检索结果-内蒙古大学图书馆

VireNet-SSD: object detection model for resource-constrained applications based on self-organized operational neural networks

引用

Neural Computing and Applications 2025年第14期37卷 8547-8569页

作者： Kamath, Vidya Renuka, A. Department of Computer Science and Engineering Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal576104 India

Discovering deep learning-based computer vision solutions for use with constrained devices is exceptionally hard, and the trade-offs are often too undermining. Deep learning models are enormous, which makes it challenging to deploy them on constrained platforms. The convolutional neural network is the fundamental framework for majority of the models that are currently in use. However, operational neural networks have recently shown to be a better option to the convolutional equivalents on a variety of tasks due to their heterogeneous nature and greater resemblance to the functioning of biological neurons. The question of whether heterogeneous models could function on constrained devices and be deployed in real time remains a major concern. To address this problem, an object detection model architecture based on a single-shot multi-box detector with self-organized operational neural networks as its backbone was developed, which can perform efficiently on constrained devices such as Raspberry Pi. The resultant backbone architecture was named as VireNet. In contrast to homogeneous conventional deep learning networks that use convolutions, heterogeneous networks were chosen to develop VireNet, which provides a more productive and effective solution. Furthermore, an in-depth explanation of the design space has been provided to aid any future research that is associated with this architectural search. This new approach might mark the very beginning of the use of heterogeneity to address issues on devices with constrained resources. © The Author(s) 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep Learning based Air Quality Forecasting using Satellite Data 6

Deep Learning based Air Quality Forecasting using Satellite ...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Sree, K. Navya Reddy, Mancharla Rakesh Saraswathi, S. Department of Computer Science and Engineering Specialization with AI & ML Sathyabama Institute of Science and Technology Chennai India Department Computer science and engineering Sathyabama Institute of Science and Technology Chennai India

ISBN: (纸本)9798331522667

Air pollution is a significant threat to human health and the environment. Accurate air quality forecasting is essential for effective mitigation strategies, including public health advisories, emission control measures, and policy interventions. This research focuses on the development of an advanced air quality forecasting system using machine learning techniques. The system uses historical data on pollutants such as PM2.5, NO2, and O3, along with meteorological parameters, to predict future air quality levels. The model is enhanced with the inclusion of sophisticated machine learning algorithms to better capture the intricate spatiotemporal patterns and enhance the accuracy of forecasting. The system may potentially provide real-time air quality forecasts that enable proactive measures for protecting public health and inform decisions for environmental policy. This research contributes to sustainable and resilient urban environments by providing valuable insights into air quality dynamics and supporting effective air pollution mitigation strategies. © 2025 IEEE.

关键词： air pollution Air quality forecasts cardiovascular diseases data-driven strategies environmental policy global climate international collaboration machine learning NO2 O3 PM2.5 policy-making pollution mitigation proactive alerts public health real-time monitoring respiratory diseases spatial variability temporal variability transboundary pollution

来源：评论

学校读者我要写书评

暂无评论

Developed a Machine Learning and Deep Learning Model for 5G MIMO Data Based Beam Selection and Intelligent Network Analytics

引用

SN computer science 2025年第3期6卷 1-21页

作者： Ashok, P. Suganya, R. Lekha, P. Pandian, Poornima Subashini, M. Nithya, M. Department of Computer Science and Engineering Sri Sai Ram Institute of Technology Tamilnadu India Department of Computer and Communication Engineering Sri Sai Ram Institute of Technology Tamilnadu India Department of Electronics and Communication Engineering Sri Sairam Engineering College Tamilnadu India Department of Computer Science and Engineering Sri Sairam Engineering College Tamilnadu India

Introduces an innovative application of 5G MIMO data in singular value decomposition (SVD) focusing on deep learning beam-selection and intelligent network analytics. This research explores the potential of leveraging 5G MIMO data to enhance network performance and efficiency through advanced ML techniques. Deep learning algorithms are employed for beam-selection, optimizing the transmission of data in 5G networks to improve throughput and reliability. Intelligent network analytics are applied to extract valuable insights from the vast amount of data generated by 5G MIMO systems, enabling proactive network management and optimization. By harnessing the capabilities of deep learning and intelligent analytics, this research aims to address key challenges in 5G network optimization and management. The integration of SVD techniques with 5G MIMO data offers a novel approach to enhancing network performance, enabling more efficient utilization of resources and improved quality of service for users. The insights gained from intelligent network analytics facilitate informed decision-making and proactive maintenance leading to greater reliability and resilience in 5G networks. This research contributes to the advancement of 5G technology by leveraging ML to unlock the full potential of MIMO data for optimizing network performance and enabling intelligent network management. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： 5G Beam-selection Deep learning Intelligent management MIMO Network analytics Network performance Optimization Proactive maintenance Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Enhancing waste sorting and recycling efficiency: robust deep learning-based approach for classification and detection

引用

Neural Computing and Applications 2025年第6期37卷 4567-4583页

作者： Sayem, Faizul Rakib Islam, Md. Sakib Bin Naznine, Mansura Nashbat, Mohammad Hasan-Zia, Mazhar Kunju, Ali K Ansaruddin Khandakar, Amith Ashraf, Azad Majid, Molla Ehsanul Kashem, Saad Bin Abul Chowdhury, Muhammad E. H. Department of Electrical and Electronic Engineering University of Dhaka Dhaka Bangladesh Department of Biomedical Engineering Military Institute of Science and Technology Dhaka Bangladesh Department of Computer Science & Engineering Rajshahi University of Engineering & Technology Rajshahi6204 Bangladesh Chemical Engineering Department University of Doha for Science and Technology Doha Qatar Department of Electrical Engineering Qatar University Doha2713 Qatar Computer Applications Department Academic Bridge Program Qatar Foundation Doha Qatar Department of Computing Science AFG College With the University of Aberdeen Doha Qatar

Given the severity of waste pollution as a major environmental concern, intelligent and sustainable waste management is becoming increasingly crucial in both developed and developing countries. The material composition and volume of urban solid waste are key considerations in processing, managing, and utilizing city waste. Deep learning technologies have emerged as viable solutions to address waste management issues by reducing labor costs and automating complex tasks. However, the limited number of trash image categories and the inadequacy of existing datasets have constrained the proper evaluation of machine learning model performance across a large number of waste classes. In this paper, we present robust waste image classification and object detection studies using deep learning models, utilizing 28 distinct recyclable categories of waste images comprising a total of 10,406 images. For the waste classification task, we proposed a novel dual-stream network that outperformed several state-of-the-art models, achieving an overall classification accuracy of 83.11%. Additionally, we introduced the GELAN-E (generalized efficient layer aggregation network) model for waste object detection tasks, obtaining a mean average precision (mAP50) of 63%, surpassing other state-of-the-art detection models. These advancements demonstrate significant progress in the field of intelligent waste management, paving the way for more efficient and effective solutions. © The Author(s) 2024.

关键词： Deep learning for waste management Intelligent waste management Object detection in waste management Sustainable waste processing Urban solid waste Waste image classification

来源：评论

学校读者我要写书评

暂无评论

On DNA Synthesis Using Shortmers and the Capacity of Non-Deterministic Costly Constrained Graphs

引用

IEEE Transactions on Information Theory 2025年第4期71卷 2397-2442页

作者： Abu-Sini, Maria Lenz, Andreas Technion—Israel Institute of Technology Department of Computer Science Haifa32000 Israel Technical University of Munich Department of Computer Engineering Munich80333 Germany Technical University of Munich Institute for Communications Engineering Munich80333 Germany

In conventional DNA synthesis machines, usually many strands are synthesized in parallel by iterating through a supersequence s and adding in each cycle the next nucleotide to a programmable subset of the strands. The length of s determines the number of the cycles, hence the time and the cost of the synthesis process. Recently, in order to reduce the number of synthesis cycles, researchers have suggested to append in each cycle a shortmer, i.e., a sequence of nucleotides, instead of a single one. The present work studies this synthesis technique from a theoretical point of view. In particular, it discusses which shortmers are the best to use (in order to reduce the number of cycles), and how to calculate the number of cycles required to synthesize in parallel a set of strands using a given set of shormers. Lastly, and following a previously described connection between the DNA synthesis problem and costly constrained graphs, this paper investigates calculating the capacity of non-deterministic costly constrained graphs. © 1963-2012 IEEE.

关键词： Markov chains

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based knowledge-aware semantic communications for remote driving image transmission

引用

Digital Communications and Networks 2025年第2期11卷 317-325页

作者： Yangfei Lin Tutomu Murase Yusheng Ji Wugedele Bao Lei Zhong Jie Li Department of Computer and Network Engineering University of Electro-Communications Information Technology Center Nagoya University National Institute of Informatics(NII) Hohhot Minzu College Toyota Motor Corporation Department of Computer Science and Engineering Shanghai Jiaotong University

Remote driving, an emergent technology enabling remote operations of vehicles, presents a significant challenge in transmitting large volumes of image data to a central server. This requirement outpaces the capacity of traditional communication methods. To tackle this, we propose a novel framework using semantic communications, through a region of interest semantic segmentation method, to reduce the communication costs by transmitting meaningful semantic information rather than bit-wise data. To solve the knowledge base inconsistencies inherent in semantic communications, we introduce a blockchain-based edge-assisted system for managing diverse and geographically varied semantic segmentation knowledge bases. This system not only ensures the security of data through the tamper-resistant nature of blockchain but also leverages edge computing for efficient management. Additionally, the implementation of blockchain sharding handles differentiated knowledge bases for various tasks, thus boosting overall blockchain efficiency. Experimental results show a great reduction in latency by sharding and an increase in model accuracy, confirming our framework's effectiveness.

关键词： Semantic communication Remote driving Semantic segmentation Blockchain Knowledge base management

来源：评论

学校读者我要写书评

暂无评论

Adopting Graph Neural Networks to Understand and Reason About Dynamic Driving Scenarios

IEEE Open Journal of Intelligent Transportation Systems

引用

IEEE Open Journal of Intelligent Transportation Systems 2025年 6卷 579-589页

作者： Su, Peng Xiang, Conglei Chen, Dejiu KTH Royal Institute of Technology Faculty of Engineering Design Department Stockholm100 44 Sweden KTH Royal Institute of Technology Electrical Engineering and Computer Science School Stockholm100 44 Sweden

With advances in Deep Neural Networks (DNN), Automated Driving Systems (ADS) enable the vehicle to perceive their surroundings in dynamic driving scenarios and perform behaviors by collecting operational data from sensors such as LiDAR and cameras. Current DNN typically detect objects by analyzing and classifying unstructured data (e.g., image data), providing critical information for ADS planning and decision-making. However, advanced ADS, particularly those required to perform the Dynamic Driving Task (DDT) autonomously, are expected to understand driving scenarios across various Operational Design Domains (ODD). This capability requires the support for a continuous comprehension of driving scenarios according to operational data collected by sensors. This paper presents a framework that adopts Graph Neural Networks (GNN) to describe and reason about dynamic driving scenarios via analyzing graph-based data based on collected sensor inputs. We first construct the graph-based data using a meta-path, which defines various interactions among different traffic participants. Next, we propose a design of GNN to support both the classification of the node types of objects and predicting relationships between objects. As results, the performance of the proposed method shows significant improvements compared to the baseline method. Specifically, the accuracy of node classification increases from 0.77 to 0.85, while that of relationships prediction rises from 0.74 to 0.82. To further utilize graph-based data constructed from dynamic driving scenarios, the proposed framework supports reasoning about operational risks by analyzing the observed nodes and relationships in the graph-based data. As a result, the model achieves a MRR of 0.78 in operational risks reasoning. To evaluate the practicality of the proposed framework in real-world systems, we also conduct a real-time performance evaluation by measuring the average process time and the Worst Case Execution Time (WCET). Com

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Extraction of road using semi-supervised deep learning method 4th

Extraction of road using semi-supervised deep learning metho...

引用

4th International Conference on Computational Methods in science and technology, ICCMST 2024

作者： Mishra, Jalaj Khan, Mohd Jawed Negi, Himanshi Alam, Jitendra Alam, Junaid Singh, Pankaj Pratap Department of Computer Science & Engineering Greater Noida Institute of Technology Greater Noida India Department of Computer Science & Engineering Central Institute of Technology Assam Kokrajhar India

ISBN: (纸本)9781032911571

Detection of road networks using high-resolution aerial or remote sensing imagery constitutes a significant focus within modern research efforts. Currently, deep learning models demonstrate efficiency to a certain degree, they are constrained by a notable reliance on annotated datasets, a practice divergent from optimal methodologies due to the scarcity of extensive, high-quality labeled data. The precision of road prediction is additionally influenced by the latent information embedded within pixels exhibiting diminished confidence values. These pixels play a crucial role in discriminating between road and non-road regions within the images, yet their utilization by deep learning models is suboptimal. To handle these two different issues, opted U-Net as our base model with a sole generator paired with twin dis-criminators and presented this combined setup of U-Net on the Generative Adversarial Network (GAN). At the base of the U-Net architecture, a bottleneck module is incorporated to augment the functionalities of the proposed model. This proposed model attains 98% accuracy on DeepGlobe Road Dataset. Comparative and quantitative assessment demonstrates the enhanced efficiency of our model compared to similar methodologies. © 2025 the Author(s).

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A Framework for Flood Disaster Detection From Remote Sensing Images Using Spatiotemporal Fusion With Digital Twin technology

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年 18卷 11547-11560页

作者： Lim, Se-Jung Sankaran, K. Sakthidasan Haldorai, Anandakumar Chonnam National University School of Electrical and Computer Engineering Yeosu Campus Yeosu-si59626 Korea Republic of Hindustan Institute of Technology and Science Department of Electronics and Communication Engineering Chennai603103 India Sri Eshwar College of Engineering Department of Computer Science and Engineering Coimbatore641202 India

Flood is regarded as common disaster which could cause serious devastation in any country. Typically, it is caused due to precipitation & river runoffs, specifically at the time of excessive rainfall season. The technology of sensor network has been used to monitor changes in landcovers and water level fluctuations. Moreover, effective disaster monitoring & notification system in real-time becomes a crucial part which needs to be overcome. For this reason, the proposed methodology is designed aiming at developing natural disaster prediction and monitoring system for alerting that aids in offering right decision at right time. At first, remote sensing image data are collected and preprocessed using Frequency Ratio and Multi-collinearity test (MCT) to ensure noise removal and image augmentation by enhancing their quality. A feature extraction process is carried with the use of Deep Convolution VGGNet-16 from which optimal features are selected using Improved Harris Hawks Optimization algorithm (IHHOA). Then, a Flexible Spatio-temporal image fusion (F-SPTF) approach is employed to fuse images. After this, Deep cascaded RNN classifier is employed for predicting flood occurrence and to map flood susceptibility areas. This, in turn, classifies the normal and abnormal condition of flood occurrence thus giving alerts in case of natural disaster occurrences which could be visualized through digital twin technologies. The suggested scheme offers an accuracy rate of about (99.89%), precision (99.37%), recall (99.82%), and F1-score (99.74%). The error rates estimated like RMSE (0.784), MAE (0.764), and MAPE (0.102) also seems to be lower than other existing models compared. © 2008-2012 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

An Initial Risk Assessment for Multimodal with LSTM-Based Trust Evaluation Framework for Autonomous Vehicle Security

引用

SN computer science 2025年第2期6卷 1-15页

作者： Renjith, P.N. Balasubramani, S. Ramesh, K. Patnala, Eswar School of Computer Science and Engineering Vellore Institute of Technology Chennai Campus Chennai India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India Department of Computer Science and Engineering Sri Krishna College of Engineering and Technology Coimbatore India

This research aims to develop a new approach to increase the safety and reliability of Autonomous Vehicle (AV) through the proposed risk assessment framework, supported by the trust evaluation approach derived from a machine learning algorithm. This work proposes a comprehensive risk assessment model with real-time sensor data, Vehicle-to-Vehicle (V2V), key communication reliability, environmental cognition, and Improved Long Short-Term Memory (I-LSTM). This framework is multidimensional compared to most conventional models, focusing primarily on assessing individual threat factors. Here, the machine learning portion is designed to evaluate and predict trust by quickly processing vast amounts of information from sensors, signals, and prior operation history. Such an approach to trust assessment enables the system to continuously evaluate the dependability of automated vehicle operation and identify threats to security with improved accuracy. The effectiveness of the performance of this method is substantiated by a number of stand-alone and live scenarios, where the model's performance is higher in perceiving possible risks, avoiding threats, and enhancing safety than the conventional approaches. The findings suggest that the safety regulations of the AVs will be improved by using a multi-dimensional risk assessment model and integrating the I-LSTM trust rating with 95.5% accuracy, 96.7% risk identification, and 180 ms response time. This will cause AV and its surrounding environment to be accepted by the public and used on the roads. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Autonomous vehicles LSTM model Machine learning Risk assessment Trust evaluation

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：