检索结果-内蒙古大学图书馆

2024 International Conference on Electrical, Electronics and Computing Technologies, ICEECT 2024

作者： Survase, Sanket Diwan, Raman Lal, Kumari Nidhi Kumar, Shishupal VNIT Nagpur Dept. of Computer Science and Engineering Nagpur India IIIT Nagpur Dept. of Computer Science and Engineering Nagpur India

ISBN: (纸本)9798350378092

The emergence of 5G technology has ushered in a new era of connectivity, making communications faster and cheaper. One of the main challenges of 5G networks is accuracy and efficiency, which are important for many applications such as driver less cars, smart cities and virtual reality. This research paper explores the integration of machine learning techniques to improve the accuracy and reliability of 5G infrastructure. The plan uses rich data generated by 5G networks, combining various parameters such as signal strength, flight time and angle of arrival. Machine learning algorithms are used to process this data and create good models for the correct location. The system is designed to adapt to dynamic and complex urban environments where traditional methods often encounter limitations. The main contribution of this research includes the development of a new machine learning-based distribution algorithm suitable for 5G networks, a comprehensive evaluation of performance comparison with the existing system, and evaluation of recommendations for feasibility and implementation. The results showed significant improvements in accuracy and reliability, demonstrating the potential of machine learning to revolutionize the 5G workplace. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Automated Exam Script Checking using Zero-Shot LLM and Adaptive Generative AI

Automated Exam Script Checking using Zero-Shot LLM and Adapt...

引用

2024 IEEE International Conference on Computing, Applications and systems, COMPAS 2024

作者： Himi, Shinthi Tasnim Tanzila Monalisa, Natasha Sultana, Shirin Afrin, Anika Hasib, Khan Md Bangladesh University of Business and Technology Dept. of Computer Science and Engineering Dhaka Bangladesh Jahangirnagar University Dept. of Computer Science and Engineering Dhaka Bangladesh Brac University Dept. of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798331529765

The manual grading of exam scripts is a labor-intensive process, often plagued by subjectivity and inconsistency. This study presents an innovative approach to automating the evaluation of exam scripts using the Large Language Model (LLM) integrated with Zero-Shot Learning (ZSL) and Generative AI. Our system leverages the capabilities of GPT-4 to generate and evaluate answers, applying similarity measures to ensure accuracy and fairness in grading. The model's adaptability through ZSL allows it to assess new questions without additional training. The system also incorporates iterative refinement techniques to enhance the quality of standard answers over time. Performance evaluations demonstrate a low error rate, with an average relative error of 1.29% for annotated questions and 1.67% for non-annotated questions compared to human graders. The performance underscores the automated system's transformative potential in revolutionizing educational assessments, offering a consistent, fair, and highly efficient alternative to traditional grading methods. © 2024 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing 5G Efficiency: Regression Analysis for Resource Allocation Optimization in Wireless Networks

Enhancing 5G Efficiency: Regression Analysis for Resource Al...

引用

2024 International Conference on Electrical, Electronics and Computing Technologies, ICEECT 2024

作者： Padmageetha, B.G. Kumar Naik, Pramod Patil, Mallanagouda Dayananda Sagar University Dept. of Computer Applications Bengaluru India Dayananda Sagar University Dept. of Computer Science and Engineering Bengaluru India RVITM Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350378092

The advent of 5G networks signifies a major breakthrough in mobile communications, providing better data rates, low latency, and improved connectivity. Efficient resource allocation within 5G networks is paramount to fully leverage these capabilities, ensuring optimal performance and user satisfaction. Traditional resource allocation methods often struggle to keep pace with the dynamic and complex nature of 5G environments. The potential benefits of machine learning (ML) is explored in this research to enhance resource allocation in 5G networks. We begin by examining the unique challenges posed by 5G networks, by ML approaches employed for resource allocation, including supervised learning such as Trees, SVM, Neural Networks. Our study we train the model using MATLAB simulator. Analysis on the response and residual plot is conducted for predicted response. Analysis and comparative study is made to find the best performance metric suitable for the predicting the model for resource allocation. The study shows the improvisation in the metrics of regression learner. Simulation results demonstrate significant improvements in network performance. Finally, we have done the comparison between the results of MATLAB simulation. This study gives better decisions to service providers to enhance the overall performance of network © 2024 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Activity Recognition from Channel State Information for Few-Sampled Scenarios

Activity Recognition from Channel State Information for Few-...

引用

2023 IEEE Globecom Workshops, GC Wkshps 2023

作者： Diaz, Guillermo Sobron, Iker Eizmendi, Iñaki Landa, Iratxe Velez, Manuel Dept. of Communications Engineering Bilbao Spain Dept. of Computer Languages and Systems Bilbao Spain

ISBN: (纸本)9798350370218

Human Activity Recognition (HAR) using channel state information (CSI) from wireless systems has been a field in progress for the last few years. In particular, amplitudes of WiFi-based CSI have been widely used for HAR in indoor scenarios. In contrast, CSI phases are less exploited due to higher sensitivity to timing errors in channel estimation. This paper further explores a recent phase processing method to obtain environmental information from CSI and improves classification using a Convolutional Neural Network in few-sampled scenarios. For this purpose, a new dataset has been generated with measurements of three receivers on different days and with different people, for activity recognition and people counting. In addition, we incorporate a transfer learning strategy using fine-tuning along with a data fusion model from different receivers to improve accuracy metrics by training the model and validating it on data taken on different days. Promising results with accuracies higher than 80 % have been obtained with transfer learning between days using 5 % of data for fine-tuning. © 2023 IEEE.

关键词： activity recognition CSI few-shot learning fine-tuning people counting phase

来源：评论

学校读者我要写书评

暂无评论

Deformable Convolution Based Road Scene Semantic Segmentation of Fisheye Images in Autonomous Driving 26

Deformable Convolution Based Road Scene Semantic Segmentatio...

引用

26th Irish Machine Vision and Image Processing Conference, IMVIP 2024

作者： Manzoor, Anam Singh, Aryan Sistu, Ganesh Mohandas, Reenu Grua, Eoin Scanlan, Anthony Eising, Ciarán Data-Driven Computer Engineering Group Dept. of Electronic and Computer Engineering University of Limerick Ireland

ISBN: (纸本)9781837242672

This study investigates the effectiveness of modern Deformable Convolutional Neural Networks (DCNNs) for semantic segmentation tasks, particularly in autonomous driving scenarios with fisheye images. These images, providing a wide field of view, pose unique challenges for extracting spatial and geometric information due to dynamic changes in object attributes. Our experiments focus on segmenting the WoodScape fisheye image dataset into ten distinct classes, assessing the Deformable Networks' ability to capture intricate spatial relationships and improve segmentation accuracy. Additionally, we explore different loss functions to address class imbalance issues and compare the performance of conventional CNN architectures with Deformable Convolution-based CNNs, including Vanilla U-Net and Residual U-Net architectures. The significant improvement in mIoU score resulting from integrating Deformable CNNs demonstrates their effectiveness in handling the geometric distortions present in fisheye imagery, exceeding the performance of traditional CNN architectures. This underscores the significant role of Deformable convolution in enhancing semantic segmentation performance for fisheye imagery. © This is an open access article published by the IET under the Creative Commons Attribution License (http://***/licenses/by/3.0/)

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

An In-dept. Exploration of Advanced Driver Drowsiness Detection systems for Enhanced Road Safety 2

An In-Depth Exploration of Advanced Driver Drowsiness Detect...

引用

2nd International Conference on computer, Communication and Control, IC4 2024

作者： Abirami, A. Bhuvaneswari, S. Vishnuvardhan, M. Karthik, Yadam Shankar, Saisuraj Easwari Engineering College Dept. of Computer Science and Engineering Chennai India Student of Easwari Engineering College Dept. of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350387933

Drowsiness, among drivers, plays a role in causing road accidents leading to loss of life, injuries, and financial setbacks. To address the issue of driver fatigue related accidents it is crucial to develop methods for detecting driver fatigue. This survey paper presents an overview of approaches used to identify driver fatigue. These approaches can be grouped into three categories: Behavioural, Vehicular and Physiological parameters. Behavioural parameters, such as eye closure percentage, blink rate patterns, yawning, head movements and facial expressions offer intrusive techniques that examine the physical state of the driver's body and provide information about their drowsiness level. Vehicular parameter-based techniques evaluate drowsiness by observing vehicle behaviour such as lane deviations, pedal usage, and unpredictable steering movements. Physiological indicators are also employed to detect tiredness. The paper also discusses the methodology employed in the research study including image processing techniques classifiers used and measurement metrics utilized, proposed methodology of fatigue detection with adding some extra features and Lastly the paper presents conclusions based on a study that can guide future researchers in identifying potential areas for further exploration in this field. © 2024 IEEE.

关键词： Physiological models

来源：评论

学校读者我要写书评

暂无评论

Evaluation of the Economic Viability and Sustainability of Renewable Energy using Building Integrated Photovoltaics in an Urban Apartment Complex

引用

Transactions of the Korean Institute of Electrical Engineers 2024年第3期73卷 508-515页

作者： Gong, Youngmin Kim, Insu Dept. of Electrical Engineering Inha University Korea Republic of Department of Electrical and Computer Engineering Inha University Korea Republic of

In order to cope with the current climate crisis, reducing greenhouse gas emissions is an important issue, and it is necessary to increase the amount of renewable energy generation. However, there is a problem of economics in renewable energy, and in the case of the Republic of Korea, there is a problem of geographical mismatch between the supply and demand of renewable energy. This study proposes building integrated photovoltaics (BIPV) as a way to solve the problems associated with renewable energy. In this study, a model for charging an electric bus by the power generated by building integrated photovoltaics was proposed, evaluated and analyzed. The results show that BIPV can generate revenue of KRW 39.9 billion over 30 years and can contribute to increasing the amount of renewable energy generation in Seoul by accounting for 1.85% of the annual solar power generation in Seoul. © 2024 Korean Institute of Electrical Engineers. All rights reserved.

关键词： Solar power generation

来源：评论

学校读者我要写书评

暂无评论

Smart Agritech : An Enhanced Solution for Advanced Plant Disease Detection, Remediation, and Data-Driven Agriculture 2

Smart Agritech : An Enhanced Solution for Advanced Plant Dis...

引用

2nd IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2024

作者： Rekha, K.S. Haridas, Aakash Dept. of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350360523

Plant diseases can have a detrimental effect on crop yield and quality, posing significant challenges to global food security. Early and accurate disease detection is essential for timely intervention and mitigation. In this study, we propose a novel approach for plant disease detection using a deep learning method based on a state-of-the-art convolutional neural network, ResNet9 architecture. The ResNet9 model is trained on a diverse dataset of plant images, including both healthy and diseased plants, representing different plant species and diseases. Our method leverages the power of deep learning to automatically learn discriminative features from plant images, enabling it to distinguish between healthy and diseased plants with a high degree of accuracy. We evaluate the performance of our model on a real-world dataset of plant images, and the results demonstrate its effectiveness in disease detection. The model achieves a high accuracy rate, indicating its potential for field deployment to assist farmers in monitoring and managing plant health. In conclusion, our study presents a promising solution for automated plant disease detection, providing farmers and agronomists with a practical tool to identify and combat plant diseases early, ultimately contributing to improving crop productivity and food security. © 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

Remote Multi-Robot Control and Management Based on a Kubernetes Cluster

引用

Journal of Institute of Control, Robotics and systems 2023年第2期29卷 161-167页

作者： Gu, Sewan Yoon, Dongweon Dept. of Electronics and Computer Engineering Hanyang University Korea Republic of Dept. of Electronic Engineering Hanyang University Korea Republic of

This paper proposes a method to remotely control and manage a Kubernetes-based multi-robot swarm efficiently while ensuring high availability of the robots’ internal controller modules. We evaluate the effectiveness of the proposed approach by experimenting with a self-balancing robot and robot arm. Each robot is configured as a worker node in a Kubernetes cluster. A master node is configured to remotely monitor their statuses and manage the cluster by running, stopping, and updating the controller module. We also develop a labeling module to automate the process of imprinting labels on all the robots in the cluster according to their hardware, software, and functions. A control module required for each robot is automatically deployed remotely, and the appropriate module for robot is selected when the control module is deployed. Furthermore, we experimentally evaluate a control feature designed to ensure high resource availability and fault tolerance. The Kubernetes system is configured to detect problems with the controllers of the self-balancing robots and to create new pods to solve these problems automatically. Our results demonstrate that multi-robots can be controlled simultaneously using an existing cloud-computing container-orchestration system. © ICROS 2023.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Integrated IoT and Machine Learning Solutions for Precision Farming: Crop Recommendation and Leaf Disease Diagnosis 8

Integrated IoT and Machine Learning Solutions for Precision ...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Harish, M. Devi, J. Vimala Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350376425

The digital convergence of the Internet of Things and machine learning has therefore redefined precision agriculture with respect to productivity and sustainability. This work therefore proposes a smart agriculture system via the following IoT sensors: Soil Moisture, DHT, and NPK sensors, along with data storage in ThingSpeak cloud *** Similarly, farmers learn which plants are best to grow based on their projected data from machine learning algorithms. A convolutional neural network named ResNet was used for its control to instantly and correctly identify plant diseases in live mode. For the system's front end, HTML, CSS, and JavaScript were used while Python facilitated creation of the back end that provides users with an easy-to-use interface. It has achieved high accuracy levels in crop recommendation through models like Decision Tree, Naive Bayes, SVM, Logistic Regression, Random Forest and XGBoost among others have attained an accuracy of 90%, 99.09%, 97.95%, 95.27%, 99.09% and 99.31% respectively in crop recommendation. By ResNet model in the identification of leaf disease, a density of 99.2% was achieved. © 2024 IEEE.

关键词： Smart agriculture

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：