检索结果-内蒙古大学图书馆

Advancement in Computation & computer Technologies (InCACCT), International Conference on

作者： P. Abirami D. Antony Joseph Rajan T. Vivekanandan V. Saillaja N. Mohankumar M. Rajmohan Department of Artificial Intelligence and Data Science Velammal Institute of Technology Chennai Tamil Nadu India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India Department of Mathematics Vel Tech Multi Tech Dr Rangarajan Dr Sakunthala Engineering College Chennai Tamil Nadu India Faculty of Management Studies SRM Institute of Science and Technology Kattankulathur Chennai Tamil Nadu India Department of Electronics and Communication Engineering B.V. Raju Institute of Technology Telangana India Department of Electronics and Communication Engineering Hindustan Institute of Technology and Science Chennai Tamil Nadu India

ISBN: (数字)9798350371314

ISBN: (纸本)9798350371321

The presentation summarizes a groundbreaking cognitive training program designed specifically for those who suffer from cognitive impairments or neurodevelopmental abnormalities. The work creates a dynamic platform for immersive and adaptable cognitive training games by combining cutting-edge Convolutional Neural Networks (CNNs) with Raspberry Pi technology. Memory, focus, and ability to think creatively are all qualities directly targeted by these games. The CNN model, trained on a broad dataset, interprets real-time user inputs, delivering quick feedback and altering game complexity depending on an individual’s performance. The incorporation of Raspberry Pi guarantees a solution that is both affordable and easily accessible. The capacity of the system to redefine cognitive rehabilitation by providing a solution that is individualizable, interactive, and broadly deployable is the potential source of the system’s influence. The goal of the work is to make a substantial contribution to the field, which will eventually be to the advantage of users, caregivers, and healthcare professionals and ultimately improve the cognitive well-being of those coping with cognitive issues.

关键词： Training Psychology Medical treatment Games Software Real-time systems Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Vision Language Modeling of Content, Distortion and Appearance for Image Quality Assessment

arXiv

引用

arXiv 2024年

作者： Zhou, Fei Gu, Tianhao Huang, Zhicong Qiu, Guoping College of Electronic and Information Engineering Shenzhen University Shenzhen518060 China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen518060 China SZU-AFS Joint Innovation Center for Artificial Intelligence Technology Shenzhen518000 China Guangdong-Hong Kong Joint Laboratory for Big Data Imaging and Communication Shenzhen518060 China School of Computer Science The University of Nottingham Ningbo China Zhejiang315100 China School of Computer Science University of Nottingham NottinghamNG8 1BB United Kingdom

The visual quality of an image is confounded by a number of intertwined factors including its semantic content, distortion characteristics and appearance properties such as brightness, contrast, sharpness, and colourfulness. Distilling high level knowledge about all these quality bearing attributes is crucial for developing objective Image Quality Assessment (IQA). While existing solutions have modeled some of these aspects, a comprehensive solution that involves all these important quality related attributes has not yet been developed. In this paper, we present a new blind IQA (BIQA) model termed Self-supervision and Vision-Language supervision Image QUality Evaluator (SLIQUE) that features a joint vision-language and visual contrastive representation learning framework for acquiring high level knowledge about the images semantic contents, distortion characteristics and appearance properties for IQA. For training SLIQUE, we have developed a systematic approach to constructing a first of its kind large image database annotated with all three categories of quality relevant texts. The Text Annotated Distortion, Appearance and Content (TADAC1) database has over 1.6 million images annotated with textual descriptions of their semantic contents, distortion characteristics and appearance properties. The method for constructing TADAC and the database itself will be particularly useful for exploiting vision-language modeling for advanced IQA applications. Extensive experimental results show that SLIQUE has superior performances over state of the art, demonstrating the soundness of its design principle and the effectiveness of its implementation. The link to the TADAC dataset is https://***/documents/tadactextannotated-distortion-appearance-and-content Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Video Pretraining Advances 3D Deep Learning on Chest CT Tasks

arXiv

引用

arXiv 2023年

作者： Ke, Alexander Huang, Shih-Cheng O'Connell, Chloe Klimont, Michal Yeung, Serena Rajpurkar, Pranav Department of Computer Science Stanford University United States Department of Biomedical Data Science Stanford University United States Department of Anesthesia Massachusetts General Hospital United States Center for Artificial Intelligence in Medicine & Imaging Stanford University United States Department of Electrical Engineering Stanford University United States Department of Biomedical Informatics Harvard Medical School United States

Pretraining on large natural image classification datasets such as ImageNet has aided model development on data-scarce 2D medical tasks. 3D medical tasks often have much less data than 2D medical tasks, prompting practitioners to rely on pretrained 2D models to featurize slices. However, these 2D models have been surpassed by 3D models on 3D computer vision benchmarks since they do not natively leverage cross-sectional or temporal information. In this study, we explore whether natural video pretraining for 3D models can enable higher performance on smaller datasets for 3D medical tasks. We demonstrate video pretraining improves the average performance of seven 3D models on two chest CT datasets, regardless of finetuning dataset size, and that video pretraining allows 3D models to outperform 2D baselines. Lastly, we observe that pretraining on the large-scale out-of-domain Kinetics dataset improves performance more than pretraining on a typically-sized in-domain CT dataset. Our results show consistent benefits of video pretraining across a wide array of architectures, tasks, and training dataset sizes, supporting a shift from small-scale in-domain pretraining to large-scale out-of-domain pretraining for 3D medical tasks. Our code is available at: https://***/rajpurkarlab/chest-ct-pretraining. © 2023, CC BY.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Monocular Depth Estimation for UAV Navigation Using Segmental Fully Convolutional Prairie Dog Neural Networks

Monocular Depth Estimation for UAV Navigation Using Segmenta...

引用

Sentiment Analysis and Deep Learning (ICSADL), International Conference on

作者： Indradeep Kumar A. Elumalai G. Santha Meena Jagath Narayana Kamineni Joshuva Arockia Dhanraj M. Revathi Amity Institute of Technology Amity University Noida Uttar Pradesh India Department of Mathematics R.M.K. Engineering College Chennai Tamil Nadu India Department of Mathematics PSNA College of Engineering and Technology (Autonomous) Dindigul Tamil Nadu India Department of Mechanical Engineering Sri Venkateshwara College of Engineering Tirupati Andhra Pradesh India Department of Computer Science and Engineering (AI&ML) School of Engineering Dayananda Sagar University Bengaluru Karnataka India Department of Artificial Intelligence and Data Science St.Joseph's Institute of Technology Chennai Tamil Nadu India

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

Unmanned Aerial Vehicles (UAVs) play an important role in very precise navigation for its usage in applications like disaster management, agricultural surveillance, and as delivery drones. Precise depth estimation is crucial for UAV to safely avoid obstacles and thus obtain proper paths for flying. Monocular Depth Estimation (MDE), is another method which is becoming popular due to its easy implementation as compared to stereo vision and LiDAR systems in which single camera depth information is inferred. However, found that there are still some problems in the current a few deep learning methods of MDE, including high computational cost, low prediction accuracy in dynamic conditions, and unsuitability for real-time or online applications. In order to solve these problems, the current research work introduces a Segmental Fully Convolutional Neural Network (SFCNN) tended by the Prairie Dog Optimization (PDO) for UAV flight. The block structure improves adaptability as well as computational complexity; PDO seeks to minimize network's parameters to increase the result precision of the depth forecast and lessen the computation time. tarting from this background, the proposed approach is intended to support lightweight real-time and reliable means for MDE to enhance UAV navigation in complex environments.

关键词： Grasslands Navigation Depth measurement Dogs Autonomous aerial vehicles Real-time systems Stereo vision Convolutional neural networks Vehicle dynamics Optimization

来源：评论

学校读者我要写书评

暂无评论

Semantically Meaningful Class Prototype Learning for One-Shot Image Semantic Segmentation

arXiv

引用

arXiv 2021年

作者： Chen, Tao Xie, Guo-Sen Yao, Yazhou Wang, Qiong Shen, Fumin Tang, Zhenmin Zhang, Jian The School of Computer Science and Engineering Nanjing University of Science and Technology China The Inception Institute of Artificial Intelligence Abu Dhabi United Arab Emirates The School of Computer Science and Engineering University of Electronic Science and Technology of China China The School of Electrical & Data Engineering University of Technology Sydney Australia

One-shot semantic image segmentation aims to segment the object regions for the novel class with only one annotated image. Recent works adopt the episodic training strategy to mimic the expected situation at testing time. However, these existing approaches simulate the test conditions too strictly during the training process, and thus cannot make full use of the given label information. Besides, these approaches mainly focus on the foreground-background target class segmentation setting. They only utilize binary mask labels for training. In this paper, we propose to leverage the multi-class label information during the episodic training. It will encourage the network to generate more semantically meaningful features for each category. After integrating the target class cues into the query features, we then propose a pyramid feature fusion module to mine the fused features for the final classifier. Furthermore, to take more advantage of the support image-mask pair, we propose a self-prototype guidance branch to support image segmentation. It can constrain the network for generating more compact features and a robust prototype for each semantic class. For inference, we propose a fused prototype guidance branch for the segmentation of the query image. Specifically, we leverage the prediction of the query image to extract the pseudo-prototype and combine it with the initial prototype. Then we utilize the fused prototype to guide the final segmentation of the query image. Extensive experiments demonstrate the superiority of our proposed approach. The source codes and models have been made available at https: //***/NUST-Machine-intelligence-Laboratory/SMCP. Copyright © 2021, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Challenges in metaverse in problem-based learning as a game-changing virtual-physical environment for personalized content development

Challenges in metaverse in problem-based learning as a game-...

引用

6th Smart Cities Symposium (SCS 2022)

作者： P.K. Dutta M. Bose A. Sinha R. Bhardwaj S. Ray S. Roy K.B. Prakash School of Engineering and Technology Amity University Kolkata Kolkata India School of Computer Application Amity University Kolkata Kolkata India Department of Mathematics Amity University Kolkata Kolkata India Senior Researcher Petersburg Polytechnic University Artificial Intelligence & Data Science Jio Institute Navi Mumbai India Department of Computer Science and Engineering Konneru Lakshmaih Education Foundation

The benefits and drawbacks of using the metaverse in the field of education are discussed, along with the possibilities and potential issues it will open up. Utilizing the idea of personalised knowledge transfer and the use of an immersive environment to match students' learning pace using horizon classroom, the Metaverse environment can add a new dimension to the field of educational technologies. We have also highlighted the virtualization-based redesign of educational environments using a personalised cloud, which is anticipated to improve learning for students by making it more affordable, collaborative, and useful. The goal is to build a metaversity that can serve as a communication tool for teachers and students anywhere in the world by providing each with an individual avatar. This platform will offer a virtual setting for students to socialise with their friends and peers and receive peer-to-peer learning, which is lacking in the current e-learning environment. The students won't need an entrance score card; instead, they will need critical learning skills to advance and mature.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Feature Rotation Invariance Learning for Point Cloud Analysis

Feature Rotation Invariance Learning for Point Cloud Analysi...

引用

Smart World Congress (SWC), IEEE

作者： Lu Shi Qi Cao Guoqing Zhang Jin Yi Yansen Huang Yigang Cen State Key Laboratory of Advanced Rail Autonomous Operation the School of Computer Science and Technology and Visual Intellgence +X International Cooperation Joint Laboratory of MOE Beijing Jiaotong University Beijing China the School of Computing Science University of Glasgow Singapore With the Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education the State Key Laboratory of Advanced Rail Autonomous Operation and the School of Computer and Information Technology Beijing Jiaotong University Beijing China the College of Civil Engineering Guizhou University Guizhou Lianjian Civil Engineering Quality Testing Monitoring Center Co. LTD Guizhou China

ISBN: (数字)9798331520861

ISBN: (纸本)9798331520878

While deep learning has significantly advanced point cloud analysis, extracting effective features from their disordered structure remains challenging. Existing approaches often rely on complex network architectures or manual feature engineering to achieve rotation invariance, which increases inference latency. This paper offers a novel perspective on this challenge, showing that rotation-sensitive models can achieve performance comparable to rotation-invariant models when trained with rotation-augmented data. Given the significant differences in the feature distributions of rotation-sensitive and rotation-invariant models, we propose Feature Rotation Invariance Learning (FRIL), a framework that leverages Distance Metric Learning and rotation-based constraints to help rotation-sensitive models extract rotation-invariant features. This approach eliminates the need for additional modules, enabling robust performance against rotations. Extensive experiments demonstrate that FRIL consistently outperforms existing rotation-invariant methods across various visual tasks.

关键词： Point cloud compression Representation learning Analytical models Solid modeling Visualization Three-dimensional displays Semantics Cloning Feature extraction data models

来源：评论

学校读者我要写书评

暂无评论

Collaborative Filtering ML Technique for Recommendation in E-Commerce Energy System

Collaborative Filtering ML Technique for Recommendation in E...

引用

IEEE International Conference on Emerging & Sustainable Technologies for Power & ICT in a Developing Society (NIGERCON)

作者： Hew Sok Yen Samuel-Soma M. Ajibade Angela Lee Siew Hoong Rex V. Culpable Celestino A. Quirante Johnry P. Dayupay Adedotun O. Adetunla Oluwadare Joshua Oyebode Department of Data Science and Artificial Intelligence School of Engineering and Technology Sunway University Selangor Malaysia Research Centre for Nanomaterials and Energy Technology (RCNMET) Sunway University Selangor Malaysia College of Technology Cebu Technological University Cebu Philippines Cebu Technological University Cebu Philippines Dept. of Mechanical and Mechatronics Engineering Afe Babalola University Ado Ekiti Nigeria Dept. of Mechanical Engineering Science University of Johannesburg Johannesburg South Africa Civil and Environmental Engineering Department Afe Babalola University Ado Ekiti Nigeria

ISBN: (数字)9798331542559

ISBN: (纸本)9798331542566

The growing integration of e-commerce into daily life has highlighted the essential need for recommender systems to enhance user experience and drive business success. This study examines machine learning techniques for developing effective recommender systems, with a particular focus on collaborative filtering (CF) and content-based filtering (CBF) methods. This study employs exploratory data analysis (EDA) to analyze e-commerce statistics, identifying trends in consumer behavior, product ratings, and user engagement, culminating in the development of a hybrid recommender system. The hybrid method amalgamates the benefits of Continuous Feedback (CF) with Context-Based Feedback (CBF) to deliver customized recommendations, hence improving accuracy and relevance for users. The application of hybrid models yields a notable improvement in predictive performance, evidenced by reduced mistake rates and heightened customer satisfaction. This research offers distinctive insights on user-product interactions, thereby advancing the comprehension of how machine learning could transform e-commerce personalization.

关键词： data analysis Consumer behavior Accuracy Filtering Collaborative filtering Transforms Predictive models User experience Electronic commerce Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Training of Spiking Neural Network joint Curriculum Learning Strategy

arXiv

引用

arXiv 2023年

作者： Tang, Lingling Chu, Jielei Gong, Zhiguo Li, Tianrui The School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China The State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science University of Macau China

Starting with small and simple concepts, and gradually introducing complex and difficult concepts is the natural process of human learning. Spiking Neural Networks (SNNs) aim to mimic the way humans process information, but current SNNs models treat all samples equally, which does not align with the principles of human learning and overlooks the biological plausibility of SNNs. To address this, we propose a CL-SNN model that introduces Curriculum Learning(CL) into SNNs, making SNNs learn more like humans and providing higher biological interpretability. CL is a training strategy that advocates presenting easier data to models before gradually introducing more challenging data, mimicking the human learning process. We use a confidence-aware loss to measure and process the samples with different difficulty levels. By learning the confidence of different samples, the model reduces the contribution of difficult samples to parameter optimization automatically. We conducted experiments on static image datasets MNIST, Fashion-MNIST, CIFAR10, and neuromorphic datasets N-MNIST, CIFAR10-DVS, DVS-Gesture. The results are promising. To our best knowledge, this is the first proposal to enhance the biologically plausibility of SNNs by introducing CL. Copyright © 2023, The Authors. All rights reserved.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Deep Training and Adapting Algorithms in Medical with De-Noising EEG

Evaluation of Deep Training and Adapting Algorithms in Medic...

引用

Advance Computing and Innovative Technologies in engineering (ICACITE), International Conference on

作者： Ali Hadi Abdulwahid Girija Rani Karetla KVB. Ganesh A Suresh Kumar K. Radha K. Shivakumar Control and Automation Engineering Department Engineering Technical College Southern Technical University Basra Iraq School of Computer Data and Mathematical Sciences Western Sydney University Australia KL Business School Koneru Lakshmaiah Education Foundation Guntur Andhra Pradesh India Department of CSE Graphic Era Deemed to be University Dept. of IT St. Martin's Engineering College Secunderabad Telangana India School of Computer Science and Artificial Intelligence SR University Warangal Telangana India

An electroencephalogram that was captured with electrodes placed can easily get contaminated with a variety of artifacts. Here is a comparative of various electroencephalogram (EEG) de-noising techniques. Three alternative techniques are used to eliminate five different kinds of noise, and also the outcomes are evaluated. These three methods are just the Least Mean Square (LMS) technique, the Connected Neural Network, and also the Recursive Least - square (RLS) adaptable algorithm (FCNN). Period charts of the actual EEG signal, the noise EEG signal, and thus the predicted EEG signal are used to display the results. RRMSE and signal- to-noise ratio were utilized to compare the effectiveness of the 3 de-noising strategies in this study. Investigating the model parameters in this case, we discover the FCNN forecasts a better outcome compared to the other two methods.

关键词：

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：