检索结果-内蒙古大学图书馆

3rd International Conference on Artificial Intelligence and Knowledge processing, AIKP 2023

ISBN: (纸本)9783031686160

The proceedings contain 28 papers. The special focus in this conference is on Artificial Intelligence and Knowledge processing. The topics include: How Do Senior Secondary Level Students and Their Teachers Perceive Artificial Intelligence and Its Implementation? An Exploratory Study;anomalous Sound Pattern Detection for Machine Health Monitoring;performance Evaluation of Various Machine learning Algorithms for Lung Cancer Prediction Using Demographic Data;enhancing Stock Portfolio Optimization Based on a Hybrid Approach Using Artificial Bee Colony Optimization and Firefly Optimization;Enhancing Yarn Quality in the Cotton Industry: AI- Based Nep Detection for Improved Manufacturing Processes;breast Cancer Diagnosis from Ultrasonic image and Histopathology image Using deep learning Approach;Advancing time Series Forecasting: LSTM Networks with Multiple Attention Mechanisms;trajectory Tracking and Navigation Model for Autonomous Vehicles Using Reinforcement learning;quantum Graph Neural Networks Based Protein-Ligand Classification;comparative Analysis on Speech Driven Gesture Generation;enhancing deep learning: Leveraging Skip Connections and Memory Efficiency;quality-Based Decision-Making Using image processing for Supply Chain Management;enhancing Endometrial Tumor Detection: Early Diagnosis with Advanced Vision Transformer Architecture;sweetSight: A deep Convolutional Neural Network Approach for Automatic Categorization of Bengal Sweets;a Systematic Review: How Computer Vision is Transforming Agriculture in Economic Growth;automatic Conversion of Broadcasted Football Match Recordings to Its 2D Top View;measuring the Vehicle-in-Motion, Density and Allocation of Traffic Signal Using Transfer learning;Ensemble Model of VGG16, ResNet50, and DenseNet121 for Human Identification Through Gait Features;Performance of Sentiment Analysis APIs on Political Opinion Polling;summarization of Telugu Text Discourses;crowd-Sourced Supervisors for the Automatic Invigilation of Online

关键词：

来源：评论

学校读者我要写书评

暂无评论

Joint Reliability Optimization and Beamforming Design for STAR-RIS-Aided Multi-User MISO URLLC Systems

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2024年第6期73卷 8041-8054页

作者： Wang, Lei Ai, Bo Niu, Yong Zhong, Zhangdui Han, Zhu Wang, Ning Beijing Jiaotong Univ Sch Elect & Informat Engn Beijing 100044 Peoples R China Beijing Jiaotong Univ Beijing Engn Res Ctr High Speed Railway Broadband Beijing 100044 Peoples R China Beijing Jiaotong Univ Sch Elect & Informat Engn Beijing 100044 Peoples R China Res Ctr Networks & Commun Peng Cheng Lab Shenzhen 518055 Peoples R China Zhengzhou Univ Henan Joint Int Res Lab Intelligent Networking & D Zhengzhou 450001 Peoples R China Univ Houston Dept Elect & Comp Engn Houston TX USA Southeast Univ Natl Mobile Commun Res Lab Nanjing 211189 Peoples R China Univ Houston Dept Elect & Comp Engn Houston TX 77004 USA Kyung Hee Univ Dept Comp Sci & Engn Seoul 446701 South Korea Zhengzhou Univ Sch Informat Engn Zhengzhou 450001 Peoples R China

Simultaneous transmitting and reflecting reconfigurable intelligent surfaces (STAR-RISs) are capable of serving users on both sides of it at the same time through active and intelligent control of space electromagnetic waves, and are therefore considered to be a powerful means to facilitate the design of ultra-reliable low-latency communication (URLLC) systems. In this paper, we investigate the joint reliability optimization and beamforming design problem for a STAR-RIS-assisted multi-user multiple-input single-output (MISO) URLLC system in an industrial IoT scenario. A system sum-rate maximization problem is formulated, subject to the STAR-RIS amplitude and phase shift constraints, power and reliability constraints. To solve this problem, we design a joint optimization algorithm based on deep reinforcement learning. The algorithm determines the optimal access point transmit precoding matrix, STAR-RIS reflection- and transmission-coefficient matrices, and the packet error probabilities for actuators based on the channel state information (CSI). On this account, the proposed algorithm dynamically tunes the STAR-RIS to make the optimal beam response for real-time channel changes. Comprehensive simulation results demonstrate that the proposed algorithm can provide substantial performance benefits over several baseline schemes. Moreover, the actual channel model with channel estimation error is also considered for reliability to evaluate the impact of imperfect CSI on system performance.

关键词： Reliability Array signal processing Ultra reliable low latency communication Reliability engineering Actuators Optimization MISO communication Beamforming design deep reinforcement learning simultaneous transmitting and reflecting reconfigurable intelligent surface ultra-reliable low-latency communication

来源：评论

学校读者我要写书评

暂无评论

A compact CNN approach for drone localisation in autonomous drone racing

引用

JOURNAL OF real-time image processing 2022年第1期19卷 73-86页

作者： Cocoma-Ortega, J. Arturo Martinez-Carranza, J. Inst Nacl Astrofis Optic Elect INAOE Cholula Mexico Univ Bristol Bristol Avon England

In autonomous drone racing, a drone flies through a gate track at high speed. Some solutions involve the use of camera localisation to control the drone. However, effective localisation is very demanding in processing time, which may compromise the flight speed. To address the latter, we propose a deep learning-based method for camera localisation that processes a small sequence of images of the scene at high-frequency operation. Our solution is a compact convolutional neural network based on the Inception network that uses a sequence of grey-scale images rather than colour images as input;we have called this network 'GreySeqNet'. Our approach aims at leveraging the localisation process using a small stack of consecutive images fed as input to the network. To save computational effort, we explore the use of grey images instead of colour images, thus saving convolutional layers. We have conducted experiments in a simulated environment to measure the performance of GreySeqNet in different race tracks with variations in gate's height and position. According to the results obtained in several test runs, our method achieves a camera pose estimation at an average operation frequency of 83 Hz running on GPU and 26 Hz on CPU, with an average camera pose error of 31 cm.

关键词： Grey-scale image deep learning Camera localisation Autonomous drone racing

来源：评论

学校读者我要写书评

暂无评论

Addressing challenges in accurate brain tumor classification in MRI: a transfer learning approach with EfficientNetB3 and comprehensive model evaluation

引用

Multimedia Tools and Applications 2024年 1-31页

作者： Das, Surajit Goswami, Rajat Subhra Department of Computer Science and Engineering National Institute of Technology Arunachal Pradesh Arunachal Pradesh Jote791113 India

Brain tumors pose significant health risks because of uncontrolled and abnormal cell growth, potentially leading to the devastating of certain organs and even death, mostly in adult populations. So, early and precise brain tumor classification (BTC) is essential, as a timely diagnosis directly impacts the efficacy of treatment and the survival rates of patients. Magnetic Resonance Imaging (MRI) is the preferred diagnostic tool for BTC due to its superior image quality, yet manual classification methods have the disadvantage of being time-consuming and labour-intensive. The maturity of deep learning (DL) in modern times has brought remarkable progress in automating complex processes across multiple domains, including transfer learning (TL) in medical imaging. In our study, we propose an approach to partially automate the BTC task through the application of transfer learning on MRI data. After applying image pre-processing techniques like cropping, enhancement and Augmentation, we tested six architectures - EfficientNetB6, EfficientNetB3, VGG19, NASNetLarge, DenseNet169 and DenseNet201. Our experiments on a comprehensive publicly available kaggle dataset show that the EfficientNetB3 model achieved the best performance, with a training accuracy of 100% and test accuracy of 99.62%, outperforming all other architectures. EfficientNetB6 demonstrated a similar accuracy of 99.62%, while DenseNet201 and NASNetLarge performed well, with accuracies of 99.24% and 99.08%, respectively. VGG19, although a popular baseline model, achieved a lower accuracy of 94.96%. These findings suggest that EfficientNetB3, alongside other advanced architectures, offers a robust and accurate solution for brain tumor classification in MRI, paving the way for more reliable and efficient diagnostic tools in clinical settings. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

A novel lightweight multi-scale feature fusion segmentation algorithm for real-time cervical lesion screening

引用

SCIENTIFIC REPORTS 2025年第1期15卷 1-12页

作者： Yang, Jiahui Zhang, Ying Fan, Wenlong Wang, Jie Zhang, Xinhe Liu, Chunhui Liu, Shuang Xue, Linyan Hebei Univ Coll Qual & Tech Supervis Baoding 071002 Peoples R China Hebei Univ Affiliated Hosp Baoding 071000 Peoples R China Hebei Univ Sci Res & Innovat Team Baoding 071002 Peoples R China Hebei Univ Natl & Local Joint Engn Res Ctr Metrol Instrument Baoding 071002 Peoples R China Hebei Univ Hebei Technol Innovat Ctr Lightweight New Energy V Baoding 071002 Peoples R China

AI-based cervical lesion segmentation in colposcopy images has significant potential in improving screening efficiency and accuracy. However, most current cervical lesion segmentation algorithms are insufficient for rapid image segmentation in mass screening due to heavy parameters and complex framework. Therefore, a lightweight algorithm segmentation for cervical lesion real-time screening system is urgently needed. In this paper, a novel lightweight LSIL + region segmentation framework termed Light-MDDNet is proposed and deployed, which uses the encoder-decoder architecture. In encoder stage, the first layer of MobileNetV2 module outputs shallow features which tend to be lost during multi-layer feature extraction. We also utilize the Denseaspp module to extract deeper semantic information. In the decoder stage, a multi-scale feature fusion (MFF) module is used to fuse multi-scale features. Finally, the algorithm is deployed and tested on the JETSON ORIN NX edge device in cervical lesion segmentation screening system. The experiments on 971 LSIL + colposcopy images of lesions processed with acetic acid show that our proposed model outperforms some state-of-the-art segmentation networks, with a pixel mean pixel accuracy (MPA) of 94.96% and an average speed per image of 19.60ms. After deployment on the mobile terminal, the segmentation accuracy of the model almost unchanged and the interference speed reduces to 31.57ms per image. The Light-MDDNet network achieves the best balance of accuracy and speed in cervical lesion segmentation, showing great potential for the deployment in the mass screening of cervical lesion.

关键词： Colposcopy images image segmentation deep learning Lightweight

来源：评论

学校读者我要写书评

暂无评论

Advanced deep learning For real time Cardiac image Analysis In Heart Disease Assessment 9

Advanced Deep Learning For Real Time Cardiac Image Analysis ...

引用

9th IEEE International Conference on Smart Structures and Systems, ICSSS 2023

作者： Sujay, V. Nivedita, V. Rama Prabha, K.P. Celine Kavida, A. Sujatha, V. Jyothi Prasad, M. Krishna University College of Engineering and Technology Department of Computer Science and Engineering Andhra Pradesh Machilipatnam India Srm Institute of Science and Technology Department of Computer Science and Engineering Ramapuram Tamil Nadu Chennai India Vellore Institute of Technology School of Computer Science and Engineering Tamil Nadu Chennai India Veltech Multitech Dr Rangarajan Dr. Sakunthala Engineering College Department of Physics Chennai India Vellore Institute of Technology School of Advanced Sciences Department of Mathematics Tamil Nadu Vellore India Rmd Engineering College Department of Electronics and Communication Engineering Tamilnadu Chennai India

ISBN: (纸本)9798350384208

This study introduces an innovative methodology for real-time cardiac image processing with the purpose of diagnosing heart issues. To achieve this, employ cutting-edge deep learning techniques. Given the escalating incidence of cardiovascular diseases, there exists an urgent requirement for state-of-the-art technologies that can enhance the accuracy of diagnoses and accelerate the duration of assessments. The proposed methodology utilizes an internally developed deep neural network architecture for real-time evaluation of cardiac images. The proposed method has demonstrated superior performance in broad testing and analysis across multiple datasets when compared to state-of-the-art alternatives. The findings indicate that the model is capable of performing the critical evaluations necessary for prompt action. This study makes a substantial contribution to the dynamic field of cardiac image processing by presenting a pragmatic approach to enhancing diagnostic accuracy and expediting clinical decision-making in the evaluation of cardiovascular conditions. © 2023 IEEE.

关键词： Heart

来源：评论

学校读者我要写书评

暂无评论

Enhancing 5G Network Throughput Using Reinforcement learning

Enhancing 5G Network Throughput Using Reinforcement Learning

引用

2024 IEEE International Conference on Communication, Computing and Signal processing, IICCCS 2024

作者： Adnan, Myasar Mundher Farkhodjonovich, Muydinov Firuzjon Shrivastava, Rohit Bhandari, Anika Aravind, A.R. Sandeep Kumar, S. The Islamic University College Of Technical Engineering Department Of Computers Techniques Engineering Najaf Iraq The Islamic University Of Al Diwaniyah College Of Technical Engineering Department Of Computers Techniques Engineering Al Diwaniyah Iraq Fergana Medical Institute Of Public Health Head Of Educational and Methodological Department Fergana Uzbekistan Ies College of Technology Department of Electronics & Communication Engineering M.P. Bhopal India Chandigarh Group of Colleges Chandigarh Engineering College Department of Computer Application Punjab Mohali India Prince Shri Venkateshwara Padmavathy Engineering College Chennai India Department of Computer and Communication Engineering Karnataka Udupi India

ISBN: (纸本)9798350390759

In this research, RL is proposed as a solution towards achieving the dynamic optimization of 5G network throughput hindered by the complexity of Intersystems environments. To this extent, the optimization problem is formulated and modeled within the framework of Markov Decision Process and the study resorts to techniques from deep Reinforcement learning leading to the design of adaptive algorithms that optimise various network parameters in real-time. It uses simulated raw 5G network data and other data open for public usage for training it and the application itself is coded in Python programming language with TensorFlow for implementing different algorithms. As for the performance, it could be seen that the RL-optimized approach is superior to traditional methods and leads to better system performance in terms of throughput, latency, energy efficiency and user satisfaction in a number of scenarios. The study identifies the possibility to apply RL to enable the learning capability of 5G networks in supporting new services and optimizing the network performance. This research finding can be beneficial for the advancement of 5G wireless communication technology by demonstrating the versatility and advantages of utilizing RL in the network. © 2024 IEEE.

关键词： deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Advancements in Machine learning for Anomaly Detection in Cyber Security 1

引用

1st International Conference on Intelligent Computing and Big Data Analytics

作者： Dey, Niladri Sekhar deepika, R. Tekuri, Karthik Sanjana, Unyala BV Raju Inst Technol Dept AI&DS Narsapur Telangana India

ISBN: (数字)9783031746826

ISBN: (纸本)9783031746819;9783031746826

The growth of complex cyber threats has spurred the investigation and development of creative approaches in anomaly detection within the area of cybersecurity. Machine learning has become a crucial technique in strengthening digital defenses against changing cyber threats due to its capacity to identify patterns and abnormalities in large datasets. This study digs into the improvements in machine learning algorithms geared particularly for anomaly identification in cybersecurity applications. Anomaly detection strategies span a broad range of methodologies, including both classic statistical approaches and more complex deep learning models. This study investigates the development of machine learning methods, emphasizing their advantages, constraints, and uses in identifying abnormal behaviors in intricate network settings. These models are highly effective in capturing complex patterns and subtle details found in cybersecurity datasets, allowing for the detection of previously unidentified risks and abnormalities with improved accuracy. In addition, the use of ensemble learning methods, such as random forests and gradient boosting machines, has enhanced the strength and scalability of anomaly detection systems. This work highlights a comprehensive analysis of various machine learning methods and anomaly detection algorithms in cybersecurity applications. It reveals that random forests achieve the highest detection accuracy at 95.2%, closely followed by gradient boosting at 94.8%. Moreover, random forests and neural networks exhibit the most effective performance in reducing false alarms, with false positive rates of 2.1% and 2.9% respectively. In terms of computing efficiency, random forests demonstrate the shortest processing time at 15.7 milliseconds, followed by neural networks at 17.9 milliseconds. While random forests and neural networks prove highly scalable, with excellent real-time performance and resilience to adversarial attacks, other models such as suppo

关键词： Machine learning Anomaly Detection Cybersecurity deep learning Ensemble learning Feature Engineering

来源：评论

学校读者我要写书评

暂无评论

Efficient Feature learning Based Xception CNN Model Optimization for MRI Brain Tumor image Classification

引用

TRAITEMENT DU SIGNAL 2025年第1期42卷 277-289页

作者： Nasreen, Shaik Balasubramanian, Prakash Badarudeen, Saleena Rashid, Mamoon Alshamrani, Sultan S. Wahab, Aisha Banu Alghamdi, Ahmed Saeed Madanapalle Inst Technol & Sci Dept Comp Sci & Technol Madanapalle 517325 India Vellore Inst Technol Sch Comp Sci & Engn Chennai 600127 India Bahrain Polytech Sch Informat Commun & Technol Isa Town 33349 Bahrain Taif Univ Coll Comp & Informat Technol Dept Informat Technol Taif 21944 Saudi Arabia BS Abdur Rahman Crescent Inst Sci & Technol Dept Comp Sci & Engn Chennai 600048 India Taif Univ Coll Comp & Informat Technol Dept Comp Engn Taif 21994 Saudi Arabia

Brain tumors are abnormal growths of brain cells that can be benign (non-tumor) or malignant (tumor). These tumors can arise from different types of brain cells and occur in various brain regions. timely detection is crucial for reducing the severity and improving prognosis. However, the traditional human examination suffers in early tumor detection due to the irregular patterns in MRI scans. Additionally, Machine learning and deep learning- based frameworks detect brain tumors more accurately than human analysis. This work introduces an efficient diagnostic approach with improved accuracy to classify the benign and malignant from MRI scans. This diagnostic approach consists of three levels. In the first level, the majority and minority samples are increased to train the framework with more subjects using imageDataGenerator with real-time data augmentation. In the second level, a pre-trained Convolution Neural Network (CNN), namely the Xception framework, is utilized to learn comprehensive information about images. The hyperparameter tuning process improves the multi-class classification accuracy in the third level. The proposed framework classifies brain tumors into multiple such as glioma, meningioma, no tumor, and pituitary. The experimental dataset is obtained from the Kaggle repository to train the framework. The outcomes attained by the proposed framework deliberate higher accuracy compared with other CNN frameworks. The proposed framework proves its efficiency in the fine-grained classification of brain tumors with a validation accuracy of 99.87%. Thus, this framework may be employed in clinical services to diagnose brain MRI tumors.

关键词： brain tumor Xception model imageDataGenerator Convolution Neural hyperparameter tuning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Dietary Monitoring using deep learning: Food Recognition and Calorie Estimation 15

Enhancing Dietary Monitoring using Deep Learning: Food Recog...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Suneela, M. Sahithi, Mandadi Vamsi, Nuthalapati Naik, Nunsavathu Balaji Chowdary, Narra Sujitha Vignan's Lara Institute of Technology & Science College Dept. of Computer Science & Engineering Guntur India

ISBN: (纸本)9798350370249

The project 'Enhancing Dietary Monitoring Using deep learning:Food Recognition And Calorie Estimation' introduces an innovative method aimed at improving dietary tracking and fostering healthier eating habits. By employing cutting-edge deep learning techniques, its core objective is to precisely identify various food items and rapidly estimate their caloric content, offering users advanced and personalized monitoring capabilities. Utilizing the Python programming language alongside the MobileNet architecture model, the project underwent rigorous training and evaluation using the expansive Food 101 dataset, comprising 37,046 food images distributed across 101 distinct classes. Notably, the model demonstrated exceptional performance, achieving a training accuracy of 97.02% and a validation accuracy of 98.17%, highlighting the efficacy of this approach in accurately categorizing a wide array of food items. This system provides users with several crucial functionalities. Furthermore, it furnishes users with essential insights by estimating the caloric content of recognized foods, facilitating effective monitoring of dietary intake. The intelligent diet monitoring capabilities enabled by Food Recognition and Calorie Estimation empower users to make informed choices regarding their dietary preferences. Through the continuous tracking and analysis of their daily food consumption, users can glean valuable insights into their nutritional habits, set personalized goals, and make necessary adjustments to achieve a well-balanced and healthy diet. Enhancing Dietary Monitoring Using deep learning:Food Recognition And Calorie Estimation stands as a prominent illustration of successful implementation of deep learning techniques, particularly with the utilization of the MobileNet architecture, for food recognition and calorie estimation. With its remarkable accuracy, real-time processing capabilities, and intelligent monitoring features, this project has the potential to revolutioni

关键词： Convolutional Neural Network (CNN) algorithm Datasets MobileNet architecture Web application

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：