检索结果-内蒙古大学图书馆

Research on automatic identification of coal mining subsidence area based on InSAR and time series classification

JOURNAL OF CLEANER PRODUCTION 2024年 470卷

作者： Xu, Jikun Yan, Chaode Boota, Muhammad Waseem Chen, Xuanchi Li, Ziwei Liu, Wangcheng Yan, Xu Zhengzhou Univ Sch Water Conservancy & Transportat Zhengzhou 450001 Peoples R China Zhengzhou Univ Yellow River Lab Zhengzhou 450001 Peoples R China Henan Univ Coll Geog & Environm Sci Kaifeng 475004 Peoples R China Hanshou Cty Nat Land Surveying & Mapping Team Changde 415900 Peoples R China Henan Univ Engn Sch Elect & Informat Engn Zhengzhou 451191 Peoples R China

Large-scale mining of coal resources has caused surface subsidence, threatening the ecological environment and surface safety and hindering the sustainable development of coal resource-based cities seriously. In order to identify coal mining subsidence area more accurately and quickly, a novel method for automatic identification of coal mining subsidence area was proposed in this study, which is based on InSAR technology and time series classification algorithm. The method comprehensively considered the quality of data acquisition and the degree of automation of algorithm implementation, realizing automatic identification of large-space coal mining subsidence area in the case of small samples. Firstly, the unclassified subsidence dataset is constructed by SAR data around time series combined with InSAR technology. Secondly, the degree of change of time series subsidence is used as the basis of classification, and it is divided into two categories: regular type of coal mining subsidence and irregular type of non-coal mining subsidence. Finally, Dynamic Time Warping (dtw) algorithm is used to calculate the similarity distance between the time series curves of each image element of the subsidence dataset to be tested and the standard coal mining subsidence type curves, which aim at identifying the coal mining subsidence area. Through utilizing the multitude filtering algorithm to filter the recognition results, the automatic recognition results of coal mining subsidence area is finally obtained. The results show that this method can still be used to efficiently identify and circle coal mining subsidence area with only 640 samples, and the average Overall Accuracy (OA) and Kappa Coefficient (KC) of coal mining subsidence area are 0.91 and 0.83, respectively. The method can not only identify the existing and potential subsidence area in the mining area, but provide technical support for ecological environment restoration and early warning of subsidence damage.

关键词： Mining subsidence identification Time series classification InSAR Mining subsidence features dtw algorithm

来源：评论

学校读者我要写书评

暂无评论

A New Method for Analyzing Storm Event Discharge-Concentration Hysteresis: The Upper Yangtze River as an Example

引用

WATER RESOURCES RESEARCH 2024年第12期60卷

作者： Xue, Juli Chen, Li Zhang, Wei Yuan, Jing Dong, Bingjiang Wuhan Univ State Key Lab Water Resources Engn & Management Wuhan Peoples R China Changjiang Water Resources Commiss Bur Hydrol Wuhan Peoples R China

The analysis of hydrological and sediment dynamics during flood events offers a new perspective on material transport within basins and the management of rivers. The literature has highlighted the hysteretic nature of material transport at the event scale, which arises from temporal differences in the transport of materials (flow and sediment). Current hysteresis research methods fall short in effectively assessing the complex events. This study leverages suspended-sediment and discharge data from the upper Yangtze River to show proof-of-concept for hysteresis studies using Dynamic Time Warping (dtw) algorithm, a time series analysis tool. To evaluate the efficacy of the method, extensive assessments were undertaken using a combination of synthetic data and basin data with over 700 flood events. The proposed index effectively captures and quantifies hysteresis relationships associated with flood events, making it a versatile tool for hysteresis studies. We also similarly tested the robustness of the method and the application to complex events, and the results were satisfactory. Furthermore, we explored the hysteretic features of flood events in the studied basin. The results revealed that a proportion ranging from 50% to 60% flood events exhibit sediment peak leading pattern, indicating that in the upper Yangtze River, sediment peaks tend to occur in a leading pattern. The operation of reservoirs profoundly impacts the dynamics of sediment transport, resulting in an increased proportion (from 27% to 54%) of sediment peaks lagging behind discharge peaks. These study findings can be used to improve hysteresis study methods and contribute to the understanding of hydrological and sediment transport characteristics.

关键词： hysteresis sediment peak dtw algorithm flood events the Yangtze River basin management

来源：评论

学校读者我要写书评

暂无评论

Predicting Traffic Flow Using Dynamic Spatial-Temporal Graph Convolution Networks

引用

Computers, Materials & Continua 2024年第3期78卷 4343-4361页

作者： Yunchang Liu Fei Wan Chengwu Liang School of Computer and Data Science Henan University of Urban ConstructionPingdingshan467036China School of Electrical and Control Engineering Henan University of Urban ConstructionPingdingshan467036China

Traffic flow prediction plays a key role in the construction of intelligent transportation ***,due to its complex spatio-temporal dependence and its uncertainty,the research becomes very *** of the existing studies are based on graph neural networks that model traffic flow graphs and try to use fixed graph structure to deal with the relationship between ***,due to the time-varying spatial correlation of the traffic network,there is no fixed node relationship,and these methods cannot effectively integrate the temporal and spatial *** paper proposes a novel temporal-spatial dynamic graph convolutional network(TSADGCN).The dynamic time warping algorithm(dtw)is introduced to calculate the similarity of traffic flow sequence among network nodes in the time dimension,and the spatiotemporal graph of traffic flow is constructed to capture the spatiotemporal characteristics and dependencies of traffic *** combining graph attention network and time attention network,a spatiotemporal convolution block is constructed to capture spatiotemporal characteristics of traffic *** on open data sets PEMSD4 and PEMSD8 show that TSADGCN has higher prediction accuracy than well-known traffic flow prediction algorithms.

关键词： Intelligent transportation graph convolutional network traffic flow dtw algorithm attention mechanism

来源：评论

学校读者我要写书评

暂无评论

KINECT BASED RECOGNITION AND DETECTION OF FITNESS QIGONG MOVEMENTS

引用

INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL 2024年第6期20卷 1837-1850页

作者： Fan, Zhehua Sun, Keshuang Putian Univ Coll Phys Educ 1133 Xueyuan Rd Putian 351100 Peoples R China Fuzhou Univ Dept Phys Educ & Res 2 Wulong Jiangbei Ave Fuzhou 350108 Peoples R China

The continuous advancement of computer technology and sensory games has provided players with a richer experience, but in the field of sports and fitness, especially in the teaching and training of fitness qigong, how to accurately identify and correct movements remains a major challenge. Therefore, this study focuses on the recognition of human movements and proposes a Kinect based recognition and detection of fitness qigong movements. The purpose is to more accurately grasp the data of body scans and body contours of athletes to correct their incorrect body movements, thereby reducing the difficulty of movement and overcoming the difficulties of traditional sports training. Firstly, the pose recognition method based on the static K-means algorithm is used to calculate and recognize human skeletal joints. Secondly, the dynamic time warping algorithm is combined to recognize and detect gymnastics posture features, and experimental analysis is conducted on the effectiveness and applicability of recognition and detection techniques. The experiment shows that the recognition accuracy for stretching and chest expansion movements is 247 and 253, respectively, while the recognition accuracy for these two movements in the preprocessed dataset is improved to 259 and 263, respectively. It can be seen that this study not only improves the accuracy of motion recognition, but also promotes the development of personalized fitness guidance. The method proposed by the research institute provides coaches with real-time feedback tools, optimizes athlete training plans, and achieves the improvement of athlete technical level and sports effectiveness. Not only did it help popularize the scientific fitness concept, but it also improved the overall teaching quality and efficiency of fitness qigong.

关键词： Kinect Action recognition dtw algorithm Artificial neural network Stat- ic K-means

来源：评论

学校读者我要写书评

暂无评论

PRODUCT DESIGN FOR THE ELDERLY BASED ON HUMAN-COMPUTER INTERACTION IN THE ERA OF BIG DATA

引用

SCALABLE COMPUTING-PRACTICE AND EXPERIENCE 2024年第3期25卷 2034-2047页

作者： Liu, Zhihong Hunan Polytech Environm & Biol Ecol Livable Coll Hengyang 421005 Peoples R China

Since 21st century, social aging trend has become more and more serious. It needs accurately identify the nursing needs of elderly disabled people, who are characterized by inconvenient movement and unclear speech. How to solve these problems has become a key point in the field of elderly care and medical care. In response to this problem, this research has designed a human -computer interactive gesture recognition system for elderly nursing beds in the context of big data. The recognition rate of the fusion feature + support vector machine (SVM) classifier adopted in this study is higher than 90% for each category of gesture. On the test set, this method has an average recognition rate of 96.35%, which is much higher than that of single feature + SVM classifier. While other methods' recognition rate is lower than 90%. The recognition rate of tag c (nursing bed posture turning left) with obvious gesture feature information is as high as 99.28%, and that of tag h (nursing bed posture bedpan lowering) with weak gesture feature is 93.65%. The human -computer interaction system has well realized the recognition intention of user's dynamic and static gestures, achieved the goal set by the research, and the interaction form is natural and reliable. In the later research, we can further realize a more comprehensive, accurate and natural human -computer interaction product design through the multi -channel joint decision -making scheme to meet the needs of the elderly.

关键词： Gesture recognition Human-computer interaction SVM algorithm dtw algorithm Feature fusion

来源：评论

学校读者我要写书评

暂无评论

Ultra-Short-Term Prediction Method of Photovoltaic Power Generation Based on Improved GRNN-LSTM Combination Model

Ultra-Short-Term Prediction Method of Photovoltaic Power Gen...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Wu, Yun Li, Tianyang Yang, Jieming Feng, Dan Northeast Elect Power Univ Sch Comp Sci Jilin Peoples R China Chaoyang City Ecol & Environm Affairs Serv Ctr Chaoyang Peoples R China

ISBN: (纸本)9798350359329;9798350359312

Ultra-short-term prediction of photovoltaic power generation is the prerequisite for real-time dispatch of the power system, in order to further improve the accuracy of ultra-short-term prediction of photovoltaic power, this paper proposes an ultra-short-term prediction method of photovoltaic power based on an improved Generalized Regression Neural Network(GRNN)-Long Short-Term Memory (LSTM) combination model. Firstly, in the GRNN model, an improved whale optimization algorithm based on grid constraints, quasi-reverse learning and local perturbations is proposed to solve the optimal smoothing factor of the model and improve the prediction accuracy. Secondly, in the LSTM model, a CNN convolutional layer and attention mechanism are introduced to better exploit temporal information and enhance the predictive capabilities for complex weather changes. Finally, a combination model threshold setting method based on an improved Dynamic Time Warping (dtw) algorithm is proposed. This method dynamically selects the best model's prediction results based on thresholds during different time periods, fully leveraging the advantages of each model to meet the diverse weather conditions in photovoltaic power prediction. Experimental results demonstrate that the improved GRNN model excels in predicting sunny weather power, the improved LSTM model excels in predicting complex weather power, and the combination model performs well across various meteorological conditions, providing a robust solution for photovoltaic power ultra-short-term prediction problems.

关键词： photovoltaic power prediction GRNN whale optimization algorithm LSTM dtw algorithm

来源：评论

学校读者我要写书评

暂无评论

Road Network Inference from GPS Traces using dtw algorithm 17

Road Network Inference from GPS Traces using DTW Algorithm

引用

IEEE 17th International Conference on Intelligent Transportation Systems (ITSC)

作者： Xie, Xingzhe Philips, Wilfried Veelaert, Peter Aghajan, Hamid Univ Ghent TELIN IPI IMINDS Ghent Belgium Stanford Univ Dept Elect Engn Stanford CA 94305 USA

ISBN: (纸本)9781479960781

This paper proposes a method for inferring the road network from Global Position System (GPS) traces, which is composed of intersections and the roads between each pair of directly-connected intersections. Random Sampling (RANSAC) algorithm is used to cluster the turning points, where the users change their moving directions, into intersections. All of the GPS traces are segmented by the intersections, resulting in connectivity matrix of the intersections and small GPS tracks for each pair of directly-connected intersections. At last, the road between each two directly-connected intersections is extracted through aligning and averaging all of the tracks using Dynamic Time Warping (dtw) algorithm. The main novelty of our methods is aligning the tracks point by point for each road using a "stretching and compression" strategy, which not only allows road estimation by averaging the aligned tracks, but also a deeper statistical analysis using their time alignment, such as analyzing the users' speed stability at a specific location. The experimental results show that our algorithm outperforms other methods by producing clean road network without spurious edges.

关键词： Global Positioning System inference mechanisms road vehicles signal sampling statistical analysis synchronisation time warp simulation dtw algorithm GPS traces GPS tracks Global Position System RANSAC algorithm connectivity matrix dynamic time warping algorithm random sampling algorithm road estimation road network inference time alignment user speed stability Euclidean distance Gold Heuristic algorithms Indexes Roads Turning

来源：评论

学校读者我要写书评

暂无评论

Hybrid Positioning Approach for Context-Aware Indoor Navigation of Visually Impaired People

引用

ASME OPEN JOURNAL OF ENGINEERING 2022年第1期1卷 011034页

作者： Rathnayake, Sachintha M. Wimalaratne, Prasad Silva, Chathurika S. Univ Colombo Sch Comp UCSC Bldg Complex35 Reid Ave Colombo 00700 Sri Lanka Univ Colombo Sch Comp Dept Commun & Media Technol UCSC Bldg Complex35 Reid Ave Colombo 00700 Sri Lanka Univ Colombo Fac Technol MahenwattaPitipana Homagama 00700 Sri Lanka

Indoor localization for visually impaired persons is an open research problem, and individual localization approaches have failed to provide accurate results in the literature. Therefore, this paper presents a context-aware navigation approach for visually impaired persons using a hybrid localization approach. The proposed approach consists of four main modules, indoor localization, context detection, wayfinding, and feedback. The hybrid localization approach is based on the geomagnetic fields and Bluetooth low energy (BLE). Contextual information such as nearby locations and landmarks were obtained using geolocation-based augmented reality with a pre-deployed map and point of interest (POI). Voice and tactile were used to give feedback. Usability evaluation of the overall proof of concept (POC) prototype has shown promising results in context detection, wayfinding, and navigation. The average distance error of the hybrid localization algorithm has given an average 2.72 m distance error. Evaluation of the way findings give the average hit rate is 75.19%, and the miss rate is 24.81%. Usability evaluation results show that the proposed algorithm improves the context-awareness of the visually impaired indoor navigation.

关键词： geomagnetic field BLE beacon hybrid localization context-aware dtw algorithm trilateration hybrid systems real-time control sensor fusion sensors and sensor networks vibrations virtual and augmented reality environments wearable technologies wireless

来源：评论

学校读者我要写书评

暂无评论

Application of intelligent audio data based on hash storage in vocal music teaching platform

引用

SOFT COMPUTING 2023年

作者： Tang, Yu Zeng, Xiaoli Aba Teachers Univ Sch Mus & Dance Aba 623002 Sichuan Peoples R China Sichuan Inst Ind Technol Sch Educ Deyang 621000 Sichuan Peoples R China

In this paper, the fast algorithm of audio retrieval is more about the template matching process of audio feature parameters. Nowadays, people regard vocal music learning as a way to relax the mood, because vocal music not only helps people vent their emotions and convey their heartfelt thoughts, but also helps regulate our body and mind. Aiming at these problems, this paper designs a vocal self-study assistant system. The vocal self-study assistant system introduces the latest technology, which can enable people to learn vocal music anywhere and anytime. First of all, the search time is reduced through the hash structure, and the search efficiency is improved. The index structure proposed in this paper includes two parts: the surface layer of the hash table and the tree layer of the hash tree. A hash tree structure that can perfectly adapt to changes in the amount of data is also proposed. In addition, this article also introduces the efficient search algorithm built by the hash tree index. According to the experimental results, it can be found that the intelligent audio data rapid retrieval algorithm using the image registration method is similar to the intelligent audio retrieval algorithm based on the dtw algorithm. Compared with the former, it is more accurate. Therefore, the retrieval algorithm in this article can be applied to intelligent audio retrieval technology based on content and semantics.

关键词： Hash storage Intelligent audio data dtw algorithm Vocal platform

来源：评论

学校读者我要写书评

暂无评论

Bilabial Consonants Recognition in CV Persian Syllable Based on Computer Vision 29

Bilabial Consonants Recognition in CV Persian Syllable Based...

引用

29th Iranian Conference on Electrical Engineering (ICEE)

作者： Khajeh, Melika Bastanfard, Azam Amirkhani, Dariush Islamic Azad Univ Karaj Fac Comp Engn Karaj Iran Islamic Azad Univ Karaj Dept Mechatron Karaj Iran Iran Broadcasting Univ Dept Engn & Media Tehran Iran

ISBN: (纸本)9781665433655

According to previous researches, Persian consonants have been divided into seven categories based on viseme. It led to several consonants being placed in one category. Detecting between consonants in one category is so hard because the spots for the production of these consonants are the same. The forms of lips do not change at the time of production;these consonants are hardly distinguishable. The major challenge is to recognize the differences between lip shapes in one category. The purpose of this study is to recognize differences between bilabial consonants such as /p/, /b/, and /m/ in a word that composed of consonant/vowel called CV by computer vision. For the first time, this study attempts to distinguish these consonants. Proper pronunciations of words are required to identify consonants. Therefore, a database has formed based on the videos of the speech therapists. Generally, this kind of process is including 1-lip detection, 2-lip feature extraction, and 3-classification systems for the diagnosis of consonants. In this paper, consonants recognition in a category based on lip shape using the CLM algorithm for lip detection is presented. Geometric algorithms for feature extraction and dtw and equalizer as a classification system are proposed. Although this study is open because we could identify differences among consonants in just one class, we could reach remarkable CV video results for the first time. We could aim for acceptable results with reasonable accuracy for bilabial consonants detection. The principle purpose of this study is to improve lip-reading systems in security issues and help hearing-impaired people in interaction with their surroundings. The results of this paper can have a positive effect on speech systems.

关键词： CLM algorithm dtw algorithm viseme Consonant feature extraction Euclidean distance

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：