检索结果-内蒙古大学图书馆

Time Convolutional Network-Based Maneuvering Target Tracking with Azimuth-Doppler Measurement

SENSORS 2024年第1期24卷 263页

作者： Huang, Jianjun Hu, Haoqiang Kang, Li Shenzhen Univ Sch Intelligent Informat Proc Shenzhen 518060 Peoples R China

In the field of maneuvering target tracking, the combined observations of azimuth and Doppler may cause weak observation or non-observation in the application of traditional target-tracking algorithms. Additionally, traditional target tracking algorithms require pre-defined multiple mathematical models to accurately capture the complex motion states of targets, while model mismatch and unavoidable measurement noise lead to significant errors in target state prediction. To address those above challenges, in recent years, the target tracking algorithms based on neural networks, such as recurrent neural networks (RNNs), long short-term memory (LSTM) networks, and transformer architectures, have been widely used for their unique advantages to achieve accurate predictions. To better model the nonlinear relationship between the observation time series and the target state time series, as well as the contextual relationship among time series points, we present a deep learning algorithm called recursive downsample-convolve-interact neural network (RDCINN) based on convolutional neural network (CNN) that downsamples time series into subsequences and extracts multi-resolution features to enable the modeling of complex relationships between time series, which overcomes the shortcomings of traditional target tracking algorithms in using observation information inefficiently due to weak observation or non-observation. The experimental results show that our algorithm outperforms other existing algorithms in the scenario of strong maneuvering target tracking with the combined observations of azimuth and Doppler.

关键词： azimuth and Doppler convolutional neural network deep learning algorithm maneuvering targets tracking

来源：评论

学校读者我要写书评

暂无评论

Accelerating deep convolutional neural network on FPGA for ECG signal classification

引用

MICROPROCESSORS AND MICROSYSTEMS 2023年 103卷

作者： Aruna, V. B. K. L. Chitra, E. Padmaja, M. SRM Inst Sci & Technol ECE Dept Chennai 603203 India VR Siddhartha Engn Coll ECE Dept Vijayawada 520007 Andhra Pradesh India

Abnormal activity of the heart is known as cardiac arrhythmia which must be recognized in earlier stage to prevent sudden death and premature death. The occurrence of arrhythmia increases with age, and it is detected using an electrocardiogram (ECG) signal. Conversely, it is very complex to manually achieve the quick and exact classification due to the complexity, non-linearity and low amplitude of the ECG signal. As a result, the healthcare field requires an automatic system to recognize abnormal heartbeats from a huge amount of ECG records. So, the deep learning algorithm named as deep Convolutional Neural Network (DCNN) is proposed in this research to analyze the ECG signal on a field-programmable gate array (FPGA). Before performing a clas-sification process, two different processes called signal pre-processing as well as feature extraction are required. For the process of signal pre-processing, the Error Normalised Least Mean Square (ENLMS) algorithm is utilized in our work, and Discrete Wavelet Transform (DWT) technique is performed to take out the relevant features from the ECG signal. Finally, FPGA based one-dimensional DCNN with 3 convolutional layers, 3 pooling layers, and 3 fully connected layers is proposed to classify the signals with proper complex features. The publicly available MIT-BIH arrhythmia and PTB databases are exploited in this research to process ECG signals on the multi-input structure. In addition, different performance parameters like classification accuracy, specificity, sensitivity, and precision are engaged to evaluate the proposed methodology;also, it is compared with different FPGA based existing classifiers. The analysis shows that the proposed design accomplishes 98.6 % classification accuracy on the MIT-BIH arrhythmia database and 99.67 % accuracy on the PTB database, which is 0.304 % higher than a multilayer perception (MLP) and 0.47 % higher than decision-based classifier. Moreover, the proposed FPGA based DCNN accelerator cons

关键词： ECG signal classification deep learning algorithm Signal de-noising process Feature extraction DWT method Error Normalised Least Mean Square (ENLMS) algorithm

来源：评论

学校读者我要写书评

暂无评论

Development of a fully automated RULA assessment system based on computer vision

引用

INTERNATIONAL JOURNAL OF INDUSTRIAL ERGONOMICS 2021年 86卷 1页

作者： Nayak, Gourav Kumar Kim, Eunsik Univ Windsor Mech Automot & Mat Engn 401 Sunset Ave Windsor ON N9B 3P4 Canada

The purpose of this study was to develop an automated, RULA-based posture assessment system using a deep learning algorithm to estimate RULA scores, including scores for wrist posture, based on images of workplace postures. The proposed posture estimation system reported a mean absolute error (MAE) of 2.86 on the validation dataset obtained by randomly splitting 20% of the original training dataset before data augmentation. The results of the proposed system were compared with those of two experts' manual evaluation by computing the intraclass correlation coefficient (ICC), which yielded index values greater than 0.75, thereby confirming good agreement between manual raters and the proposed system. This system will reduce the time required for postural evaluation while producing highly reliable RULA scores that are consistent with those generated by manual approach. Thus, we expect that this study will aid ergonomic experts in conducting RULA-based surveys of occupational postures in workplace conditions.

关键词： RULA deep learning algorithm Musculoskeletal injuries Automated posture assessment system

来源：评论

学校读者我要写书评

暂无评论

SPACE: Structured Compression and Sharing of Representational Space for Continual learning

引用

IEEE ACCESS 2021年 9卷 150480-150494页

作者： Saha, Gobinda Garg, Isha Ankit, Aayush Roy, Kaushik Purdue Univ Sch Elect & Comp Engn W Lafayette IN 47907 USA

Humans learn incrementally from sequential experiences throughout their lives, which has proven hard to emulate in artificial neural networks. Incrementally learning tasks causes neural networks to overwrite relevant information learned about older tasks, resulting in 'Catastrophic Forgetting'. Efforts to overcome this phenomenon often utilize resources poorly, for instance, by growing the network architecture or needing to save parametric importance scores, or violate data privacy between tasks. To tackle this, we propose SPACE, an algorithm that enables a network to learn continually and efficiently by partitioning the learnt space into a Core space, that serves as the condensed knowledge base over previously learned tasks, and a Residual space, which is akin to a scratch space for learning the current task. After learning each task, the Residual is analyzed for redundancy, both within itself and with the learnt Core space. A minimal number of extra dimensions required to explain the current task are added to the Core space and the remaining Residual is freed up for learning the next task. We evaluate our algorithm on P-MNIST, CIFAR and a sequence of 8 different datasets, and achieve comparable accuracy to the state-of-the-art methods while overcoming catastrophic forgetting. Additionally, our algorithm is well suited for practical use. The partitioning algorithm analyzes all layers in one shot, ensuring scalability to deeper networks. Moreover, the analysis of dimensions translates to filter-level sparsity, and the structured nature of the resulting architecture gives us up to 5x improvement in energy efficiency during task inference over the current state-of-the-art.

关键词： Task analysis Principal component analysis Redundancy Data privacy Complexity theory Training Partitioning algorithms Continual learning catastrophic forgetting deep learning algorithm principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Application for Recognizing Sign Language Gestures Based on an Artificial Neural Network

引用

SENSORS 2022年第24期22卷 9864-9864页

作者： Kozyra, Kamil Trzyniec, Karolina Popardowski, Ernest Stachurska, Maria Ailleron SA Jana Pawla 2 43b PL-31864 Krakow Poland Agr Univ Krakow Dept Machinery Exploitat Ergon & Prod Proc Balicka 116B PL-30149 Krakow Poland Poznan Univ Tech Fac Management Engn Inst Safety & Qual Engn J Rychlewskiego 2 PL-60965 Poznan Poland

This paper presents the development and implementation of an application that recognizes American Sign Language signs with the use of deep learning algorithms based on convolutional neural network architectures. The project implementation includes the development of a training set, the preparation of a module that converts photos to a form readable by the artificial neural network, the selection of the appropriate neural network architecture and the development of the model. The neural network undergoes a learning process, and its results are verified accordingly. An internet application that allows recognition of sign language based on a sign from any photo taken by the user is implemented, and its results are analyzed. The network effectiveness ratio reaches 99% for the training set. Nevertheless, conclusions and recommendations are formulated to improve the operation of the application.

关键词： convolutional neural networks deep learning algorithm machine image recognition systems

来源：评论

学校读者我要写书评

暂无评论

Combined framework based on data preprocessing and multi-objective optimizer for electricity load forecasting

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2023年第1期119卷

作者： Xia, Yurui Wang, Jianzhou Wei, Danxiang Zhang, Ziyuan Macau Univ Sci & Technol Inst Syst Engn Macau 999078 Peoples R China

In recent years, accurate electricity load forecasting has become increasingly essential for improving the management efficiency of power-generation systems. However, previously proposed hybrid models directly apply signal-processing technology in data preprocessing, resulting in poor efficiency in matching the electricity sequence characteristics. Moreover, most studies exhibit non-optimal performance in practical applications because they focus on forecasting accuracy and ignore forecasting stability. In this study, a combined framework that includes amodified noise processing strategy, multi-objective optimization algorithm, and deep neural network is proposed to solve the low prediction-accuracy problem in electricity load forecasting. The 30-minute real time data of electricity load from Queensland, Australia, are employed to verify the reliability of the proposed framework. The mean absolute percentage error values of the proposed framework in a multi-step prediction approached the values of MAPE1-step = 0.79%, MAPE2-step = 1.13%, and MAPE3-step = 1.50% in Series 1, which significantly outperformed the existing contrast models.

关键词： Electricity load forecasting Combined framework Signal processing deep learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Identifying Dike-Pond System Using an Improved Cascade R-CNN Model and High-Resolution Satellite Images

引用

REMOTE SENSING 2022年第3期14卷 717页

作者： Ma, Yintao Zhou, Zheng She, Xiaoxiong Zhou, Longyu Ren, Tao Liu, Shishi Lu, Jianwei Huazhong Agr Univ Sch Resources & Environm Wuhan 430070 Peoples R China Minist Agr Key Lab Arable Land Conservat Middle & Lower Reac Wuhan 430070 Peoples R China Minist Ecol Environm Ecol Environm Monitoring & Sci Res Ctr Yangtze River Basin Ecol Environm Supervis & Adm Wuhan 430014 Peoples R China

The dike-pond system (DPS) is the integration of a natural or man-made pond and crop cultivation on dikes, widely distributed in the Pearl River Delta and Jianghan plain in China. It plays a key role in preserving biodiversity, enhancing the nutrient cycle, and increasing crop production. However, DPS is rarely mapped at a large scale with satellite data, due to the limitations in the training dataset and traditional classification methods. This study improved the deep learning algorithm Cascade Region Convolutional Neural Network (Cascade R-CNN) algorithm to detect the DPS in Qianjiang City using high-resolution satellite data. In the proposed mCascade R-CNN, the regular convolution layer in the backbone was modified into the deformable convolutional layer, which was more suitable for learning the features of DPS with variable shapes and orientations. The mCascade R-CNN yielded the most accurate detection of DPS, with an average precision (AP) value that was 2.71% higher than Cascade R-CNN and 11.84% higher than You Look Only Once-v4 (YOLOv4). The area of oilseed rape growing on the dikes accounted for 3.42% of the total oilseed rape planting area. This study demonstrates the potential of the deep leaning methods combined with high-resolution satellite images in detecting integrated agriculture systems.

关键词： dike-pond detection high-resolution satellite deep learning algorithm Cascade R-CNN YOLOv4

来源：评论

学校读者我要写书评

暂无评论

Multi-Stream Fusion Network for Skeleton-Based Construction Worker Action Recognition

引用

SENSORS 2023年第23期23卷 9350-9350页

作者： Tian, Yuanyuan Liang, Yan Yang, Haibin Chen, Jiayu City Univ Hong Kong Dept Architecture & Civil Engn Hong Kong 999077 Peoples R China Shenzhen Univ Coll Civil & Transportat Engn Key Lab Resilient Infrastruct Coastal Cities MOE Shenzhen 518060 Peoples R China Tsinghua Univ Sch Civil Engn Beijing 100084 Peoples R China

The global concern regarding the monitoring of construction workers' activities necessitates an efficient means of continuous monitoring for timely action recognition at construction sites. This paper introduces a novel approach-the multi-scale graph strategy-to enhance feature extraction in complex networks. At the core of this strategy lies the multi-feature fusion network (MF-Net), which employs multiple scale graphs in distinct network streams to capture both local and global features of crucial joints. This approach extends beyond local relationships to encompass broader connections, including those between the head and foot, as well as interactions like those involving the head and neck. By integrating diverse scale graphs into distinct network streams, we effectively incorporate physically unrelated information, aiding in the extraction of vital local joint contour features. Furthermore, we introduce velocity and acceleration as temporal features, fusing them with spatial features to enhance informational efficacy and the model's performance. Finally, efficiency-enhancing measures, such as a bottleneck structure and a branch-wise attention block, are implemented to optimize computational resources while enhancing feature discriminability. The significance of this paper lies in improving the management model of the construction industry, ultimately aiming to enhance the health and work efficiency of workers.

关键词： construction worker action recognition deep learning algorithm 3D skeleton data multi-stream network

来源：评论

学校读者我要写书评

暂无评论

Random Interpolation Resize: A free image data augmentation method for object detection in industry

引用

EXPERT SYSTEMS WITH APPLICATIONS 2023年第1期228卷

作者： Wan, Dahang Lu, Rongsheng Xu, Ting Shen, Siyuan Lang, Xianli Ren, Zhijie Hefei Univ Technol Sch Instrument Sci & Optoelect Engn Hefei 230009 Peoples R China Hefei Univ Technol Prov Key Lab Measuring Theory & Precis Instrument Hefei 230009 Anhui Peoples R China

In the inspection task of industrial machine vision, insufficient data frequently occurs, and data enhancement can artificially incorporate the prior knowledge of human vision, expand the image data, and improve the model's performance, which has become the model's standard configuration. However, the majority of current data enhancement methods are intended for general scenes, and there are few image enhancement methods designed particularly for industrial object detection. Furthermore, many data enhancement methods require additional training time or annotation recalculation. This paper proposes a novel image data enhancement method, Random Interpolation Resize (RIR). We alter the interpolation method of the standard resize step in the preprocessing from fixed collocation to random selection in order to expand the image data and improve the model's generalization and detection capabilities. There are no online editing options for annotations, and no additional training time is available. Multiple data sets were tested using various target detection algorithms, resulting in a 0.45% to 5.6% enhancement in mAP0.5 and an increase in the detection effect.

关键词： Data augmentation Image interpolation Object detection Industry applications deep learning algorithm Convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Mixed local channel attention for object detection

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2023年第PartC期123卷

作者： Wan, Dahang Lu, Rongsheng Shen, Siyuan Xu, Ting Lang, Xianli Ren, Zhijie Hefei Univ Technol Sch Instrument Sci & Optoelect Engn Hefei 230009 Peoples R China Hefei Univ Technol Anhui Prov Key Lab Measuring Theory & Precis Instr Hefei 230009 Peoples R China

Attention mechanism, one of the most extensively utilized components in computer vision, can assist neural networks in emphasizing significant elements and suppressing irrelevant ones. However, the vast majority of channel attention mechanisms only contain channel feature information and ignore spatial feature information, resulting in poor model representation effect or object detection performance, and the spatial attention modules were often complex and expensive. In order to strike a balance between performance and complexity, this paper proposes a lightweight Mixed Local Channel Attention (MLCA) module to improve the performance of the object detection network, and it can simultaneously incorporate both channel information and spatial information, as well as local information and global information to improve the expression effect of the network. On this basis, the MobileNet-Attention-YOLO(MAY) algorithm for comparing the performance of various attention modules is presented. On the Pascal VOC and SMID datasets, MLCA achieves a better balance between model representation efficacy, performance, and complexity than alternative attention techniques. Against the Squeeze-and-Excitation(SE) attention mechanism on the PASCAL VOC dataset and the Coordinate Attention(CA) method on the SIMD dataset, the mAP is enhanced by 1.0 % and 1.5 %, respectively.

关键词： Attention mechanism Local channel attention Object detection deep learning algorithm Convolutional neural network

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：