检索结果-内蒙古大学图书馆

A Dangerous Driving Behavior Detection Method Based on Improved YOLOv8s

engineering Letters 2025年第3期33卷 721-731页

作者： Zhou, Tong Zhang, Xiaoxia Chen, Huilong School of Computer Science and Software Engineering University of Science and Technology LiaoNing Anshan114051 China

Detecting dangerous driving behavior is a critical research area focused on identifying and preventing actions that could lead to traffic accidents, such as smoking, drinking, yawning, and drowsiness, through technical methods. Advanced computer vision and machine learning technologies enable efficient detection models to monitor and analyze driver behavior, improving road safety. Due to challenges posed by complex environments, this paper introduces an enhanced detection algorithm, YOLOv8s-CDS, to improve the identification of dangerous driving behaviors. First, the ConvNeXt V2 module is integrated with the C2f module to form C2fNeb2, optimizing feature extraction for behaviors like smoking or phone use. Second, the DASI (Dimension-Aware Selective Integration) module enhances detection accuracy through multi-scale fusion and dimension perception. Additionally, the SCConv module replaces the Conv module in the Bottleneck, forming C2fSCConv, which reduces spatial redundancy and improves detection efficiency.A comprehensive experimental analysis of dangerous driving image datasets demonstrates that the mean average precision (mAP) of the YOLOv8s-CDS algorithm is 91.20%, which is 2.4% higher than that of the YOLOv8s algorithm. Compared to other object detection algorithms, such as Faster R-CNN, YOLOv5s, YOLOv7s, YOLOX and YOLOv8, YOLOv8s-CDS demonstrates greater practicality in detecting dangerous driving behaviors, contributing to a reduction in traffic accidents and enhancing the safety of life and property. © 2025, International Association of Engineers. All rights reserved.

关键词： Highway accidents

来源：评论

学校读者我要写书评

暂无评论

FDM-RTDETR: A Multi-Scale Small Target Detection Algorithm

引用

IEEE Access 2025年 13卷 88747-88761页

作者： Wang, Hongya Yu, Yongtao Tang, Zhaoxia Huaiyin Institute of Technology Faculty of Computer and Software Engineering Jiangsu Huaian223003 China

To address challenges in uncrewed aerial vehicles (UAV) object detection including complex backgrounds, severe occlusion, dense small objects, and varying lighting conditions, we propose FDM-DETR, a novel detection algorithm specifically designed for small objects in UAV imagery. This method effectively captures global image information by fusing multi-scale spatial features and performing feature extraction in the frequency domain within the backbone network. We design a Dynamic Feature Interaction (DIFI) module with position-based biases in the encoder, enhancing the model’s perception of local features for small objects. In the neck network, we introduce a Multi-Scale Feature Enhancement Pyramid (MSFEP) module to improve feature extraction capabilities for small object detection. Compared to RT-DETR, our improved model achieves performance gains of 2.5% and 2.7% in AP on the Vis-Drone2019 validation and test sets, respectively. While maintaining low computational complexity and parameter count, the method demonstrates significant improvements in detection performance. FDM-DETR exhibits robust practicality and reliability in UAV-based small object detection tasks. © 2013 IEEE.

关键词： Target drones

来源：评论

学校读者我要写书评

暂无评论

Novel design of a sentiment based stock market index forecasting system

引用

Soft Computing 2024年第20期28卷 12081-12095页

作者： Roy, Partha Depatment of Computer Science and Engineering Bhilai Institute of Technology Durg India

This article proposes a novel idea for creating a sentiment-based stock market index forecasting model by amalgamating price and sentiment data hidden in the price pattern itself. The state-of-the-art methodologies used in forecasting stock markets involve gathering sentiment data from external sources like tweets, but the proposed model is unique in the sense it extracts the sentiment information from the price itself, making it more reliable and easier to test and implement. In the proposed system the simple daily time series is converted to an information enriched fuzzy linguistic time series with a unique approach of incorporating information about the sentiment behind the Open High Low Close (OHLC) price formation that took place at every instance of the time series. A unique approach is followed while modeling the information retrieval (IR) system which converts a simple IR system it into a forecasting system. A number of experiments were conducted using the proposed model on Nifty-50 index values (5 years) and it was found that the Root Mean Squared Error (RMSE) value came around 1.03 and RMSE% came around 1.72% which is quite small compared to number of observations and hence this gives a strong indication that the proposed system has the capability to perform good quality of forecasts. The model is simple and easy to implement with very nominal memory requirements, compared to other type of models. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

DLP4DA-RPL: A Distributed Lightweight Protocol for Detection and Avoidance of Discarded DIO and DAO Attacks on RPL Routing Protocol in IoT

引用

IEEE Sensors Journal 2025年第12期25卷 22880-22894页

作者： Deepavathi, P. Mala, C. Department of Computer Science and Engineering National Institute of Technology Tiruchirappalli 620015 India

The Internet of Things (IoT) occupies the entire world in its hands. IoT devices have a resource-constrained nature known as Low Power and Lossy Networks (LLN). The Routing Protocol for Low Power and Lossy Networks (RPL) is provided by the Internet engineering Task Force (IETF) group to secure the IoT networks. The control messages Destination Oriented Directed Acyclic Graph (DODAG) Information Object (DIO) and DODAG Advertisement Object (DAO) play a crucial part in RPL. Attackers focused on these control messages to degrade the performance of IoT networks and slowly bring them to a halt. To overcome these problems, this paper proposes a DLP4DA-RPL protocol to detect and avoid Discarded DIO (DDIO) and Discarded DAO (DDAO) control message attacks. The Contiki operating system simulates this proposed protocol using the Cooja simulator and this proposed protocol is implemented in our college environment. It is inferred from the simulation and real-time results that the proposed DLP4DA-RPL protocol outperforms the existing RPL protocols, such as RPL with Attacks, RPL without Attacks, SecTrust-RPL, and DDoS-RPL concerning End-to-end Delay, Energy Consumption, Packet Delivery Ratio, Throughput and Network Performance. © 2025 IEEE.

关键词： Routing protocols

来源：评论

学校读者我要写书评

暂无评论

The Improved Unet Semantic Segmentation Network for Remote Sensing Images

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2025年第4期52卷 1187-1195页

作者： Zhu, Hang Zhao, Ji School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China

With the development of artificial intelligence, deep learning has been increasingly used to achieve automatic detection of geographic information, replacing manual interpretation and improving efficiency. However, remote sensing images themselves have the issue of slight inter-class variance and significant intra-class variance, making it challenging to extract valuable information. Additionally, the increasing resolution and size of remote sensing images in recent years have introduced more complexity in the types of information, further increasing the difficulty of extracting valuable data. This paper proposes an improved Unet semantic segmentation network (referred to as RAUnet). First, in the encoder, continuous convolutional blocks are enhanced to extract features. At the same time, the EMAM multi-scale attention module is employed for cross-channel learning, capturing information from different feature channels of the target and using the surrounding feature information to assist in distinguishing target information. To capture multi-directional long-range dependencies, the Lo2 module is used for long-range modeling, which captures not only local contextual information but also long-range dependencies. In the decoder, a Dysample upsampling module is used to restore feature details, and in the skip connection layer, features are added for feature fusion. Experimental results show that compared to mainstream models, the proposed method achieves superior segmentation results on the Potsdam and Vihingen datasets. © (2025), (International Association of Engineers). All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Explainable AI for Pancreatic Cancer Prediction and Survival Prognosis: An Interpretable Deep Learning and Machine Learning Approach

引用

Informatica (Slovenia) 2024年第4期48卷 623-640页

作者： Srinidhi, B. Bhargavi, M.S. Department of Computer Science and Engineering Bangalore Institute of Technology Bengaluru India

Pancreatic cancer's devastating impact and low survival rates call for improved detection methods. While Artificial Intelligence has shown remarkable progress, its increasing complexity has led to "black box" models, hindering their acceptance in critical fields like healthcare. To address this, Explainable Artificial Intelligence (XAI) has gained traction, aiming to create transparent AI systems. In this study, we propose a comprehensive approach that combines the power of Deep Learning for pancreatic cancer detection using Computed Tomography (CT) images and Machine Learning (ML) for survival prognosis based on clinical data. By leveraging CT images with Deep learning models such as Convolutional Neural Networks, VGG-16 and DenseNet-201, effective diagnosis of Pancreatic Cancer is achieved and comprehensive insights into the tumor's spatial characteristics are obtained. DenseNet-201 outperformed the other models in terms of accuracy and interpretability with a predictive accuracy of 95%. The integration of ML techniques such as Stochastic Gradient Descent, Naïve Bayes and Extra Tree classifiers with clinical data predicts the chances of survival, providing vital information for treatment planning and personalized care. To validate the model's accuracy and interpretability, a comprehensive XAI validation is conducted using state-of-the-art techniques like Local Interpretable Model-agnostic Explanations and Shapley Additive Explanations. These methods provide localized explanations for predictions, allowing clinicians to understand risk and survival chances. This study holds immense potential to aid healthcare professionals in diagnosis, prognosis, and personalized treatment strategies, contributing to enhanced patient outcomes in the fight against pancreatic cancer. © 2024 Slovene Society Informatika. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Sentimental Analysis for Trump Tweets Using R 8th

Sentimental Analysis for Trump Tweets Using R

引用

8th International Conference on Information System Design and Intelligent Applications, ISDIA 2024

作者： Nishok, V.G. Bharathi, N. Department of Computer Science and Engineering Faculty of Engineering and Technology SRM Institute of Science and Technology Vadapalani Campus Chennai India

ISBN: (纸本)9789819786657

Twitter is the best source for sentiment analysis, product reviews, current issues, etc. Sentiment analysis extracts positive and negative opinions from the Twitter data set, and R studio provides the best environment for this Twitter sentiment analysis. Find if Trump’s phone Android is fake or not by comparing his iPhone and Android tweets using R with datasets. Detailed analysis is not there. The Twitter data collected might not be representative of the entire population. By using filtering of tweets as we need Android and iPhone tweets here and usage of tweets per day, no of tweets with and without quotes and pictures and links, taking common words from Android and iPhone and trying with log ratio that is Android /iPhone and with log ratio and common word find sentiment. We got good results by the usage of Twitter of each device, no of tweets quoted and non-quoted, no picture/link and picture/link, most common words, words compare with Android and iPhone and log ratio, finding sentiment of it which type of word it is. My work helps his account is a trump or not for Android as it contains negative tweets by common words, Android and iPhone words and log odd ratio with that it detects sentiment as it is a positive, negative or neutral by showing anger, sad, happy, etc. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Developing a tool for assessing classroom healthiness in Egyptian primary schools

引用

HBRC Journal 2025年第1期21卷 17-41页

作者： Raafat Makram, Hadeer Dewidar, Khaled Mohamed Abdel-Razek, Shahira Assem Guirguis, Marianne Nabil Department of Architectural Engineering Faculty of Engineering Delta University for Science and Technology Gamasa Egypt Department of Architectural Engineering Faculty of Engineering Ain Shams University Cairo Egypt Architectural Engineering Department Faculty of Engineering The British University in Egypt Cairo Egypt

Ensuring a healthy indoor classroom environment is essential for supporting student health, comfort, and academic performance. However, most existing environmental assessment tools evaluate entire buildings rather than addressing the unique conditions of individual classrooms. To bridge this gap, this study introduces the Classroom Healthiness Assessment Tool for IEQ (CHAT: IEQ), a novel, classroom-specific framework for assessing indoor environmental quality (IEQ) and overall healthiness. CHAT: IEQ evaluates six key IEQ dimensions: thermal comfort, air quality, lighting quality, sound quality, view quality, and spatial quality. It integrates 60 key performance indicators (KPIs) across 24 assessment criteria, systematically derived and benchmarked against national and international standards, expert insights, and existing rating systems. The tool generates a quantitative "overall healthiness value," enabling precise identification of environmental deficiencies. Applied to nine Egyptian primary classrooms, the assessment uncovered significant IEQ disparities, identifying critical health risks and areas for improvement. As a practical decision-making resource, CHAT: IEQ supports evidence-based interventions and guiding renovation and retrofitting efforts. This study highlights the pressing need for targeted strategies to create healthier, more comfortable, and academically supportive classrooms for young learners. By addressing specific classroom challenges and improving environmental conditions, CHAT: IEQ offers a valuable tool for enhancing student well-being and optimizing learning environments. It also contributes to ongoing efforts in improving public health in educational spaces, particularly in regions with limited resources. © 2025 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

New insights on thermal ageing of electrical insulating oils as revealed from photoluminescence and absorption spectroscopy

引用

High Voltage 2024年第5期9卷 1033-1045页

作者： Hesham S.Karaman Eman G.Atiya Diaa-Eldin A.Mansour Mohsen Ghali Z.M.S.Elbarbary Manal M.Emara Department of Electrical Engineering Faculty of Engineering at ShoubraBenha UniversityCairoEgypt Department of Electrical Power and Machines Engineering Faculty of EngineeringTanta UniversityTantaEgypt Department of Electrical Power Engineering Faculty of EngineeringEgypt-Japan University of Science and Technology(E-JUST)New Borg El-Arab CityAlexandriaEgypt Department of Energy Materials Institute of Basic and Applied ScienceEgypt-Japan University of Science and Technology(E-JUST)New Borg El-Arab CityAlexandriaEgypt Department of Physics Faculty of ScienceKafrelsheikh UniversityKafrelsheikhEgypt Department of Electrical Engineering College of EngineeringKing Khalid UniversityAbhaSaudi Arabia Center for Engineering and Technology Innovations King Khalid UniversityAbhaSaudi Arabia Department of Electrical Engineering Faculty of EngineeringKafrelsheikh UniversityKafrelsheikhEgypt

Recently,significant efforts have been exerted to replace mineral oil with environmentally friendly oils due to safety and environmental ***,there is a need to clarify the physical mechanisms behind the ageing impact of these *** authors use advanced optical spectroscopy techniques in correlation with dielectric measurements to understand the ageing processes in environmentally friendly oils as well as mineral ***,different samples of environmentally friendly oils and mineral oil were utilised to investigate the ageing *** samples were subjected to different ageing periods using a thermal accelerated ageing ***,the severity of the produced byproducts due to the oil degradation is examined based on several measured properties representing macroscopic and microscopic *** macroscopic category was evaluated through dielectric properties,including breakdown voltage,dielectric permittivity,and dissipation *** microscopic category,on the other hand,was assessed using techniques such as ultraviolet-visible absorption spectroscopy and photoluminescence *** techniques enabled a deep understanding of the molecular-level changes occurring in the oil under ageing conditions,thereby getting new insights into oil ageing *** is worth mentioning that natural ester oil demonstrated the most favourable performance across various properties under ageing conditions.

关键词： absorption thermal spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Efficient 3D Tracking and Detection of Multi-Rotor UAVs Using mmWave Radar with Semi-Supervised Learning

引用

IEEE Sensors Journal 2025年第12期25卷 22001-22014页

作者： Xi, Rui Wei, Wenjie Zhang, Malu University of Electronic Science and Technology of China Department of Computer Science and Engineering Chengdu611731 China

Small UAVs pose security risks to sensitive areas and individuals due to their rapid movement and wide coverage capabilities. Effective monitoring necessitates the deployment of lightweight and energy-efficient surveillance systems. This research introduces an efficient 3D tracking and detection approach for small UAVs, utilizing millimeter-wave radars and Spiking Neural Networks (SNNs). By capturing micro-Doppler characteristics of UAV movements, it effectively processes low signal-to-noise ratios and uncertain signals. An improved angle estimation algorithm, combining dynamic programming and particle filters, enables realtime 3D UAV tracking with reduced computational complexity. Then, a simple UAV detection model based on SNN architecture is developed by leveraging UAVs’ position and corresponding Doppler information. Furthermore, a bio-inspired semi-supervised method is proposed to facilitate the training of SNNs using a limited number of annotated samples. The effectiveness of the proposed methodology is evaluated under various environmental conditions. Results indicate a significant improvement in tracking computation time efficiency, with the recognition model size reduced to one-tenth of its original size, yet it maintains near-original system performance. © 2001-2012 IEEE.

关键词： Semi-supervised learning

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：