检索结果-内蒙古大学图书馆

9th IEEE International Conference for Convergence in Technology, I2CT 2024

作者： Abhinav, B.V. Adhi Nandan, J. Gurikar, Adithya S. Joshi, Aditya Pandharkar, Akshit Prajwala, T.R. Pes University Department of Computer Science And Engineering Bengaluru India

ISBN: (纸本)9798350394474

In today's football landscape, scouting has evolved into a critical component for teams seeking hidden gems, established stars, and future talents. Amid this evolution, an innovative xG-based scouting system is poised to become a prominent fixture in the football lexicon. This system leverages the power of underlying stats like Expected Goals (xG) to meticulously evaluate players worldwide, recommending those who align with a team's unique needs and exhibit a significant *** approach uses a combination of various regression models and geometric distances to combine a large range of metrics and staggering statistics to function as a talent scout, ushering in a new era of player identification. It is able to identify players with huge potential and recommend them to clubs using it. This paper provides a comprehensive insight into the working of our pioneering xG-based scouting system, detailing its data-driven recommendations for teams. Ultimately this xG based scouting system enhances a team's ability to unearth the stars of tomorrow. © 2024 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

REPLAYING WITH REALISTIC LATENT VECTORS IN GENERATIVE CONTINUAL LEARNING 3

REPLAYING WITH REALISTIC LATENT VECTORS IN GENERATIVE CONTIN...

引用

3rd Conference on Lifelong Learning Agents, CoLLAs 2024

作者： Jeong, Hyemin Kim, Seong-Woong Choi, Dong-Wan Department of Computer Science and Engineering Inha University Korea Republic of

In generative continual learning for GANs, replay-based methods mitigate forgetting of past knowledge by retraining either synthesized images from the previous generator (generative replay) or real images from the memory buffer (memory replay) during training each new task. However, despite its strength at memory efficiency, generative replay often fails to produce realistic images, due to the gap between synthetic and real images especially in challenging datasets. Although memory replay can address this issue by storing real images, it still suffers from the practical limit of memory space, gradually deteriorating the quality of generated images. In this paper, we propose a novel mixed replay method, called Realistic Latent Vector Fitting (RactoFit), which not only effectively resolves the drawbacks of generative and memory replay but also combine their strengths, memory utilization yet realism preservation. To efficiently utilize the memory space, our proposal is to maintain realistic latent vectors corresponding to previous real images, rather than storing those images themselves. In addition to replaying with these stored latent vectors, we also design a new optimization technique for latent vectors that can generate more realistic images from the previous generator, not just taking random vectors as in generative replay. Through our experimental analysis, we demonstrate that our method outperforms the baseline methods of continual learning for GANs in terms of the standard metrics for generative models, along with qualitative results clearly showing the highest level of realism of our generated images. © 2024 CoLLAs. All Rights Reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unmasking Pneumonia with Deep Learning: Enhancing Medical Diagnosis through Advanced AI Models 14

Unmasking Pneumonia with Deep Learning: Enhancing Medical Di...

引用

14th International Conference on Cloud Computing, Data science and engineering, Confluence 2024

作者： Puri, Naman Ashhad, Abdul Kumar, Nitish Amity University Department of Computer Science Engineering Noida India

ISBN: (纸本)9798350344837

Pneumonia has emerged as a global health concern, with a higher mortality rate compared to Covid-19. In 2019, over two million people succumbed to this infectious disease, including nearly 600,000 infants under the age of 5. The traditional method of disease identification, reliant on manual examination by radiologists, is plagued by its unreliability due to suboptimal accuracy. Advancements in computational resources, particularly the enhanced computing capabilities of GPUs, have opened opportunities to train highly complex models. This research undertakes a comparative study of various deep learning models for the purpose of pneumonia detection. The primary objective is to perform binary image classification for pneumonia recognition using three distinct models: a baseline Sequential model built from scratch using TensorFlow, VGG16 Autoencoder, and Keras ViT. The aim is to assess their efficacy on the test set. The dataset comprises 5856 Chest X-Ray images, both anterior and posterior views, categorized as Normal or Pneumonic. © 2024 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Enhanced CNN Approaches for Multi-Image Embedding in Image Steganography 2

Enhanced CNN Approaches for Multi-Image Embedding in Image S...

引用

2nd International Conference on Information and Communication Technology, ICICT 2024

作者： Hossain, Md. Irtiza Kadir, Samiul Fagun, Farhan Ishraq Samiul, Ishtiaq Saukhin, Rafi Zaman Hossain, Muhammad Iqbal Department of Computer Science and Engineering Brac University Dhaka Bangladesh

ISBN: (纸本)9798331508227

We unveil a convolutional neural network (CNN)architectured steganographic model aimed at concealing multiple secret images in a single cover image, seeking to enhance payload capacity and minimize any encoding or decoding errors. We use a method that employs CNNs for encoding and decoding, harnessing a multi-scale encoder and a key-based decryption approach for increased security. Steganography is accurately and successfully achieved at two and three image levels by the model. For the use of two-image steganography, an accuracy of 95.16% was achieved for the encoded cover image, and decoding accuracies of 97.16% and 97.28% for secret images 1 and 2, respectively. In the three-image steganography, the accuracy of the coded cover image stood at 93.84%, while the decoded secret images achieved accuracies of 96.39%, 94.82%, and 94.76%. We boosted security by employing cryptographic techniques such as AES and ChaCha20 and instituted key integration at the architectural level. Our findings show the competent encoding and decoding of a range of secret images with enhanced security and noteworthy precision. ©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

A NOTE ON THE QUALITATIVE BEHAVIOUR OF AN ODE MODEL RELATED TO ENDOTOXIN TOLERANCE

引用

UPB Scientific Bulletin, Series A: Applied Mathematics and Physics 2024年第4期86卷 127-130页

作者： Olteanu, Mircea Ştefan, Radu Department of Mathematical Methods and Models Faculty of Applied Sciences University "Politehnica" of Bucharest Romania Department of Automatic Control and Systems Engineering Faculty of Automatic Control and Computer Science University "Politehnica" of Bucharest Romania

关键词： Differential equations

来源：评论

学校读者我要写书评

暂无评论

Traffic Density Prediction System using Deep Learning 2

Traffic Density Prediction System using Deep Learning

引用

2nd International Conference on Data science and Information System, ICDSIS 2024

作者： Verma, Hritik Sarkar, Sayan Sadhukhan, Souranil Mishra, Aniket Mondal, Md Ashifuddin Narula Institute Of Technology Department Of Computer Science And Engineering India

ISBN: (纸本)9798350381665

In major cities throughout the world, traffic congestion is still a major problem that negatively affects the efficiency of transportation system. Traffic congestion creates several issues that require a creative and adaptable strategy to solve. This work tackles the problem by accurately forecasting vehicle density by merging state-of-the-art deep learning models, specifically YOLO - v8 for real-time vehicles identification and Stacked Long Short-Term Memory (LSTM) models for forecasting traffic density. These methods are combined to create a powerful vehicle density prediction system. The integration of YOLOv8 with LSTM provides a practical response to the growing issues brought on by traffic congestion in cities. The simulation results shows that accuracy of YOLOv8 is 95.36, while average RMSE value of Stacked LSTM models is 0.591. The proposed model is compared with RNN model for vehicle density forecasting and the proposed model performs better than RNN in terms of accuracy. © 2024 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Dynamic Prototype Weighting for Multi-label Classification Problems 20

Dynamic Prototype Weighting for Multi-label Classification P...

引用

20th CSI International Symposium on Artificial Intelligence and Signal Processing, AISP 2024

作者： Shahsavandi, Ali Taheri, Mohammad Ziarati, Koorush Shiraz University Department of Computer Science and Engineering Shiraz Iran

ISBN: (纸本)9798350383942

Multi-label classification involves the assignment of several labels to each data instance simultaneously. Binary relevance (BR) is widely acknowledged as the most straightforward approach for handling multi-label scenarios. The process involves breaking down the multi-label learning task into a number of independent binary learning tasks. Using Nearest Neighbor (NN) as the binary classifier in BR (BRNN) is a simple, descriptive, and powerful approach. However, the NN has drawbacks, including its dependence on the distance criterion. To address this, we propose a method that tunes a parametric distance using a prototype weighting approach, minimizing complete cross-validation (CCV) classification error on training data. This improves the classifier's generalization and reduces randomness. Nevertheless, it is well established that when dealing with imbalanced data, other performance evaluation metrics, such as the F-measure, offer more relevant insights than classification error. The second contribution of this paper is extending this method to improve the F-measure. Due to the imbalanced nature of multi-label data, it is expected that performance will improve. Our method is compared to state-of-the-art NN-based approaches, demonstrating comparable or superior performance in experiments. © 2024 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Employing A Deep Learning Approach for Brain Tumour Detection Using MR-Images 4

Employing A Deep Learning Approach for Brain Tumour Detectio...

引用

4th IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2024

作者： Ravali, Paripelli Reddy, Pundru Chandra Shaker Praveen, Pappula Sr University Department of Computer Science and Engineering Warangal India

ISBN: (纸本)9798350352931

Depending on its size and location, a brain tumor might affect a person's facial or head symmetry. Asymmetry in the face can caused by a brain tumor if it situated in a region that influences the muscles that conserve facial symmetry. The asymmetry brought on by a brain tumor might not be obvious at first, particularly if the tumor is still in its early stages. The goal of deep-learning for brain-tumors (BTs) classification is to identify brain pictures and categorize them as either benign or malignant. One application of Convolutional-Neural-Networks (CNN) in medical imaging is the categorization of brain cancers. The prognosis for people with BTs drastically diminished when these tumors are misdiagnosed. One frequent method for detecting brain tumors is to review the patient's magnetic resonance imaging (MRI) scans. When dealing with massive datasets and many types of BTs, this method is laborious and error-prone. Aquila-Optimizer (AQO) was utilized for the initial populace generation of the selected dataset. CNN-models were trained to perceive the three most common types of BTs-glioma, meningioma, and pituitary. The VGG-19 model achieved the highest accuracy, at 98.95%. © 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

Brain MRI Images for Tumour Detection Using Storage Optimisation Technique 4th

Brain MRI Images for Tumour Detection Using Storage Optimisa...

引用

4th International Conference on Mobile Radio Communications and 5G Networks, MRCN 2023

作者： Vankdothu, Ramdas Hameed, Mohd Abdul Department of Computer Science and Engineering Osmania University Hyderabad India

ISBN: (纸本)9789819706990

A brain tumour is caused by a mass of random cells inside the brain, which is dangerous and harmful to the brain. Today, it is difficult to accurately recognise brain images. The current demand is for research on the storage, processing, and manipulation of medical image data utilising contemporary technology with little human involvement. The study and creation of cutting-edge technology for the analysis, representation, and interpretation of visual data are known as image processing. The requirement for an effective storage model that may assist in saving the brain MRI images is investigated in this study with the use of an image processing approach. A matrix-based technique is suggested to store the brain MRI pictures with less storage capacity. This model converts DICOM-formatted brain MRI images into matrix format. The patient’s information and image data are combined in the DICOM images’ image data and header information. These information are transformed and put in the matrix. The suggested model’s input is obtained from the stored matrix. The suggested model employs many stages of image processing. The procedure begins with pre-processing of the brain MRI pictures, then clusters the white matter (WM), grey matter (GM), and cerebrospinal fluid (CSF), segments the tumour, and categorises the tumour before handling storage of the MRI images. Filtering methods are used on MRI data at the pre-processing stage to get rid of noise and text artefacts. The K-means clustering technique is used to separate the white matter, grey matter, and CSF. With regard to both pixels and edges, the MRI picture is segmented. When it comes to tumour classification, RBF kernel-based SVM ensemble performed better, and SVM ensemble is used to classify brain tumours. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Voice Assisted E-Commerce Website 15

Voice Assisted E-Commerce Website

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Kumar, Gitansh Matharu, Manmeet Kaur Joshi, Gaurank Chauhan, Jatin Kumar, Ankit Department of Computer Science ABES Engineering College Ghaziabad India

ISBN: (纸本)9798331300579

The way humans interact with computers has evolved thanks to automatic voice-controlled devices. Voice or speech recognition systems enable a user to make a hands-free request to the computer, which then processes the request and returns relevant responses to the user. Voice-controlled technologies have become more efficient and are widely implemented in many sectors to enable and improve human-to-human and human-to-computer interactions after years of development and research in machine learning and artificial intelligence. Web-based technologies enable cutting-edge e-commerce applications to provide interactive and user-friendly interfaces. However, in other cases, people, particularly those with visual difficulties, are unable to completely appreciate the utility of such programs. A voice-controlled system embedded in a web application can improve user experience and functionality. In the current corporate environment, e-commerce is on the rise. Using the Internet as an electronic medium, e-commerce systems facilitate the buying and selling of goods. By enabling contact-free interactions between the user and the machine, voice/speech recognition systems greatly simplify the process. Voice recognition has been the subject of a great deal of research up to this point. The user experience and task completion can be improved by utilizing all of these in online apps. This feature will also improve the web app's accessibility because a significant portion of the population suffers from various forms of visual impairments, and it will be especially helpful to them. © Grenze Scientific Society, 2024.

关键词： Speech 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：