检索结果-内蒙古大学图书馆

Data, Decision and Systems (ICDDS), IEEE International conference on

ISBN: (数字)9798350363890

ISBN: (纸本)9798350363906

Deep neural networks have found wide applications in fields such as natural language processing, language translation, computer vision, and speech recognition, including recommendation systems. Among different types of deep neural networks used in recommendation systems, neural collaborative filtering (2017), which is a multilayer perceptron based recommender system, is widely explored as a general model for user-item interactions. neural collaborative filtering is generic and can express and generalize matrix factorization under its framework. However, pairwise learning of neural collaborative filtering is less explored. In this paper, we present a framework NCF-PL, short for neural collaborative filtering with pairwise learning to model the pairwise preference of the items for the users using implicit feedback data. To model user-item interaction, both dot product and MLP are explored. Using dot product to model user-item interaction generalizes matrix factorization under the NCF-PL framework. We perform experiments on two real-world datasets to demonstrate the improvements of our NCF-PL framework over the state-of-the-art Bayesian personalized ranking framework.

关键词： Measurement Computer vision Translation Collaborative filtering artificial neural networks Speech recognition Multilayer perceptrons Natural language processing Data models Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Detection Using artificial Convolutional neural networks 4

Brain Tumor Detection Using Artificial Convolutional Neural ...

引用

4th International conference on Intelligent Circuits and Systems, ICICS 2022

作者： Ramu, B. Bansal, Sandeep Rathour, Navjot School of Electronics & Electrical Engineering Lovely Professional University Punjab Jalandhar India Uttaranchal Institute of Technology Uttaranchal University Uttarakhand Dehradun India

Automatic flaw detection in pictorial representation associate degreed CT brain photos is crucial in an exceptional type of diagnostic and therapeutic applications. Due to the large quantity of data in pictorial representation scans and additionally the crooked boundaries, growth segmentation and identification established tough. Associate degree automatic growth detection methodology was used during this investigation that improved accuracy, yield, and diagnostic time. The goal is to kind the tissue into three groups. There as three sorts of cancer: ancient, early, and malignant. The number of data in pictorial representation and CT scans is simply too nice for human interpretation and analysis. Tumor segmentation in resonance imaging (MRI) has emerged as a rising study subject inside the sphere of medical imaging in recent years. The flexibility to accurately notice the size and size of a growth is important among the identification of the sickness. Pre-processing of imaging footage, feature extraction, classification supported ANN and a cluster of the tumor half because the four phases of the diagnostic approach. The choices as retrieved victimization wave transformation once the image has been pre-processed (DWT). The photos as classified into ancient and pathological brain footage victimization an artificial neural Network (ANN). With a spotlight on the special Fuzzy c-means cluster, the simplest formula for tumor detection is projected. The goal of this paper is to improve the ANFIS architecture so that it can achieve high classification accuracy and quantify tumor thickness and volume © Published under licence by IOP Publishing Ltd.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

A Temporal and Self-Attention Based Method for Small Object Detection in UAV imagery

A Temporal and Self-Attention Based Method for Small Object ...

引用

International Joint conference on neural networks (IJCNN)

作者： Liang Zuo Jie Hao LingXiao Yu Nanjing University of Aeronautics and Astronautics Nanjing China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Unmanned aerial vehicle (UAV) images are widely applied in real-world applications. However, traditional object detection methods have encountered a sharp performance drop on UAV images, largely due to the presence of numerous small objects with low resolution, sparse textures, and blurred features. In this paper, we propose a novel Adaptive Anchor Detection Network (AADN) that dynamically generate anchors through deep neural network. Subsequently the proposed Temporal And Self-Attention (TAA) module enhances the extracted image features by capturing temporal and internal correlation information. Furthermore, we introduce a data augmentation method based on category k-means clustering, designed to reduce irrelevant background regions and improve the network’s ability to distinguish objects with similar categories. Extensive experiments show the superior performance of AADN on both the VisDrone2019 and TinyPerson dataset, achieving an impressive 2% increase in mean average precision (mAP) compared to state-of-the-art methods.

关键词： Adaptive systems Correlation image resolution Object detection artificial neural networks Autonomous aerial vehicles Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Research on Development and Integration of artificial Intelligence Aided Diagnosis System 22

Research on Development and Integration of Artificial Intell...

引用

3rd Asia-Pacific conference on image processing, Electronics and Computers, IPEC 2022

作者： Sun, Erhua Cai, Xiaocheng Lei, Jiali School of Digital Engineering Chongqing College of Architecture and Technology Chongqing China

ISBN: (纸本)9781450395786

In view of the current lack of agile development project management and steep learning curve of tensorflow serving deployment in the medical field of artificial intelligence, based on the named entity recognition and entity annotation of Chinese electronic medical records, this paper uses the iterated dilated convolutional neural networks(ID-CNNs) and conditional random field modeling of deep learning, develops restful API by combining the model training results with Python flask, and uses spring boot / spring cloud Alibaba, Using container technology docker and enterprise kubernetes management platform rancher, using agile development project management and the idea of front-end and back-end separation, promote the establishment of deep learning model, the parallel development of training process and system software, and the agile development, integration, debugging and deployment of artificial intelligence aided diagnosis system. © 2022 ACM.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

AUTOMATIC ROAD CRACK RECOGNITION BASED ON DEEP LEARNING networks FROM UAV imageRY 6

AUTOMATIC ROAD CRACK RECOGNITION BASED ON DEEP LEARNING NETW...

引用

ISPRS GeoSpatial conference / Joint 6th Sensors and Models in Photogrammetry and Remote Sensing conference (SMPR) / 4th Geospatial Information Research (GIResearch) conference

作者： Samadzadegan, F. Javan, F. Dadrass Hasanlou, M. Gholamshahi, M. Mahini, F. Ashtari Univ Tehran Sch Surveying & Geospatial Engn Coll Engn Tehran Iran Univ Twente Fac Geoinformat Sci & Earth Observat ITC NL-7522 NB Enschede Netherlands Kharazmi Univ Dept Elect & Comp Engn Fac Engn Tehran Iran

Roads are one of the essential transportation infrastructures that get damaged over time and affect economic development and social activities. Therefore, accurate and rapid recognition of road damage such as cracks is necessary to prevent further damage and repair it in time. The traditional methods for recognizing cracks are using survey vehicles equipped with various sensors, visual inspection of the road surface, and recognition algorithms in image processing. However, performing recognition operations using these methods is associated with high costs and low accuracy and speed. In recent years, the use of deep learning networks in object recognition and visual applications has increased, and these networks have become a suitable alternative to traditional methods. In this paper, the YOLOv4 deep learning network is used to recognize four types of cracks transverse, longitudinal, alligator, and oblique cracks utilizing a set of 2000 RGB visible images. The proposed network with multiple convolutional layers extracts accurate semantic feature maps from input images and classifies road cracks into four classes. This network performs the recognition process with an error of 1% in the training phase and 77% F1-Score, 80% precision, 80% mean average precision (mAP), 77% recall, and 81% intersection over union (IoU) in the testing phase. These results demonstrate the acceptable accuracy and appropriate performance of the model in road crack recognition.

关键词： Deep Learning Convolutional neural Network Road Cracks Road Crack Recognition YOLO Deep Learning Network YOLOv4 Deep Learning Network

来源：评论

学校读者我要写书评

暂无评论

Modeling and Verification of Sigma Delta neural networks using Satisfiability Modulo Theory 25

Modeling and Verification of Sigma Delta Neural Networks usi...

引用

Proceedings of the 26th ACM SIGPLAN/SIGBED International conference on Languages, Compilers, and Tools for Embedded Systems

作者： Sirshendu Das Ansuman Banerjee Swarup Kumar Mohalik Indian Statistical Institute Kolkata India Ericsson India Pvt. Ltd. Bangalore India

ISBN: (纸本)9798400719219

In the context of modern day embedded safety-critical systems and low-resource edge devices in particular, Sigma-Delta neural networks (SDNNs) offer a promising alternative to traditional artificial neural networks (ANNs) by leveraging event-driven, sparse computations inspired by biological neural processing. This energy-efficient paradigm makes SDNNs well-suited for neuromorphic hardware and real-time applications, particularly in scenarios with temporal redundancy, such as video processing. However, as neural networks become integral to safety-critical systems, ensuring their robustness against adversarial perturbations is an absolute necessity. In this work, we propose an end-to-end framework for formal modeling and verification of SDNNs using Satisfiability Modulo Theory (SMT). Unlike empirical robustness evaluations, SMT-based verification provides formal guarantees by encoding SDNN behavior and adversarial robustness properties as mathematical constraints. We introduce an SMT-based formulation for encoding SDNNs with SMT constraints and define a robustness property motivated by video stream processing. Our approach systematically examines how well SDNNs can handle adversarial attacks, ensuring they work correctly in safety-critical applications. We validate our framework through experiments on temporal version of the MNIST dataset. To the best of our knowledge, this is the first formal verification framework for SDNNs, bridging the gap between neuromorphic computing and rigorous verification.

关键词： Formal Verification

来源：评论

学校读者我要写书评

暂无评论

TFNet: Exploiting Temporal Cues for Fast and Accurate LiDAR Semantic Segmentation

TFNet: Exploiting Temporal Cues for Fast and Accurate LiDAR ...

引用

IEEE Computer Society conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Rong Li Shijie Li Xieyuanli Chen Teli Ma Juergen Gall Junwei Liang HKUST(GZ) China University of Bonn Germany Lamarr Institute for Machine Learning and Artificial Intelligence Germany HKUST China

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

LiDAR semantic segmentation plays a crucial role in enabling autonomous driving and robots to understand their surroundings accurately and robustly. A multitude of methods exist within this domain, including point-based, range-image-based, polar-coordinate-based, and hybrid strategies. Among these, range-image-based techniques have gained widespread adoption in practical applications due to their efficiency. However, they face a significant challenge known as the "many-to-one" problem caused by the range image ’s limited horizontal and vertical angular resolution. As a result, around 20% of the 3D points can be occluded. In this paper, we present TFNet, a range-image-based LiDAR semantic segmentation method that utilizes temporal information to address this issue. Specifically, we incorporate a temporal fusion layer to extract useful information from previous scans and integrate it with the current scan. We then design a max-voting-based post-processing technique to correct false predictions, particularly those caused by the "many-to-one" issue. We evaluated the approach on two benchmarks and demonstrated that the plugin post-processing technique is generic and can be applied to various networks.

关键词： Training Laser radar Three-dimensional displays image resolution Semantic segmentation Face recognition neural networks

来源：评论

学校读者我要写书评

暂无评论

applications of deep learning in fish habitat monitoring: A tutorial and survey

引用

EXPERT SYSTEMS WITH applications 2024年第PartB期238卷

作者： Saleh, Alzayat Sheaves, Marcus Jerry, Dean Azghadi, Mostafa Rahimi James Cook Univ Coll Sci & Engn 1 James Cook Dr Townsville Qld 4811 Australia James Cook Univ ARC Res Hub Supercharging Trop Aquaculture Genet S 1 James Cook Dr Townsville Qld 4811 Australia

Marine ecosystems and their fish habitats are becoming increasingly important due to their integral role in providing a valuable food source and conservation outcomes. Due to their remote and difficult to access nature, marine environments and fish habitats are often monitored using underwater cameras to record videos and images for understanding fish life and ecology, as well as for preserve the environment. There are currently many permanent underwater camera systems deployed at different places around the globe. In addition, there exists numerous studies that use temporary cameras to survey fish habitats. These cameras generate a massive volume of digital data, which cannot be efficiently analysed by current manual processing methods, which involve a human observer. Deep Learning (DL) is a cutting-edge artificial Intelligence (AI) technology that has demonstrated unprecedented performance in analysing visual data. Despite its application to a myriad of domains, its use in underwater fish habitat monitoring remains under explored. In this paper, we provide a tutorial that covers the key concepts of DL, which help the reader grasp a high-level understanding of how DL works. The tutorial also explains a step-by-step procedure on how DL algorithms should be developed for challenging applications such as underwater fish monitoring. In addition, we provide a comprehensive survey of key deep learning techniques for fish habitat monitoring including classification, counting, localisation, and segmentation. Furthermore, we survey publicly available underwater fish datasets, and compare various DL techniques in the underwater fish monitoring domains. We also discuss some challenges and opportunities in the emerging field of deep learning for fish habitat processing. This paper is written to serve as a tutorial for marine scientists who would like to grasp a high-level understanding of DL, develop it for their applications by following our step-by-step tutorial, and see how

关键词： Marine Science Computer Vision Convolutional neural networks image and video processing Machine Learning Deep Learning Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

applications of artificial Intelligence-Based Communication Systems in Rail Transit

Applications of Artificial Intelligence-Based Communication ...

引用

Internet of Things, Automation and artificial Intelligence (IoTAAI), International conference on

作者： Yuming Fu Lanzhou Institute of Technology Lanzhou China

ISBN: (数字)9798350386974

ISBN: (纸本)9798350386981

This paper explores the integration of artificial Intelligence (AI) into communication systems within urban rail transit, emphasizing the development of a Train-to-Train (TT) communication-based train control system that deviates from traditional centralized control methods. By utilizing the capabilities of Deep Reinforcement Learning (DRL) and neural network architectures, the proposed system enhances operational efficiency, safety, and reliability of train operations by allowing autonomous and distributed decision-making directly on trains. The application of a multi-layer fully connected neural network enables sophisticated data processing and decision-making through deep learning techniques, addressing the challenges of resource allocation in dense urban transit scenarios. Simulation results validate the effectiveness of the AI-driven approach, demonstrating significant improvements in the quality of service (QoS), spectral efficiency, and system throughput under varying train densities. The study confirms that AI can play a crucial role in advancing the intelligence and efficiency of rail transit systems, offering a scalable solution for future developments in urban transportation.

关键词： Rails Spectral efficiency neural networks Decision making Transportation Quality of service Data processing Safety Internet of Things Resource management

来源：评论

学校读者我要写书评

暂无评论

Research on Badminton Movement Machine Learning Model Based on Computer Vision Technology

Research on Badminton Movement Machine Learning Model Based ...

引用

image processing and Computer applications (ICIPCA), IEEE International conference on

作者： Cheng Zong Hohhot Vocational College Hohhot China

ISBN: (数字)9798350360240

ISBN: (纸本)9798350384161

This paper aims to explore an innovative method combining computer vision and machine learning to accurately identify and analyze various movements in badminton. This paper first summarizes the application prospect of computer vision in the field of sports analysis, and introduces its specific application scenarios in badminton in detail. By constructing a complete technical framework of image preprocessing module, feature extraction algorithm and deep learning model, the complex movements of badminton players such as swing, stroke and moving pace are captured and analyzed. In the research process, we used multi-view image fusion and key point detection technology to accurately extract action features in badminton, combined with convolutional neural network (CNN), recurrent neural network (RNN), long term memory network (LSTM) and other deep learning models to efficiently learn and model these features. Thus, the automatic classification and recognition of badminton movement can be realized. The experimental results show that the model has significant accuracy in badminton action recognition, good generalization ability and practicability, and can be effectively applied in the badminton teaching and training process of athlete performance evaluation, competition data analysis and other aspects. This research result not only expands the practical application of computer vision technology in the field of badminton, but also provides new ideas and tools for further promoting the development of sports intelligence and digitalization.

关键词： Training Deep learning Computer vision Analytical models Recurrent neural networks Computational modeling Feature extraction Data models Convolutional neural networks Sports

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：