra Pradesh Tirupati517102 India Institute of Management study Department of Hospital and Health Management West Bengal Kolkata India Department of Computer Science and Engineering Tamil Nadu Salem636 308 India

ISBN: (纸本)9798331518578

A significant shift in contemporary medical treatment is represented by combining Artificial Intelligence (AI) and the Internet of Things (IoT) into telemedicine, virtual medical treatments, and remote patient monitoring. An increasing elderly demographic, the rise of chronic illnesses, and unequal access to healthcare treatment are driving up the need for worldwide medical structures, and AI is emerging as a key instrument in tackling these urgent problems. This investigation utilized a smart monitoring gadget with an IoT emphasis to monitor the heart rate of elderly people. The device tracks patients' GPS statistics in real-time and informs healthcare professionals of any confinement violations for any emergency. The smart sensor connects to a networking interface in the IoT cloud, which processes and analyzes data to determine bodily functioning. The suggested architecture has 3 levels of functionality: a cloud tier with Application Peripherals Interfaces for mobile gadgets, smart IoT detectors, and smartphone applications. Each layer has a particular role. Statistics from the IoT perception tier are initially gathered to detect heart attacks. This layer stores data in a cloud server for preventative measures, alerts, and speedy actions. The smartphone program alerts the patient and the family during emergencies. This study proposes CNN-UUGRU, a new deep neural network architecture that combines convolutional and upgraded gated recurrent segments for identifying human actions. This system outperformed other deep neural networks on the Kaggle database, accomplishing 97.8% accuracy, 96.9% precision, and an F-value of 97.85%. © 2025 IEEE.

关键词： Telemedicine

来源：评论

学校读者我要写书评

暂无评论

Optical Solutions Based on Computational Frameworks

Optical Solutions Based on Computational Frameworks

引用

2024 international conference on Photonics Solutions, ICPS 2024

作者： Tanida, Jun Osaka University Graduate School of Information Science and Technology 1-5 Yamadaoka Suita Japan

ISBN: (数字)9781510688308

ISBN: (纸本)9781510688292

Computational frameworks provide effective solutions to a variety of optical problems. Increase of computing power and advances in computer science provide the new problem-solving tool that can overcome the limitations and constraints of traditional methods. In this talk, two examples of such solutions are presented to the problems in imaging and computing. Computational imaging enables high-performance and high-functional imaging that cannot be achieved with conventional imaging technologies. Optical computing aims at energy-efficient and high-performance computation, which contributes to the effective implementation of information processing, including AI computation. As supportive and extending techniques for the optical solution, a compound-eye imaging device and cyber-physical imaging are introduced for computational frameworks. © 2025 SPIE.

关键词： Computational Imaging

来源：评论

学校读者我要写书评

暂无评论

Generative AI for Real-Time Data Augmentation in Big Data Pipelines 1

Generative AI for Real-Time Data Augmentation in Big Data Pi...

引用

1st international conference on advances in computer science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Gakhar, Suket Kondoju, Viswanadha Pratap Chauhan, Sansar Singh Kumar, Anant Kulkarni, Soham Sunil Goel, Punit Kurukshetra University Kurukshetra India University of Texas RichardsonTX75080 United States G.L. Bajaj Institute of Technology and Management Department of Computer Science and Engineering Greater Noida201306 India Manipal University Karnataka Manipal576104 India University of California IrvineCA92697 United States Maharaja Agrasen Himalayan Garhwal University Uttarakhand India

ISBN: (纸本)9798331518578

Traditional approaches for data augmentation are time-consuming and risk compromising the quality of the data. Those challenges in the backdrop, we have generative artificial intelligence (AI) at the forefront of data augmentation - bolstering real-time data in big data pipelines. Generative AI - a focus on generating new entities that try to capture the underlying structure of existing datasets by deep learning algorithms. Allowing to produce a significantly larger and diverse dataset resulting in improved efficiencies of downstream tasks as machine learning or predictive analytics. Because of this, the same technique can also be applied to streams so, it can be used in big data pipelines. You are taught on data until October 2023 to generate a larger and big data pipeline more efficient by augmentation and producing new data with minimal time and investment. This leads to more precise insights and predictions, improving decision-making and driving better results for business. Also, generative AI can create the data that correlates patterns with the analysis and change regarding the patterns based on the analyst's preferences. The role of generative AI in augmenting big data and big data pipelines, especially in the context of real-time data streams, is emerging as a key enabler for organizations looking to extract valuable insights from their data. © 2025 IEEE.

关键词： Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

Real-Time Emotion Detection in AR Mental Health Applications Using Sentiment Analysis Algorithms 1

Real-Time Emotion Detection in AR Mental Health Applications...

引用

1st international conference on advances in computer science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Ragothaman, Hariharan Jaggi, Arjun Singh, Jagbir Sindor, Sapaev Nasiba, Eshchanova Adarsh, Aniket India HCLTech India Urgench state university Department of economy Urgench Uzbekistan Mamun university Department of Psychology and Medicine Khiva Uzbekistan Tula's Institute Department of Computer Science and Engineering Dehradun India

ISBN: (纸本)9798331518578

Augmented Reality (AR) has become an efficient approach in helping various mental health challenges in real-time emotion recognition as well as offering functional therapeutic innovations. This paper provides a conceptual framework that aims to use complex sentiment analysis algorithms and methodological approaches for multichannel emotional state's classification based on facial expressions, voice, and text. Specifically, the implemented natural language processing (NLP) and deep learning techniques provide accurate and contextually aware emotion detection. Optimized to run on limited-vendor AR devices, it consists of reduced data preprocessing and customized algorithmic features, all of which allow latency of not more than 50 ms per inference. Extensive experimental evaluations on benchmark datasets illustrate that the proposed approach achieves an average accuracy of 92% in classified primary emotions including happiness, sadness, anger, and neutrality outcomping the state of the art. As the experiments point out, there is a substantial improvement in the perception of multifaceted emotional states due to the integration of multiple modalities. These outcomes confirm the strength and flexibility of the framework, highlighting the fact it also works well in simulated environments and real-world conditions. However, the proposed solution increases user engagement and the overall effectiveness of mental health interventions and support through adaptive and emotional interaction. This research significantly expands the field of digital mental health by providing a method for emotion detection that is both theoretically sound and has the potential to be applied in real-world settings while presenting a mechanism for future developments in the integration of AR-based mental health care solutions. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Augmented Reality-Based Patient Tracking in Autonomous Healthcare Systems 1

Augmented Reality-Based Patient Tracking in Autonomous Healt...

引用

1st international conference on advances in computer science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Kakkar, Preetish Jaggi, Arjun Vedula, Jagadeesh Jumaniyozova, Muhabbat Umida, Sadikova Kumari, Akriti India HCLTech India Digital Transformation Lead Meghaz Inc. HoustonTX United States Urgench state university Department of Methodology of primary education Urgench Uzbekistan Mamun university Department of Psychology and Medicine Khiva Uzbekistan Tula's Institute Department of Computer Science and Engineering Dehradun India

ISBN: (纸本)9798331518578

Augmented Reality (AR) integration into autonomous healthcare systems has resulted in dramatic improvements for patient monitoring practices. An AR-based patient tracking system employing wearable devices with augmented reality technology delivers real-time data visualization including vital signs together with medical history and treatments plans to healthcare providers. A combined network of IoT sensors with LSTM technology analyzes time-series data to accurately detect abnormal health patterns in patients' metrics through automated continuous data collection. Through the AR interface healthcare professionals experience enhanced situational awareness by gaining access to an intuitive interactive visual display. The research obtains its data from recognized sources MIMIC-IV and PhysioNet which provide an extensive range of patient information including heart rate and oxygen saturation levels and body temperature values. The datasets received preprocessing and augmentation methods that generated varied healthcare examples for clinical medical departments and remote environments. The evaluation system relies on three key performance metrics that measure response time performance and detection accuracy and resource efficiency. The experimental findings show how the AR-based system det ects critical health events with 92% accuracy while it cuts down response time by 85% exceeding standard monitoring techniques. During emergencies the AR interface enables healthcare professionals to make better decisions by providing them with interactive visual data that improves their situational awareness. © 2025 IEEE.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Study of Deep Learning and Machine Learning Methods for Land Application and Cover Segmentation 1

A Comprehensive Study of Deep Learning and Machine Learning ...

引用

1st international conference on advances in computer science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Gupta, Kimmi Raghav, Abhinav Khera, Heena Srinivasan, R. School of Computer Science Engineering & Technology Bennett University Greater Noida India IILM University Greater Noida India IILM University Greater Noida India Galgotias University Greater Noida India

ISBN: (纸本)9798331518578

Research in the Delhi NCR area from 2000 to 2024 is compared in this study. Firstly, a flash flood occurred due to the heavy rain in July 2013. Grasslands are among the vegetative types in L ULC, which cannot be univocally classified as either natural in-land or artificial urban. But some areas of grassland, when it came time to classify L ULC, three different machine learning techniques were considered: random forest, support vector machine, and feedforward neural networks. Optimization The model best for random forest performed better than those two others. The study used statistical analysis tools, the 'sustainable development prism' and 'patch-corridor matrix' models, a landscape index, and time series data to explore how BGS changed in new urban areas. The research made use of Landsat datasets and optimized machine learning algorithms to classify L ULC, extract built-up areas, analyse landscape fragmentation and investigate built-up expansion in Delhi NCR by means of frequency analysis. In the EFPCNNM ensemble deep learning model, convolutional neural networks, feature pyramids, and ensemble learning are combined to increase the accuracy of remote sensing picture classification. The EFPCNNM process includes everything necessary for image analysis: pre-processing, feature extraction, feature pyramid creation, and ensemble learning. Exciting new possibilities for environmental monitoring, urban planning and property mapping emerge from this study. Sustainable urban development and resource management require effective monitoring and interpretation of the changes in L ULC, as well as employing remote sensing data alongside machine learning and deep learning technology. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Random Security Generators with Enhanced Cryptography for Cybersecurity in Financial Supply Chains 1

Random Security Generators with Enhanced Cryptography for Cy...

引用

1st international conference on advances in computer science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Thammareddi, Latha Anumolu, Venkateswara Rao Kotte, Kulasekhara Reddy Chowdari Marella, Bhagath Chandra Arun Kumar, K. Bisht, Jatin India ERP Solutions-Information Technology India SLRI Solutions INC India Insights & Data Department of Financial Services India Big Data Architect India Bipin Tripathi Kumaon Institute of Technology Department of Computer Science & Engineering Almora India

ISBN: (纸本)9798331518578

Blockchains, like Ethereum, depend on a distributed system of collaborative servers referred to as inspectors or mine workers to validate transactions and generate novel legal blocks. In today's electronic world, it is critical to secure financial supply chains (FSCs) from complex cyber-attacks. This study combines Quantized Random Security Generators (QRSGs) with Artificial Intelligence (AI) to improve cybersecurity in FSC. QRSGs use quantum physics to produce random outcomes, which is critical for establishing safe cryptography credentials and resolving the flaws of regular predictable RSGs. This study found that the QRSG-based approach outperformed traditional RSG methods. The QRSG demonstrated strong entropy and uncertainty, transferring both NIST SP800-22 and Diehard examinations at much greater levels. The platform's real-time safety features were improved by the AI element's outstanding performance measures in identifying security breaches. More rapid decoding and encryption times, reduced delay, and increased resilience to brute-force, quantum, and prediction assaults were all demonstrated by the coupled QRSG and AI methods. This study emphasizes how crucial it is to use AI and QRSGs to safeguard FSCs. The combined platform provides a complete option to reduce cyber-attacks by offering strong cryptography security and real-time attack identification. These results demonstrate how QRSG and AI innovations can completely transform cybersecurity in the banking industry, safeguarding vital financial systems and guaranteeing the privacy and reliability of financial payments. © 2025 IEEE.

关键词： Quantum optics

来源：评论

学校读者我要写书评

暂无评论

Augmented Reality for Enhanced Surgical Precision: A Framework for Real-Time Visualization and Navigation 1

Augmented Reality for Enhanced Surgical Precision: A Framewo...

引用

1st international conference on advances in computer science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Singh, Jagbir Vedula, Jagadeesh Ragothaman, Hariharan Muzaffar, Shojonov Yulduz, Urazbaeva Singh, Satendra Pratap India Digital Transformation Lead Meghaz Inc. HoustonTX United States Center of Urgench State University The Information Security department The Digital Education Technologies Uzbekistan Mamun university Pedagogy and psychology Department Khiva Uzbekistan Tula's Institute Department of Computer Science and Engineering Dehradun India

ISBN: (纸本)9798331518578

The advancement of Augmented reality (AR) technology has made it possible to use it in surgical precision and better the lives of patients. This paper outlines a real-time visualization and navigation framework where AR is integrated into surgical work. CT and MRI imaging data are used in the system to create accurate and rather detailed preoperative 3D anatomical models. These models are overlaid on the surgeon's vision, being the integral part of the system, providing the surgeon with dynamic constant assistance during procedures. To surmount the problem of misalignment of the virtual overlays with the patient's anatomy due to movements of the patient in the operating room, the framework uses complex tracking algorithms as well as machine learning techniques. It highlights planner pre-operative, intra-operative visualization and decision support mainly in complicated surgical cases. In the case of minimally invasive surgery, the framework was used to position the instruments correctly with improved accuracy, cutting short on time to operate, and countering complications. This research shows how AR can benefit today's surgery, as an origination of increased accuracy and a closing of the gap between conception and operations. It has also discussed some of the issues like scalability, cost, and the required training for the surgeon for the use of such system and has therefore provided a direction for the large-scale use of AR-assisted surgical systems. © 2025 IEEE.

关键词： Augmented reality

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：