检索结果-内蒙古大学图书馆

Cognitive Computing and Complex Data (ICCD), International Conference on the

作者： Hui Zong Yun Zhao Heng Zhou Le Zhang Faculty of Computer and Software Engineering Huaiyin Institute Of Technology Huaian China

Chemical accident news data encompasses essential information such as news headlines, news content, and news sources, with the context of news content playing a crucial role. To enhance the accuracy of text feature extraction and improve the efficiency of chemical accident news classification, this paper introduces a feature fusion-based classification approach. The proposed model employs a multi-layer convolutional neural network (CNN) to extract local features from the text of chemical accident news. Additionally, a Bidirectional Long Short-Term Memory (BiLSTM) network is utilized to capture global features, supplemented by the integration of a Self-Attention mechanism behind the BiLSTM network to assign weights to the features and reduce noise. The local and global features are then fused to enrich the semantic information. Furthermore, the feature fusion information undergoes maximum pooling and average pooling to reduce dimensionality and enhance the training speed. Finally, the information is fed into a Softmax layer for classification. Experimental results demonstrate that the proposed neural network model, namely ABLSACNN (Add-CNN-BiLSTM-Self-Attention), outperforms the CNN-Self-Attention model. The ABLSACNN model exhibits an improvement of1.59% in accuracy, 2.46% in recall rate, and 1.93% in F1 score on the chemical accident news dataset, thereby showcasing its superiority.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Techniques in Mobile Edge Computing for Internet of Medical Things 3

Deep Learning Techniques in Mobile Edge Computing for Intern...

引用

3rd International Conference on Emerging Smart Technologies and Applications, eSmarTA 2023

作者： Alawadhi, Abdulwadood Ahmad, R. Badlishah Almogahed, Abdullah Abrar, Ahmad Department of Computers and Information Technology Yemen Universiti Malaysia Perlis Faculty of Electronic Engineering and Technology Perlis Malaysia Universiti Tun Hussein Onn Malaysia Faculty of Computer Science and Information Technology Johor Parit Raja Malaysia School of Computing Universiti Utara Malaysia InterNetWorks Research Laboratory Sintok-Kedah Malaysia

ISBN: (纸本)9798350305333

The fast expansion of the Internet of Medical Things (IoMT) has resulted in a ubiquitous home health diagnostic network. High patient demand results in high costs, short latency, and communication overload. As a result, 6G is the next generation of IoT, IoMT, and cellular networks, intending to considerably improve the quality of smart healthcare services through high throughput and decreased latency. So far, adopting cloud computing for time-critical applications and decreasing access delays to resources is difficult. Deep learning has been extensively employed to extract characteristics from complicated networks as artificial intelligence technology has advanced. On the other hand, deep learning models are often run in cloud computing data centres with tremendous processing resources. Conventional cloud computing systems primarily rely on the network, which has significant latency and security and privacy issues. One of the successful solutions is the Mobile Edge Computing (MEC) paradigm, which brings cloud computing services closer to the edge network and uses available resources. Mobile edge computing places computer and storage nodes near mobile devices at the Internet's edge, leading to considerable savings in system operating time, memory cost, and power usage. Deep learning is used in mobile edge computing to forecast changes in demand based on daily patient behaviours. It also prepares the network by scaling up network resources as required. This study aims to discuss IoMT and identfy the problems in deep learning for mobile edge computing technology and its applications. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Detecting Academic Fraud at Online Tests During COVID-19 Using Machine Learning-Based Methods 1

引用

1st International Conference on Digital Transformation in Education and Artificial Intelligence Applications, MoStart 2023

作者： Volarić, Tomislav Martinović, Goran Ljubić, Hrvoje University of Mostar Trg hrvatskih velikana 1 Mostar Bosnia and Herzegovina Faculty of Electrical Engineering Computer Science and Information Technology Josip Juraj Strossmayer University of Osijek Osijek Croatia

ISBN: (数字)9783031368332

ISBN: (纸本)9783031368325

The first step in eliminating academic dishonesty (in e-learning systems) is to detect fraudulent activities. There are various approaches that deal with this problem, but only few of them are based on human-computer interaction (HCI). Accordingly, we have developed a novel data acquisition model that collects information about student HCI activities. This model was applied within an open-source module, named Student Activity Tracker, available as chromium web browser extension. During the COVID-19 pandemic (in academic year of 2019/2020.), an experiment was conducted with 54 volunteer participants that performed online tests from home. As a result, 500k raw logs were collected and later processed and used to develop four machine learning models. The main contribution of this research is the proof of an obvious correlation between HCI activities and fraudulent behaviour even on such a small sample. Also, we believe that this module can help other researchers to create new data sets and build new more advanced models. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Two-Stage Isolated Dc-Dc Converter, Including Interleaved Buck and Llc Converters, with Low Switching and Conduction Losses

SSRN

引用

SSRN 2023年

作者： Kolagar, Arash Dehestani Khakbaz, Hamed Pahlavani, Mohammad Reza Alizadeh Faculty of Electrical & Computer Engineering Malek Ashtar University of Technology Iran

In this paper, the design and implementation of an isolated DC-DC converter with a two-stage structure is proposed. In the first stage, a regulated interleaved buck DC-DC converter (IBC) is used, and in the second stage, an unregulated full-bridge LLC resonant isolated converter with series-parallel transformers is applied. The converter control method includes fixed-frequency pulse width modulation (PWM) peak current-mode (PCM) for the interleaved buck converter, and the full-bridge LLC resonant converter is controlled with a fixed duty cycle and frequency. Therefore, the LLC converter has the highest gain and efficiency under different load conditions and changes in the input voltage. For the LLC resonant converter, zero voltage switching (ZVS) at turn-on, and zero current switching (ZCS) at turn-off is achieved for all semiconductor power switches. Consequently, switching losses are reduced. In this converter, two identical transformers, with small dimensions, are used instead of one transformer in the conventional LLC resonant converter. The primary winding of these two transformers are connected in series to obtain equal primary current while the secondary windings are in parallel to provide the same secondary voltage. Therefore, the power can be balanced automatically. The series connection can reduce the number of turns in the primary winding and the parallel connection can reduce the current stress of the secondary windings and the conduction losses of the rectifier diodes. In this paper, the principles of operation, steady state analysis and design of the proposed converter have been described and simulated, and finally, in order to confirm the efficiency of the proposed converter, a laboratory set-up with an output power of 1kW, input voltage of 450-650VDC, and an output voltage of 24VDC has been implemented. © 2023, The Authors. All rights reserved.

关键词： Pulse width modulation

来源：评论

学校读者我要写书评

暂无评论

Adversarial Ensemble Learning for Mortality Prediction in Intensive Care Units

Adversarial Ensemble Learning for Mortality Prediction in In...

引用

International Conference on Developments in eSystems engineering (DESE)

作者： Kareem Hameed Khalaf A. Moallemi Khiavi Dhafar Hamed Abd Faculty of electrical and computer engineering University of Tabriz Iran College of Computer Science and Information Technology University of Anbar Ramadi Iraq

ISBN: (数字)9798350368697

ISBN: (纸本)9798350368703

Predicting patient mortality risk in intensive care units (ICUs) is one of the tasks that has strategic significance in improving clinical decisions and health care outcomes. Disease mortality monitoring methods based on machine learning models have shown efficacy; however, their susceptibility to adversarial attacks in the input data presents reliability and robustness challenges. The present work addresses these challenges by introducing an effective ensemble model enriched with adversarial training to increase the performance of mortality prediction models in the ICU context. The developed methodology combines a variety of ensemble methods, such as random forest, extreme gradient boosting, bagging, AdaBoost, extra trees, and the light gradient boosting machine. These approaches work by combining several algorithms and employing adversarial training strategies that put the stakeholder’s data in their correct order and bar data tampering at all points of the model development ecosystem. The set of experiments performed with the help of real ICU datasets proved that this approach provides better accuracy, robustness, and reliability of predictions than standard models do. The extra trees algorithm achieved the best accuracy among the tested models.

关键词： Training Accuracy Biological system modeling Mortality Medical services Predictive models Prediction algorithms Robustness Ensemble learning Random forests

来源：评论

学校读者我要写书评

暂无评论

Safety Helmet Detection Algorithm for Complex Scenarios Based on PConv-YOLOv8

Safety Helmet Detection Algorithm for Complex Scenarios Base...

引用

Cognitive Computing and Complex Data (ICCD), International Conference on the

作者： Yuanyuan Wang Feilong Jiang Yazhou Li Haiyan Zhang Meifeng Wang Shaofeng Yan Faculty of Computer and Software Engineering Huaiyin Institute of Technology Huaian China

Detecting safety helmets in complex environments is challenging due to issues like occlusion and lighting variations. Addressing the issues of slow detection speed and low object detection accuracy in complex environments with the YOLOv8 model, this paper introduces a lightweight safety helmet detection model, called PConv-YOLOv8, that is suitable for real-time applications in complex environments. Our method incorporates the PConv (Partial Convolution) module into the YOLOv8 model, reducing the complexity of the feature extraction network while enhancing feature representation accuracy. It also incorporates SimAM attention to extract and enhance the most relevant features by evaluating their similarity. Additionally, it considers category imbalance and positional regression in the target detection task, enhancing the model’s performance in target category identification and positional localization. Moreover, we propose the Wise-Distribution Focal Loss function to improve bounding box selection accuracy and enhance the model’s robustness. This paper introduces the Wise-Distribution Focal Loss method, which enhances the performance of target category recognition and location localization by improving the accuracy of bounding box selection and increasing the robustness of the overall model. The experimental results demonstrate that the method proposed in this paper achieves a 125% improvement in detection speed and a 1.8% increase in mAP0.5 compared to the YOLOv8 model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Smart Agriculture: Enhancing Crop Management through IoT-Based Real-Time Monitoring and Automation

Smart Agriculture: Enhancing Crop Management through IoT-Bas...

引用

Information technology and Digital Applications (ICITDA), IEEE International Conference on

作者： Hushalictmy Paliyanny Rajermani Thinakaran Somasekar Jalari Vikram Neerugatti Madhusudana Rao Nalluri Ravindra Raman Cholla Faculty of Data Science and Information Technology INTI International University Malaysia Department of Computer Science and Engineering Faculty of Engineering and technology Jain (Deemed-to-be University) Bangalore India Department of Computer Science and Engineering ICFAI Foundation for Higher Education Hyderabad Telangana India

ISBN: (数字)9798331510732

ISBN: (纸本)9798331510749

Internet of Things plays an important role in agriculture in order to provide an innovative and smart solution to traditional farming. IOT is all about connecting physical devices to the internet and can access from a remote place. So that crop monitoring becomes easy even if the farmer is in a remote place. Due to automation, human efforts are required less. Also the IoT data helps the farmer make decisions about planting, harvesting or fertilizing. This paper explains the system we have implemented for monitoring the agriculture with the help of IoT. The system is developed in order to provide real time information on crop conditions to the farmer. For that, it uses various types of sensors connected to the microcontroller in order to measure parameters like temperature, soil moisture, and water level, and accordingly, it activates actuators like a fan, motor or pump to manage ventilation and irrigation. We have used the GSM module to send the alert to the farmer and the WiFi module is used to send the agriculture data to the cloud platform. So that farmer can monitor the farm or crops remotely. The system is continuously collecting farm data from the sensors. If the crop soil is very dry them system will turn on the water pump. Also, for high temperature, the fan will get activated in order to cool down that area. This feature is mostly used in indoor farming. The farmer can monitor the farm condition in real time with the help of cloud platform. This system is helpful for improving productivity, crop management, and save resources i.e. efficient use of water which prevents water wastage.

关键词： Temperature sensors Temperature measurement Fans Soil moisture Crops Real-time systems Water pumps Water resources Monitoring Farming

来源：评论

学校读者我要写书评

暂无评论

Correction to: Automated approach to predict cerebral stroke based on fuzzy inference and convolutional neural network (Multimedia Tools and Applications, (2024), 10.1007/s11042-024-19254-0)

引用

Multimedia Tools and Applications 2024年 1-2页

作者： Alrowais, Fadwa Jamjoom, Arwa A. Karamti, Hanen Umer, Muhammad Alsubai, Shtwai Abate, Andrea F. Ashraf, Imran Department of Computer Sciences College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Department of Information Systems Faculty of Computing and Information Technology King Abdulaziz University Jeddah21589 Saudi Arabia Department of Computer Science The Islamia University of Bahawalpur Bahawalpur Pakistan Department of Computer Science College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz University P.O. Box 151 Al-Kharj11942 Saudi Arabia Department of Computer Science University of Salerno Fisciano84084 Italy Department of Information and Communication Engineering Yeungnam University Gyeongsan38541 Korea Republic of

The original publication of this article contains an error in the affiliation of authors Fadwa Alrowais and Hanen Karamti. Incorrect: Department of Information Systems, College of computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh, 11671, Saudi Arabia Correct: Department of computer Sciences, College of computer and Information Sciences, Princess Nourah Bint Abdulrahman University, P.O. Box 84428, Riyadh, 11671, Saudi Arabia The original article has been corrected. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Creating a Surround View Algorithm with Implementation on a Real Embedded ADAS Platform 32

Creating a Surround View Algorithm with Implementation on a ...

引用

32nd International Conference on Software, Telecommunications and computer Networks, SoftCOM 2024

作者： Marinic, Ivan Vranjes, Mario Grbic, Ratko Herceg, Marijan TTTech Auto d.o.o. Cara Hadrijana 10b Osijek Croatia Faculty of Electrical Engineering Computer Science and Information Technology Osijek Kneza Trpimira 2B Osijek Croatia

ISBN: (纸本)9789532901382

computer Vision (CV) has seen significant advances, and autonomous driving technologies have been transforming the automotive industry in recent years. Autonomous vehicles require robust CV algorithms, while Advanced Driver Assistance Systems (ADAS) help the driver when driving and increase traffic safety. In this paper, the algorithm for generating a Surround View (SV) of the vehicle is proposed and implemented on a real embedded ADAS platform to test its performance in real hardware scenarios. The algorithm implements geometric operations like image distortion correction, perspective transformation, and image stitching to create a comprehensive and connected surround view. The subjective image quality evaluation results showed that the proposed algorithm achieves a fairly high quality of the final top-view image. The experiments also show that its operating speed when running on a real ADAS platform is suitable for cases when the vehicle speed is not high, such as when parking. © 2024 University of Split, FESB.

关键词： Automotive industry

来源：评论

学校读者我要写书评

暂无评论

Robust multi-label classification via data reconstruction by neighborhood samples augmentation

引用

Multimedia Tools and Applications 2024年 1-26页

作者： Liu, Zhifeng Xi, Sitao Abeo, Timothy Apasiba Shen, Xiang-Jun Zhou, Conghua Song, Heping Li, Peiwang School of Computer Science and Communication Engineering JiangSu University Zhenjiang212013 China Faculty of Applied Science and Technology Tamale Technical University Tamale Ghana Jiangsu Yangjing Petrochemical Group Co.Ltd Yangjing China Nanjing University of Posts and Telecommunications Jiangsu Nanjing222000 China

In multi-label learning, traditional methods try to directly establish mapping functions between samples and their labels. However, such methods may suffer low classification performance due to inherent noise and incoherent representation of samples. Therefore, considering the correlation between samples and their neighbors, as they may share common feature semantics, a multi-label classification method via feature enhancement from neighborhood samples, referred to as DRNSA is proposed. In this method, we construct a Laplacian graph dynamically, by considering the distance of two samples in a projected low rank subspace. With this neighborhood selection strategy, we then build a multi-label classifier via feature enhancement from neighborhood samples. Different from past works that directly build classifiers from samples and their labels, we build a new enhanced data sample which is weighted by its semantically similar neighborhood samples. Thus, our method can obtain better robust subspace in very high noisy data representations. Experiments conducted on cal500, corel5k, corel16k1 and corel16k4 datasets, show a significant out-performance of our DRNSA method over multi-label classification methods, including MLSF, MLFE, BR, PLST, CSSP, CPLST, and FaIE. © The Author(s) 2024.

关键词： Noise abatement

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：