检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Xin Li Feng Xu Feifei Tao Yao Tong Xin Lyu Jianyi Zhong André Kaup College of Computer Science and Software Engineering Hohai University Nanjing China Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China School of Computer Engineering Jiangsu Ocean University Lianyungang China School of Artificial Intelligence and Information Technology Nanjing University of Chinese Medicine Nanjing China Chair of Multimedia Communications and Signal Processing Friedrich-Alexander University Erlangen-Nuremberg Erlangen Germany

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Semantic segmentation of remote sensing images (RSIs) is essential for applications such as environmental monitoring, urban planning, and disaster management. Convolutional Neural Networks (CNNs) and their variants struggle to capture comprehensive spectral context for learning discriminative representations. In this paper, we propose a Spectrum-Enhanced Network (SPENet) that leverages the Frequency Transformer Block (FTB) to capture rich spectral context. FTB integrates Spectrum-Enhanced Attention (SEA) with Multi-Head Frequency Self-Attention (MH-FSA), incorporating more informative contextual cues. Specifically, SEA aggregates spectral statistics through covariance matrix normalization before applying channel-wise attention. By projecting feature maps onto the frequency domain, MH-FSA provides the network with a broader context, extending beyond the low-frequency focus of standard self-attention mechanisms. Extensive experiments on the ISPRS Potsdam and LoveDA datasets show that SPENet significantly outperforms state-of-the-art methods. Besides, the proposed SEA module notably rises average F1-score/overall accuracy/mean insert over union wiht more than 2.5/2.6%/2.3%, as demonstrated by ablation study.

关键词： Semantic segmentation Frequency-domain analysis Urban planning Semantics Speech enhancement Signal processing Transformers Sensors Remote sensing Standards

来源：评论

学校读者我要写书评

暂无评论

Decision Making and Recognition of String Characters using NN-Fuzzy Implication System

Decision Making and Recognition of String Characters using N...

引用

3rd International Conference on Machine Learning and data engineering, ICMLDE 2024

作者： Henge, Santosh Kumar Bhagat, Avinash Mandal, Sanjeev Kumar Viraati, Nikhil Reddy Singh, Ravleen Kedhar, K. Rushi Department of Computer Science and Engineering School of Computer Science and Artificial Intelligence SR University Warangal506371 India School of Computer Applications Lovely Professional University Punjab Phagwara India Bangalore India Department of Data Insights Crisp Shared Services 7160 Columbia Gateway Dr Columbia United States Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation AP Vaddewaram India BE-CSE RV Institute of Technology and Management Bengaluru India

This research proposes the neural network (NN)-fuzzy logic control (FLC)-based methodology, which is designed with two stages of execution. Stage-1 is composed with the NN approach;it takes the input from the scanned image, the input from the classified clustered group, processes it with hidden layers, and generates the final output, which is input to the FLC in stage 2. The input of stage 2 converts the input into fuzzified data (0s and 1s) and trains the FLC system with fuzzified set values. The trained data has been simulated for further stages in the FLC-based decision-making approach and integrated to identify the character patterns based on the trained dataset. FLC-based planting and normalization techniques are integrated for re-training the data. The dataset has been framed with more than 6200 handwritten image characters, which were written by 235 writers. It aligned with the pre-processing, classification, and filtering stages and achieved a 99.8% recognition rate. © 2025 The Author(s).

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Smart Personal Protective Equipment in Ambulance Services with IoT Integration for Safety

Smart Personal Protective Equipment in Ambulance Services wi...

引用

International Conference on Smart Technologies For Smart Nation (SmartTechCon)

作者： R. Senkamalavalli Chethan Chandra S Basavaraddi L. M. Merlin Livingston N. Latha Elangovan Guruva Reddy Department of Computer Science and Engineering Kammavari Sangham Institute of Technology Bangalore Karnataka India Department of Computer Science and Engineering Kalpataru Institute of Technology Tiptur Tumkur Karnataka India Department of Electronics and Communication Engineering Jeppiaar Institute of Technology Chennai Tamil Nadu India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India Department of Artificial Intelligence and Data Science Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh India

Internet of Things (IoT) technology has improved ambulance safety and efficiency. In ambulance services, Smart PPE (Personal Protective Equipment) improves patient and healthcare worker safety via IoT connectivity. In crises, ambulances are vital. However, healthcare professionals risk contagious infections and physical damage. Though vital, traditional PPE lacks real-time monitoring and communication, leaving healthcare workers exposed. These issues are addressed with Smart PPE using IoT. This novel invention adds sensors and communication devices to paramedic and EMT PPE. These sensors measure air quality, temperature, and the wearer's heart and body temperature. A centralized system can remotely monitor healthcare personnel's safety and well-being using real-time data. Smart PPE has two-way communicators and emergency alert systems. Emergency coordination is improved by ambulance crews and dispatch centers communicating seamlessly. The Smart PPE can automatically inform the team and dispatch in urgent situations, increasing response times and patient outcomes. IoT enables predictive maintenance and data analytics. Trends and dangers may be identified from gathered data, allowing proactive risk mitigation. Smart PPE can measure use and remind users to maintain and replace equipment, assuring dependability when required most. By continually monitoring conditions, allowing real-time communication, and enabling data-driven decision-making, this unique technology improves ambulance services and reduces dangers to devoted personnel.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cognitive Defense Cyber Attack Prediction and Security Design in Machine Learning Model

Cognitive Defense Cyber Attack Prediction and Security Desig...

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： P.T. Devadarshini B Chandrashekar Sumit Pundir Mohit Tiwari Ravikiran Madala E. Indhuma Department of Artificial Intelligence and Data Science Easwari Engineering College Chennai TamilNadu India Department Of Computer Science and Engineering St. Martin's Engineering College Kompalli Secunderabad Telangana Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun Uttrakhand India Department of Computer Science and Engineering Bharati Vidyapeeth's College of Engineering Delhi Network and Data Center Engineer Ph.D Information Technology University of Cumberlands Durham North Carolina US Department of Computer Science and Engineering St.Martln's Engineering College Secunderabad Telangana India

Companies of all sizes in today's linked digital world are susceptible to cyber dangers. In this study, we provide a novel approach to cyber defence that integrates machine learning with cognitive defensive techniques to identify and prevent cyber attacks in their tracks. We built three ML models that use cognitive defensive strategies and other cutting-edge security measures like encryption and intrusion detection. A 95% accuracy rate was reached by our models, which is far greater than where things stand right now models. Our work has the potential to have a huge effect since the models we've developed may one day help businesses take a more preventative stance against cyber threats. Our findings may potentially be used to fields outside than cyber security. Overall, our study shows that machine learning and cognitive defense are useful for foreseeing and stopping cyber threats, and points the way toward fruitful future study in this area.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Correction: MSegNet: A Multi-View Coupled Cross-Modal Attention Model for Enhanced MRI Brain Tumor Segmentation

引用

International Journal of Computational intelligence Systems 2025年第1期18卷 1-2页

作者： Wang, Yu Xu, Juan Guan, Yucheng Ahmad, Faizan Mahmood, Tariq Rehman, Amjad Shandong Research Institute of Industrial Technology Shandong China Department of Endocrinology Taian City Central Hospital Taian China College of Engineering Northeastern University San Jose USA Qiqihar Medical University Heilongjiang Province China Artificial Intelligence and Data Analytics (AIDA) Lab CCIS Prince Sultan University Riyadh Saudi Arabia Faculty of Information Sciences University of Education Vehari Campus Vehari Pakistan

来源：评论

学校读者我要写书评

暂无评论

Rkl: Reward-Kullback-Leibler Divergence Method for Improving Machine Learning Model Prediction Performance

SSRN

引用

SSRN 2023年

作者： Zhu, Jian Cui, Yasen Zhou, Wei Zang, Huaijuan Zhang, Haiyan Ren, Yongsheng Xu, Jiajia Zhan, Shu Ma, Wenhui School of Computer and Information Engineering Hefei University of Technology Hefei230601 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230601 China Faculty of Metallurgical and Energy Engineering Kunming University of Science and Technology Kunming650093 China The National Engineering Research Center of Vacuum Metallurgy Kunming University of Science and Technology Kunming650093 China Lingyang Industrial Internet CO. LTD Hefei China

In recent years, the fields of physics and chemistry have progressively adopted machine-learning methods. The crystal structure of materials can be conveniently represented as nodes and edges, making them amenable to graph-based representations. Graph neural networks have also found wide application in replacing traditional Density Functional Theory (DFT) calculations for predicting material properties. Classical Graph Convolutional Neural Networks such as CGCNN have demonstrated extensive applicability in predicting material properties, but their predictive accuracy often heavily relies on the effective extraction of crystal features. These models are typically limited to predicting properties associated with the extracted features, with limited performance on other properties. This paper introduces the RKL method, inspired by Reinforcement Learning from Human Feedback (RLHF), to enhance the accuracy of various graph neural network models in material property predictions. RKL diverges from the traditional reliance on crystal feature extraction. Instead, it combines the KL divergence with a reward function to create an optimizable objective function for fine-tuning model parameters. Experimental results demonstrate that the proposed RKL method significantly improves predictive accuracy. We validate the effectiveness of this method on three models: CGCNN, OGCNN, and GATGNN, and finally confirm its generalization capabilities on the ALIGNN model. © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Automated and Decentralized Cloud based water level audit system with loT

Automated and Decentralized Cloud based water level audit sy...

引用

International Conference on science technology engineering and Management (ICONSTEM)

作者： S. Selvakumar C. Geetha R. Vidhya Muthulakshmi Sreevardhan Cheerla Ashok Kumar Sudhir Joshi Department of Computer Science and Engineering AarupadiVeedu Institute of Technology Vinayaka Mission Research Foundation Paiyanur Tamil Nadu India Department of Computer Science and Engineering R. M. K. Engineering College Kavaraipettai Tamil Nadu India Department of Artificial Intelligence and Data Science Panimalar Engineering College Poonamallee Chennai Tamil Nadu Deportmem of Electronics and Communications Engineering KoneruLakshmaiah Education Foundation Vaddeswaram Andhra Pradesh India Department of Computer Science Banasthali Vidyapith Rajasthan India Department of Mechanical Engineering Graphic Era Deemed to be University Dehradun Uttarakhand India

ISBN: (数字)9798350365092

ISBN: (纸本)9798350365108

Water bodies play a fundamental role in the development of society. The construction of dams for water storage has been carried out since ancient civilizations and, along with the development of modern society, new forms of construction have emerged. Over time, these constructions led to improvements for the population which, in turn, took the price of changing the environment and its effects. On this paper a water level audit system was developed with hardware for sensing and sending the data through the cellular network to a server for storage and later displaying it to the user so that he doesn't need to go back to the essay location, being useful for research on the local hydraulic system.

关键词： Ultrasonic imaging Ultrasonic variables measurement Energy measurement Hardware Battery charge measurement Software Pressure measurement

来源：评论

学校读者我要写书评

暂无评论

FDM: NutriGuide - A Cross-Platform Flutter Application for Managing and Educating on Nutritional Deficiencies

FDM: NutriGuide - A Cross-Platform Flutter Application for M...

引用

Intelligent Cyber Physical Systems and Internet of Things (ICoICI), International Conference on

作者： Vidhya K T.M Thiyagu Antony Taurshia B. Nagarajan Jenefa A Joshua Flower Jebas I School. of CST Karunya Institute of Tech. and Sci. Coimbatore India Dept. of CSE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Sci. and Tech. Dept. of Artificial Intelligence and Data Science KPR Institute of Engineering and Technology Coimbatore India

ISBN: (数字)9798331540661

ISBN: (纸本)9798331540678

In today's fast-paced world, many individuals strug-gle to maintain a balanced diet, leading to various nutritional de-ficiencies. Effective management and education on these deficien-cies are crucial for improving public health. Traditional methods of addressing nutritional deficiencies often lack personalization and user engagement. The NutriGuide application, developed using the Flutter framework, aims to revolutionize nutritional management by providing a user-centric, cross-platform solution. Utilizing a comprehensive database of nutrients and symptoms, the application offers personalized dietary recommendations based on user inputs. The dataset includes detailed information on common deficiencies, symptoms, and nutrient-rich foods. Experimental results indicate high user satisfaction, with an average satisfaction score of 4.5 out of 5, and significant im-provements in nutritional intake, such as a 28.6 % increase in Vitamin A intake and a 50% increase in Vitamin D intake. In conclusion, NutriGuide presents an innovative approach to nutritional health, combining modern technology with evidence-based recommendations to empower users in managing their dietary needs.

关键词： databases Education Nutrients Electronic healthcare Internet of Things Public healthcare

来源：评论

学校读者我要写书评

暂无评论

GANs-guided Conditional Diffusion Model for Synthesizing Contrast-enhanced Computed Tomography Images

GANs-guided Conditional Diffusion Model for Synthesizing Con...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Yulin Yang Jing Liu Qingqing Chen Yinhao Li Xian-Hua Han Hongjie Hu Lanfen Lin Yen-Wei Chen Gradate School of Information Science and Engineering Ritsumeikan University Shiga Japan Research Center for Healthcare Data Science Zhejiang Lab. Hangzhou China Department of Radiology of Sir Run Run Shaw Hospital Zhejiang University School of Medicine Hangzhou China College of Information Science and Engineering Ritsumeikan University Shiga Japan Artificial Intelligence Research Center Yamaguchi University Yamaguchi Japan College of Computer Science and Technology Zhejiang University Hangzhou China

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

In contrast to non-contrast computed tomography (NC-CT) scans, contrast-enhanced (CE) CT scans can highlight discrepancies between abnormal and normal areas, commonly used in clinical diagnosis of focal liver lesions. However, the use of contrast agents in CE-CT scans imposes significant physical and economic burdens on patients in clinical practice. Recently, Generative Adversarial Networks (GANs)-based synthesis models offer an alternative approach that obtains CE-CT images from NC-CT images. However, poor coverage and mode collapse greatly limit their performance. Diffusion models (DMs)-based methods have demonstrated superior performance in natural image synthesis tasks. Nevertheless, our experiment shows that CE-CT images synthesized from DMs-based method exhibit higher overall quality but lower local quality. The quality of local areas, particularly those related to lesion areas, is crucial in medical image synthesis tasks. Hence, we propose a GANs-guided conditional diffusion model (GANs-CDM), combining the GANs and conditional diffusion model (CDM), to generate CECT images. In the proposed GANs-CDM, the GANs is to generate a preliminary CE-CT image, serving as conditional input for guiding the subsequent CDM to produce refined CE-CT images. Qualitative and quantitative evaluation on arterial and portal venous phase synthesis tasks demonstrates that our proposed GANs-CDM can significantly improve both the local and global quality of synthetic images.

关键词： Economics Image synthesis Computed tomography Biological system modeling Liver Diffusion models Generative adversarial networks Lesions Portals Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Predicting of Uncertainty Facial Expressions in Children with Autism Spectrum Disorder Based on an Improved Fuzzy Convolutional Neural Network Model

SSRN

引用

SSRN 2024年

作者： Abd-Alhalem, Samia M. Ali, Hesham A. El-Shafai, Walid Soliman, Naglaa F. Algarni, Abeer D. El-Samie, Fathi E. Takieldeen, Ali E. Faculty of Artificial Intelligence Delta University for Science and Technology Gamasa35712 Egypt Computers and Control Systems Engineering Department Faculty of Engineering Mansoura University Mansoura35516 Egypt Security Engineering Lab Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Zagazig University Egypt Menoufia University Egypt

Facial expression recognition plays a pivotal role in comprehending emotions and social interactions, particularly in individuals grappling with autism spectrum disorder (ASD), who often encounter challenges in non-verbal communication. For some with ASD, even subtle shifts in their facial expressions can prove elusive, rendering it arduous to categorize their emotional states accurately. Consequently, the analysis and processing of facial expression data hold the potential to facilitate early autism diagnosis, thereby enabling timely therapeutic interventions and alleviating the economic and psychological burdens experienced by patients. In this study, we introduce an enhanced approach that leverages a fuzzy convolutional neural network (CNN) and an Improved Binary Genetic Algorithm (IBGA) for autism diagnosis based on facial expression data. Our model confronts the intricate task of recognizing facial images by selecting salient features employing the IBGA method. Moreover, it employs fuzzy weights to ascertain the probability of similarity within the classifier layer. Our proposed model has yielded impressive outcomes, boasting an average accuracy of 0.9405 for ASD detection and 0.9365 for the recognition of six distinct facial expressions. These results hold profound implications for the enhancement of emotion recognition systems and the refinement of interventions aimed at bolstering social interactions for individuals grappling with ASD. © 2024, The Authors. All rights reserved.

关键词： Emotion Recognition

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：