检索结果-内蒙古大学图书馆

signal processing, Communications and Engineering Management conference (ISPCEM), International

作者： Zhang You Qian Yi Zhang Yiquan Na Yu Zhao Jundan Yu Ting Hu Yue Lv Peng Engineering Construction Consulting Branch of State Grid Shanghai Electric Power Company Shanghai China Shanghai Power Transmission and Transformation Engineering Co. Ltd. Shanghai China

ISBN: (数字)9798331528676

ISBN: (纸本)9798331528683

this paper proposes a construction risk management method based on multimodal knowledge graph, aiming to improve the risk identification and prediction capabilities in the construction process. the system combines advanced natural language processing (NLP) algorithms, which can automatically extract and integrate construction-related information from multi-source heterogeneous data, and construct a comprehensive knowledge graph covering multimodal data such as text, images, and videos. In terms of algorithm design, an improved NLP model is used to conduct in-depth semantic analysis and association mining of text data, while integrating image recognition and video analysis technologies to achieve all-round data integration and analysis of complex construction scenes. In the system simulation stage, this paper conducts comprehensive verification through a large amount of actual construction data, focusing on evaluating the risk identification and prediction performance of the system in different scenarios. the simulation results show that the accuracy of this method in identifying construction risks has reached more than 95%, and the error rate of predicting construction risks is controlled within 5%, which significantly improves the accuracy and efficiency of construction risk management, fully verifies the practicality and reliability of the system, and provides strong technical support for construction management.

关键词： Accuracy Power transmission signal processing algorithms Knowledge graphs Prediction algorithms Natural language processing Systems simulation Risk management Data mining Videos

来源：评论

学校读者我要写书评

暂无评论

Depression Detection Based on Eeg signals Using Machine Learning Algorithms

Depression Detection Based on Eeg Signals Using Machine Lear...

引用

Sciences and Techniques of Automatic Control and Computer Engineering MI-STA, IEEE International Maghreb Meeting of the conference on

作者： Fatima M. Alneqrat Ali Hussein Maamar Asmaa Nasr Mohammed Hajer A. Aghnaya College of Electronic Technology - Bani Walid

ISBN: (数字)9798350372632

ISBN: (纸本)9798350372649

Depression, a psychological disorder with detrimental effects on an individual's thoughts, actions, and mood, afflicts millions of people. As it has evolved into a serious illness, there is a pressing need for accurate diagnostic methods. this research employs features extracted from EEG signals, utilizing the Discrete wavelet Transform (DWT) algorithm to diagnose depression. Two machine-learning algorithms, Support Vector Machines (SVM) and K-nearest Neighbors (KNN), were employed for classification. the study, conducted using a dataset from Hospital University Sains Malaysia (HUSM), demonstrates the efficacy of this approach. Results indicate that the KNN algorithm achieved a remarkable test accuracy of 99.51 %, while SVM reached 91.18%, both utilizing features derived from the DWT algorithm. these models successfully differentiate between depressed patients and healthy controls with high accuracy rates. In summary, this research highlights the potential of EEG signals as a biomarker for identifying depression, offering significant advancements in diagnosis and treatment approaches for this condition.

关键词： Support vector machines Accuracy Machine learning algorithms signal processing algorithms Nearest neighbor methods Depression Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Proof-of-Concept of Uncompressed 4K Video Transmission from Drone through mmWave

Proof-of-Concept of Uncompressed 4K Video Transmission from ...

引用

Consumer Communications and Networking conference, CCNC IEEE

作者： Yoshitaka Takaku Yohei Kaieda Tao Yu Kei Sakaguchi Tokyo Institute of Technology Japan Intelligent Systems Laboratory SECOM Co. Ltd Tokyo Japan

ISBN: (数字)9781728138930

ISBN: (纸本)9781728138947

Drones are attracting increasing attention in varieties of research fields because of their flexibility and are expected to be applied to a wide range of potential applications, among which the super-high-resolution video surveillance system using drones especially gains the authors' research attention. Surveillance systems using cameras with fixed locations always suffer the blind spots due to the blockage or inappropriate deployments. Instead, by using the drones equipped with cameras, the surveillance performance can be drastically improved due to their high mobilities. the video quality is also a key factor of the surveillance performance. In face recognition, one of the most important surveillance applications, the uncompressed video can greatly improve the detection accuracy, but it is difficult to transmit uncompressed video in real time due to the huge data sizes. To address the issue, we propose to use the ultra-high speed mmWave communication for the video transmission from drones. Moreover, due to the limited battery energy and computing power in drones, we introduce the edge computing and propose to offload all the computation from the drones to the ground station. In addition, a proof-of-concept prototype hardware of the proposed uncompressed 4K video transmission system from drones through mmWave is developed, and the experiments results are consistent with the system design expectations.

关键词： distributed processing face recognition image resolution millimetre wave communication object detection remotely operated vehicles video cameras video signal processing video surveillance drone honey bees Unmanned vehicles video monitoring Distributed processing Video transmission Video signal processing Video cameras image resolution Object detection Facial Recognition

来源：评论

学校读者我要写书评

暂无评论

SYSTEM FOR DISPLAYING FOG DENSITY USING COLOUR MIXING DUE TO LIGHT VEILING

SYSTEM FOR DISPLAYING FOG DENSITY USING COLOUR MIXING DUE TO...

引用

4th Lighting conference of China,Japan and Korea

作者： K.Nakamura H.Nomoto T.Matsumura E.Momma H.Ishii T.Ono NIHON UNIVERSITY

the light veiling phenomenon of light sources in fog occurs because of the diffuse reflections of radiated light caused by fog *** mixing the red and green light veils generated by this phenomenon,the authors constructed a system similar to traffic signal lights in order to display green,yellow,and red light veils based on the level of risk,which corresponds to fog *** study has demonstrated a system that simultaneously measures fog density and changes the displayed colour of light veiling similar to traffic signal *** authors have shown that the range of fog densities that display yellow colour as a warning can be *** addition,the practicability of fog density measurement and display using this system has been clarified.

关键词： LED light source fog density light veiling image processing

来源：评论

学校读者我要写书评

暂无评论

Multimodal Fusion Intelligent Driving Fatigue Monitoring and Warning in Police Traffic Scenarios

Multimodal Fusion Intelligent Driving Fatigue Monitoring and...

引用

signal processing, Communications and Engineering Management conference (ISPCEM), International

作者： Guancheng Chen Long Chen Kaiwen Tan Pinxian Xie School of Criminal Investigation People’s Public Security University of China Beijing China School of Computer Science and Engineering Wuhan University of Engineering Wuhan China School of Traffic Management People’s Public Security University of China Beijing China

ISBN: (数字)9798331528676

ISBN: (纸本)9798331528683

the study presents a multimodal fusion intelligent driving fatigue monitoring and warning system tailored for police traffic scenarios. this system integrates diverse data modalities, including facial expressions, body posture, heart rate, and speech, to achieve comprehensive and precise fatigue detection. Leveraging edge-cloud collaborative computing and infrared image recognition technology, the system operates efficiently across various environmental conditions, enhancing its reliability and stability. the system's adaptability is further demonstrated through its compatibility with different levels of autonomous driving (L1 to L5), offering customized solutions that range from assisted to fully autonomous driving. Specially designed for police operations, the system provides features such as fleet management, equipment integration, and real-time connectivity to command centers, which collectively improve the safety and effectiveness of law enforcement tasks. Compared to traditional single-modality systems, this multimodal approach significantly enhances detection accuracy, stability, and functional diversity, positioning it as a competitive solution for widespread application in both general and specialized driving contexts.

关键词： Heart rate Accuracy Law enforcement image edge detection Collaboration Fatigue Real-time systems Safety Monitoring Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Research on a Hyperplane Decomposition NMF Algorithm Applied to Speech signal Separation 22

Research on a Hyperplane Decomposition NMF Algorithm Applied...

引用

Proceedings of the 2022 4th International conference on Video, signal and image processing

作者： Chaofeng Lan Han Ye Yan Liu Xiaoxia Guo Yulan Han School of Measurement and Communication Engineering Harbin University of Science and Technology China

ISBN: (纸本)9781450397810

Non-negative Matrix Factorization (NMF) solves the single-channel speech separation problem. However, problem solving mostly separates the pure speech signal from the mixed speech signal with noise. this paper proposes an NMF algorithm based on hyperplane decomposition to separate speech for this problem. Based on the NMF algorithm, the observed signal is decomposed into different hyperplanes, a nonlinear mapping between the amplitude of the observed signal and the amplitude of the signal to be separated is constructed, and the speech signal is reconstructed according to the amplitude spectrum of the pure speech signal to realize the separation of the two original speech signals. the correlation coefficients between the reconstructed speech signal and the original speech signal after decomposition into different numbers of hyperplanes are compared and analyzed. the effects of different numbers of hyperplanes on the separation effect of speech signals are discussed. the study shows that when the number of hyperplanes is 20, the similarity coefficient after speech separation is 0.8356, and the separation effect is better. Meanwhile, the algorithm proposed in this paper can obtain more extracted features, which can be used as the training data of deep learning algorithm and provide some technical reference for speech separation.

关键词： Hyperplane decomposition Speech separation NMF algorithm

来源：评论

学校读者我要写书评

暂无评论

Enhancing Facial image Resolution: Leveraging UNET++ for Super-Resolution using Deep Learning

Enhancing Facial Image Resolution: Leveraging UNET++ for Sup...

引用

International conference on Computer and Information Technology (ICCIT)

作者： Asef Jamil Ajwad Sk Tahmed Salim Rafid Saurov Podder Department of Electrical and Electronic Engineering BRAC University Dhaka Bangladesh

this paper presents a novel and robust method for achieving 4X upscaling of facial images, leveraging the UNET++ architecture and applied to the widely recognized Flickr-Faces-HQ (FFHQ) dataset comprising high-resolution 512x512 images. the study systematically explores the performance of four distinct UNET++ model sizes, each offering a unique balance between computational efficiency and upscaling quality. through extensive experimentation, the proposed approach demonstrates remarkable prowess in preserving intricate facial features, enhancing texture details, and maintaining visual realism during the upscaling process. Notably, the best-performing model exhibits an impressive average Peak signal-to-Noise Ratio (PSNR) of 30.465 dB, a Structural Similarity Index (SSIM) of 0.859 and a Multiscale SSIM (MS-SSIM) of 0.976, establishing a new standard of excellence in facial image upscaling. these findings contribute to the advancement of image processing techniques, particularly in the context of facial imagery, and hold profound implications for a wide range of applications, including computer graphics, image enhancement, and face recognition systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DAASPP: Depth-Wise Asymmetric Atrous Spatial Pyramid Pooling for COVID-19 Lesion Segmentation

DAASPP: Depth-Wise Asymmetric Atrous Spatial Pyramid Pooling...

引用

IEEE International conference on signal and image processing applications (ICSIPA)

作者： Siti Raihanah Abdani Syed Mohd Zahid Syed Zainal Ariffin Nursuriati Jamil Shafaf Ibrahim School of Computing Sciences College of Computing Informatics and Mathematics Universiti Teknologi MARA Shah Alam Selangor Malaysia

ISBN: (数字)9798350352368

ISBN: (纸本)9798350352375

Medical image segmentation plays a vital role in automated disease screening and diagnosing systems. One of the diseases that depend on image segmentation output is COVID-19, in which the diseased lesion is informative in order to determine the disease severity. the task of segmenting COVID-19 lesions is a challenging process, not only due to computational costs and hardware limitations but also because of the varying sizes and shapes of the lesions. In this study, we proposed to integrate a multiscale unit, specifically the ASPP, into a base DABNet, resulting in a lightweight module called DAASPP. the addition of a multiscale unit is meant to further improve the network capability in extracting lesion features of various scales so that small-and large-scale lesions can be segmented accurately. there are two variations of DAASPP have been proposed: one with a single-unit ASPP and another network with a dual-unit ASPP. Both variations are placed at the last and second last DABNet blocks due to the availability of complex features at these two layers. Four different scales are explored for each network variation, specifically the 2, 3, 4, and 5 dilated convolution layers. the results showed that DAASPP with a single-unit ASPP and four parallel scale branches demonstrated the best segmentation performance, achieving mean IoU, mean Dice coefficient, and mean accuracy scores of 0.6629, 0.7461, and 0.9991, respectively. this improvement in extracting the lesion regions will help in producing a better diagnosis system of the COVID-19 severity level.

关键词： COVID-19 image segmentation Shape Convolution Feature extraction Hardware Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Approximate Multiplier Using Reordered 4–2 Compressor with OR-based Error Compensation

Approximate Multiplier Using Reordered 4–2 Compressor with ...

引用

International conference on ASIC

作者： Yufeng Xu Yi Guo Shinji Kimura Graduate School of Information Production and System Waseda University Japan

Today, the approximate circuits have become an efficient solution for low power design on human related error-tolerant applications, such as multimedia, recognition and several signal processing. Approximate multipliers are believed to be an important key to make approximate arithmetic systems, and more area efficient multiplier is expected. the paper proposes a new area-efficient 4-2 compressor based on input reordering and OR-based error compensation. By the reordering, we can focus on just 2 of 4 inputs, and the compressor becomes very simple and less gates. Two multipliers are proposed with different accuracy based on reordered compressors with OR-based error compensation. the experimental results show that the proposed multipliers achieve high accuracy (98.7% and 97.39%) while reduce power consumption (by 44.72% and 45.95%) and area (by 31.72% and 34.85%). the proposed approximate multipliers are applied on image sharpening process and show high PSNR and SSIM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

image compression and enlargement algorithms

引用

International Journal of Circuits, Systems and signal processing 2021年 15卷 836-846页

作者： Burova, I.G. Dem’yanovich, Yu.K. Terekhov, A.N. Altynova, A.Yu. Satanovskiy, A.D. Babushkin, A.A. St. Petersburg State University 7/9 Universitetskaya nab St.Petersburg199034 Russia

In some cases, there are problems associated with the compression and enlargement of images. the use of splines is quite effective in some cases. In this paper, a new image compression algorithm is presented. the features of increasing the size of an image when using local polynomial or non-polynomial splines are considered. the main method for enlarging an image is based on the use of splines of the second and third order of approximation. Polynomial and trigonometric splines are considered. To speed up the process of enlarging the image, we used the parallelization techniques. © 2021, North Atlantic University Union NAUN. All rights reserved.

关键词： image compression

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：