检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICml 2024

作者： Shi, Liangliang Fan, Jack Yan, Junchi School of Artificial Intelligence Department of Computer Science and Engineering MoE Lab of AI Shanghai Jiao Tong University Shanghai China Department of Computer Science University of North Carolina Chapel Hill United States

We propose to understand Contrastive Language-Image Pretraining model (CLIP) from the Optimal Transport (OT) perspective. Specifically, we show that training of CLIP is an embodiment of inverse OT and the adopted two InfoNCE losses in CLIP correspond to a special case of bilevel optimization of a modified entropic OT. We then generalize the original CLIP loss to an OT-based loss family using variants of Regularized OT (e.g. Fused Gromov OT, unbalanced OT, etc.), and show their superior performance on public datasets for downstream tasks in both image and text domain. We also rethink the inference stage of CLIP by using the tool of OT, and propose to adopt the fused Gromov OT for (zero-shot) classification, in which the prediction is based on the graph representation whereby images and texts are nodes for graph matching. By our new technique, we show how to generalize zero-shot classification to other more flexible zero-shot tasks with competitive performance: long-tailed classification and selective classification. The former assumes the known prior distribution of labels, while in the latter case, only a subset of samples are asked to predict, yet with the need of high prediction confidence. The code is available at https://***/fan23j/ICml2024-OT-CLIP. Copyright 2024 by the author(s)

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Enhanced Brain Tumor Prediction via Entropy-Coded BPSO in CIELAB Color Space

引用

computers, Materials & Continua 2023年第11期77卷 2031-2047页

作者： Mudassir Khalil Muhammad Imran Sharif Ahmed Naeem Muhammad Umar Chaudhry Hafiz Tayyab Rauf Adham E.Ragab Department of Computer Engineering Bahauddin Zakariya UniversityMultan60000Pakistan Department of Computer Science Kansas State UniversityManhattanKS66506USA Department of Computer Science University of Management and TechnologyLahore54000Pakistan Centre for Smart Systems AI and CybersecurityStaffordshire UniversityStoke-on-TrentST42DEUK Industrial Engineering Department Collage of EngineeringKing Saud UniversityPO Box 800Riyadh11421Saudi Arabia

Early detection of brain tumors is critical for effective treatment *** tumors in their nascent stages can significantly enhance the chances of patient *** there are various types of brain tumors,each with unique characteristics and treatment protocols,tumors are often minuscule during their initial stages,making manual diagnosis challenging,time-consuming,and potentially *** techniques predominantly used in hospitals involve manual detection via MRI scans,which can be costly,error-prone,and *** automated system for detecting brain tumors could be pivotal in identifying the disease in its earliest *** research applies several data augmentation techniques to enhance the dataset for diagnosis,including rotations of 90 and 180 degrees and inverting along vertical and horizontal *** CIELAB color space is employed for tumor image selection and ROI *** deep learning models,such as DarkNet-53 and AlexNet,are applied to extract features from the fully connected layers,following the feature selection using entropy-coded Particle Swarm Optimization(PSO).The selected features are further processed through multiple SVM kernels for *** study furthers medical imaging with its automated approach to brain tumor detection,significantly minimizing the time and cost of a manual *** method heightens the possibilities of an earlier tumor identification,creating an avenue for more successful treatment planning and better overall patient outcomes.

关键词： Brain tumor deep learning feature extraction feature selection feature fusion transfer learning

来源：评论

学校读者我要写书评

暂无评论

Role of RPA to Seize Opportunities in 5G Edge Computing in Telecommunications

Role of RPA to Seize Opportunities in 5G Edge Computing in T...

引用

2024 International Conference on Advances in Computing Research on science engineering and Technology, ACROSET 2024

作者： Yendluri, Dileep Kumar Tatikonda, Reshmi Tatikonda, Ramya Ponnala, Jainath Kempanna, M. Bhuvanesh, A. University of the Cumberlands Department of Computer Science Williamsburg United States University of the Central Missouri Department of Computer Information Systems Warrensburg United States University of the Cumberlands Department of Information Technology Williamsburg United States Jawaharlal Technological University Department of Electronics and Communication Engineering Hyderabad India Bangalore Institute of Technology Department of Ai and Ml Bangalore India Psn College of Engineering and Technology Department of Electrical and Electronics Engineering Tirunelveli India

ISBN: (纸本)9798350388800

This paper explores the role of Robotic Process Automation (RPA) in leveraging opportunities presented by 5G edge computing in the telecommunications industry. Integrating RPA and 5G edge computing offers numerous benefits, including enhanced operational efficiency, real-time decision-making, improved service delivery, and cost savings. However, it also poses challenges such as complex integration, security concerns, and the need for effective change management. The paper comprehensively analyzes the potential benefits, challenges, and recommendations for implementing RPA in 5G edge computing. It explores use cases, future advancements, emerging technologies, and anticipated opportunities and challenges. The findings highlight the need for clear objectives, process optimization, collaboration between IT and business teams, and continuous monitoring to leverage RPA in 5G edge computing effectively. © 2024 IEEE.

关键词： Telecommunication industry

来源：评论

学校读者我要写书评

暂无评论

Cloud Based Automated Control System Workshops and Rooms for Controlling Parameters 1

Cloud Based Automated Control System Workshops and Rooms for...

引用

1st International Conference on Advances in computer science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Kumar, Dinesh Kuntal, Ravinder Singh Deep, Pragya Chamoli, Anup Shekhar Singh, Pinki Mandal, Rishabh SRM Institute of Science & Technology Department of Computer Science and Engineering UP Ghaziabad India Nitte Meenakshi Institute of Technology Department of Mathematics Karnataka Bangalore India IIMT College of Engineering Department of AI & DS Greater Noida India Uttaranchal School of Computing Sciences Uttaranchal University Dehradun248001 India Accurate College of Engineering & Management Department of Computer Science and Engineering Greator Noida India Tula's Institute Department of Computer Science and Engineering UK Dehradun India

ISBN: (纸本)9798331518578

Across all industries, cloud-based automated control systems have completely changed how operational and environmental parameters are tracked and controlled. With cloud-integrated systems for real-time data collection, processing, and control, this concept presents intelligent, remote-controlled workshops and control rooms. To guarantee accurate control of crucial variables like temperature, humidity, pressure, and equipment efficiency, these systems make use of IoT devices, ai techniques, and big data analytics. Through sophisticated data perspectives, the cloud-based strategy enables predictive maintenance, improves flexibility, and lowers operating expenses. Stakeholders may make prompt, data-driven choices from anywhere with remote access to control rooms. These seminars provide practical experience with cloud-controlled settings and function as training and development centres. The system's flexibility to meet a range of industrial demands is further enhanced by its compatibility with external tools and equipment. The design, deployment, and possible uses of cloud-based control systems are covered in this paper, with an emphasis on how they might promote operational excellence, energy efficiency, and smart manufacturing. © 2025 IEEE.

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

Real-Time Wrist Fracture Detection Using YOLO11

Real-Time Wrist Fracture Detection Using YOLO11

引用

Advanced Computing Technologies (ICoACT), International Conference on

作者： Nellore Sai Nikhil Vemula Kesavaaditya Gupta Sai Harshavardhan Srungavarapu Gouranga Mandal School of Computer Science and Engineering VIT - AP University Amaravati Andhra Pradesh India Department of Computer Science and Engineering (AI & ML) Dayananda Sagar University Bengaluru Karnataka India

ISBN: (数字)9798331509859

ISBN: (纸本)9798331509866

More than 1.71 billion individuals globally are impacted by bone diseases, especially conditions related to the musculoskeletal system, with fractures being a major worry. Prompt diagnosis is crucial, however, overlooked fractures are frequent in emergency situations, resulting in care delays. ai, particularly deep learning (DL), is becoming increasingly popular for aiding radiologists in identifying fractures in medical images. This review examines how deep learning is used in bone imaging. We employed the YOLO11 model, an algorithm for detecting objects in real-time that can forecast both bounding boxes and class probabilities at once, to detect bone fractures in real-time. We analyzed a variety of bone fracture images from different sources. Sophisticated training methods were used to improve the model's precision and resilience. The YOLO11 model showed great efficiency in detecting and categorizing fractures, providing substantial promise for live clinical use and enhancing diagnostic speed in medical settings.

关键词： Deep learning Wrist YOLO Training Reviews Computational modeling Bones Real-time systems Medical diagnostic imaging Resilience

来源：评论

学校读者我要写书评

暂无评论

Cloud-Native Hybrid Deep Learning Pipeline for Network Traffic Classification using Convolutional Recurrent Neural Network

Cloud-Native Hybrid Deep Learning Pipeline for Network Traff...

引用

2024 International Conference on Distributed Systems, computer Networks and Cybersecurity, ICDSCNC 2024

作者： Satish, E.G. Sudheer Kumar, Komuravelly Adnan, Myasar M. Krithika, M. Sundari, MandapatiVenkata Rama Nitte Meenakshi Institute of Technology Department of Cse Bengaluru India Sr University Department of Computer Science & Artificial Intelligence Warangal India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq Vels Institute of Science Technology and Advanced Studies Department of BCA/IT Pallavaram India Gokaraju Rangaraju Institute of Engineering and Technology Department of Ai&ml Bachupally Hyderabad India

ISBN: (纸本)9798350375442

Identifying encrypted traffic from emerging applications is important and challenging as traditional traffic classification approaches fail to achieve the desired level of accuracy. This necessitates the elaborate strategies to learn about the encrypted network flow. The research focuses on developing a cloud native hybrid Deep Learning (DL) pipeline for Network Traffic Classification (NTC). Initially, the ISCXVPN2016 dataset is considered that consists encrypted and non-encrypted traffic where the raw data is pre-processed with packet length normalization. The features are extracted applying Convolutional Neural Networks (CNNs) to define statistical flow features including inter-arrival time, packet size and flow duration. The data from network traffic is processed and classified using Convolutional Recurrent Neural Network (CRNN) with microservices executed in serverless containers. The hyper parameters in the DL models are then tuned using grid search and the random search algorithms. Experimental results showed that the proposed cloud native CRNN pipeline achieved accuracy of 98.67%, precision of 95.46%, and 94.32% when compared to the existing NTC models Stacked Autoencoders (SAE) based CNN (SAE-CNN) and Autoencoders based CNN (AE-CNN). © 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

ai Technology for the Practices of Societal Sustainable Development

AI Technology for the Practices of Societal Sustainable Deve...

引用

Computational Intelligence for Security, Communication and Sustainable Development (CISCSD), International Conference on

作者： N Santhosh Kumar CH Rajendra Prasad K Pavan Kumar P Department of Computer Science and Engineering ANURAG Engineering College Kodad Telengana India Department of Computer Science and Engineering (Cyber Security) Institute of Aeronautical Engineering Hyderabad India Department of Computer Science and Engineering (AI & ML) Vardhaman College of Engineering Hyderabad India

ISBN: (数字)9798350365405

ISBN: (纸本)9798350365412

The importance of incorporating ai technology into the engineering process is growing as technology gets more integrated. In this paper, we will explore artificial intelligence (ai) and its applications in sustainability engineering and management, specifically looking at how ai may improve efficiency, optimize the use of resources, and have a lasting impact. The primary focus is on addressing sustainable sustainability through the use of ai technology in civil, medical, agricultural, and mechanical engineering fields, among others. ai is a symbol of cutting-edge technology that has a significant influence on the growth of industries, the decrease of waste, and the state of the environment. The purpose of this study is to review the literature in search of important trends and insights, and then to investigate how artificial intelligence might be used to encourage sustainable practices in the workplace. From optimizing a flexible workforce to intelligently planning tasks and managing risks.

关键词： Industries Reviews Employment Symbols Market research Planning Security Artificial intelligence Sustainable development Mechanical engineering

来源：评论

学校读者我要写书评

暂无评论

Using 3D CNN for classification of Parkinson’s disease from resting-state fMRI data

引用

Journal of engineering and Applied science 2023年第1期70卷 89页

作者： Islam, Nair Ul Khanam, Ruqaiya Kumar, Ashok Department of Computer Science and Engineering Sharda University UP Greater Noida India Department of Electronics and Communication Engineering Center for AI in Medicine Imaging and Forensic Sharda University UP Greater Noida India Center for AI in Medicine Imaging and Forensic Sharda University UP Greater Noida India

Parkinson’s disease is a chronic and progressive movement disorder caused by the degeneration of dopamine-producing neurons in the substantia nigra of the brain. Currently, there is no specific diagnostic test available for Parkinson’s disease, and physicians rely on symptoms and medical history for diagnosis. In this study, a 3D-CNN deep learning model is proposed for detecting Parkinson’s disease using 4D-fMRI data. The data is preprocessed using independent component analysis (ICA) and dual regression processes through MELODIC in FSL, which results in a sequence of 30 3D spatial maps, each with its unique time course. A reference network, referred to as an atlas, is then applied using the fslcc command in FSL to map the 3D spatial maps. Fourteen resting-state networks (RSNs) are identified successfully, while the remaining maps are rejected as noise or artifacts. The detected RSNs or 3D spatial maps are fed into the 3D-CNN model, which is trained with a 10-fold cross-validation method. The proposed model has an accuracy of 86.07% on average. © 2023, Faculty of engineering, Cairo University.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Temporal Difference-Aware Graph Convolutional Reinforcement Learning for Multi-Intersection Traffic Signal Control

引用

IEEE Transactions on Intelligent Transportation Systems 2024年第1期25卷 327-337页

作者： Lin, Wei-Yu Song, Yun-Zhu Ruan, Bo-Kai Shuai, Hong-Han Shen, Chih-Ya Wang, Li-Chun Li, Yung-Hui National Yang Ming Chiao Tung University Department of Electrical and Computer Engineering Hsinchu30010 Taiwan National Tsing Hua University Department of Computer Science Hsinchu300 Taiwan Hon Hai Research Institute Ai Research Center New Taipei City11492 Taiwan

Traffic light control plays a crucial role in intelligent transportation systems. This paper introduces Temporal Difference-Aware Graph Convolutional Reinforcement Learning (TeDA-GCRL), a decentralized RL-based method for efficient multi-intersection traffic signal control. Specifically, we put forward a new graph architecture using each lane as a node for considering intersection relations. Additionally, we propose two new rewards by considering temporal information, namely Temporal-Aware Pressure on Incoming Lanes (TAPIL) and Temporal-Aware Action Consistency (TAAC), which enhance learning efficiency and time-interval sensitivity. Experimental results on five datasets show the superiority of TeDA-GCRL over state-of-the-art methods by at least 9.5% in average travel time. © 2000-2011 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing Resource Allocation for Secure Communication in IoT Ecosystems

Optimizing Resource Allocation for Secure Communication in I...

引用

2024 International Conference on Distributed Systems, computer Networks and Cybersecurity, ICDSCNC 2024

作者： Naga, Suresh Bysani Venkata Kotiyal, Arnav Singh, Suruchi Brahma Rao, K.B.V. Mitra, Abhijit Natrayan, L. Eightfold.ai Ex - Cohesity CA United States Graphic Era Deemed to Be University Department of Computer Science & Engineering Dehradun India Uiet Chhatrapati Shahu Ji Maharaj University Department of Computer Science and Engineering Kanpur India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering India Pune India Simats Saveetha School of Engineering Department of Mechanical Engineering India

ISBN: (纸本)9798350375442

The proliferation of social media has made sites like Twitter a treasure trove of information for diagnosing mental health problems like depression. By examining trends in user-generated material, this research presents a machine learning system with the goal of identifying Twitter profiles exhibiting symptoms of sadness. We made sure to include tweets from a wide range of demographics in our dataset by collecting them from both people who reported having depression and a control group. Text, facial expressions, and interaction patterns were all subjected to feature extraction analysis. We used sentiment analysis and natural language processing (NLP) techniques to identify depressive symptoms in language and emotions. A number of ml models were trained and assessed for accuracy, precision, and recall;these models included Neural Networks, Random Forests, and Support Vector Machines (SVMs). Our approach outperforms baseline algorithms in identifying depressed symptoms, according to the data. Providing a scalable method for early diagnosis of depression, this research adds to the continuing efforts in digital psychiatry. It could aid in prompt intervention and support for affected patients. Responsible use of technology in mental health monitoring requires further discussion of privacy implications and ethical considerations when implementing such models. Several indicators were used to objectively analyze the performance of the machine learning models. With 89% accuracy, 86% precision, and 88% recall, the Neural Network model was the top performer. Additionally, the Random Forest model performed admirably, achieving 85% accuracy, 83% precision, and 84% recall. A recall of 81%, precision of 80%, and accuracy of 82% were all rather respectable for the SVM model. © 2024 IEEE.

关键词： Tweets

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：