检索结果-内蒙古大学图书馆

8th International Workshop on Advanced Computational Intelligence and Intelligent Informatics, IWACIII 2023

作者： Zeng, Xiang-Yu Zhang, Bo-Yang Liu, Zhen-Tao School of Future Technology China University of Geosciences Wuhan430074 China School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China

ISBN: (纸本)9789819975891

With the rapid development of online education around world, it becomes difficult for teachers to evaluate the effect of learning during the online class. To solve this problem, an attention detection system based on gaze estimation using self-supervised learning is proposed. Self-supervised learning is used to train the gaze estimation network and it achieved an average gaze angle error of 6. 5∘ on the MPIIFaceGaze dataset. Cross dataset testing was performed by 5 test subjects in the RT-GENE dataset and all samples in the Columbia dataset, in which achieved average gaze angle error 13. 8∘ and 5. 5∘. It is found that the network has good cross dataset generalization performance, but it is susceptible to factors such as feature occlusion and low image clarity. Then, we developed an attention detection system which has functions of unmanned detection, eye state detection, and gaze detection. Online classroom experiments were conducted to verify the effectiveness of the proposed method, in which the average accuracy of the detection of distraction is around 60%. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing Bounding Box Regression in complex Backgrounds

Optimizing Bounding Box Regression in Complex Backgrounds

引用

Chinese Automation Congress (CAC)

作者： Jun Chen Haiyan Zhang Anjun Yu Yiwei Wang Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education School of Automation China University of Geosciences Wuhan China Jiangxi Ganyue Expressway Co. Ltd. Nanchang China School of Automation China University of Geosciences Wuhan China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

In the context of electrical power operation sites, the automated and accurate detection of whether workers are properly equipped with safety gear, such as safety clothing, helmets, and safety ropes for high-altitude operations, is crucial for ensuring the safety of personnel. Traditional object detection models often struggle to accurately identify these critical pieces of safety equipment in complex environments, due to variable object sizes, overlapping objects, and substantial background noise. To specifically address these challenges, we propose a novel loss function-Enhanced Alignment Intersection over Union (EAIoU) loss. This loss function is designed to enhance the model's ability to discriminate between closely spaced and overlapping safety gear in real-time, significantly improving robustness against scale variations and complex backgrounds. In experiments based on the YOLOv8s architecture, our model achieved a mean Average Precision (mAP) of 92.1 % on a dataset specific to electrical power operations, markedly outperforming traditional IoU loss functions. Additionally, EAIoU demonstrated improved performance on the COCO dataset, indicating its generalization capability across various complex scenarios. This research not only enhances the accuracy and real-time performance of safety equipment detection at electric power operation sites but also opens new avenues for advanced object detection technology in complex, multi-object environments.

关键词： Accuracy Gears Shape Object detection Robustness Real-time systems Safety Power systems Personnel Object recognition

来源：评论

学校读者我要写书评

暂无评论

Disturbance Observer-Based control of Weight on Bit in Drilling Process with Formation Variation

Disturbance Observer-Based Control of Weight on Bit in Drill...

引用

Asian control Conference

作者： Shipeng Chen Wangnian Li Chengda Lu Yang Zhou Weihua Cao Min Wu School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China CCTEG Xi'an Research Institute (Group) Co. Ltd. Xi'an China

ISBN: (数字)9789887581598

ISBN: (纸本)9798331540845

In deep geological drilling, encountering various formations is inevitable. Formation changes can lead to fluc-tuations in the weight on bit due to the bit-rock interaction. This paper proposes a disturbance observer-based weight on bit control system to mitigate the adverse effects of formation changes on system performance. First, an axis-torsion coupled dynamic model is established, and the relationship between the two dimensions is analyzed. The validity of the model is confirmed through comparison with field data collected from a geothermal well drilling operation. Then, a disturbance observer is designed to estimate and compensate for the disturbance at the control input, thereby reducing weight on bit fluctuations caused by formation variations. Simulation results considering formation variation during drilling verify the effectiveness of the proposed method.

关键词： Drilling Simulation System performance Geology Process control control systems Disturbance observers

来源：评论

学校读者我要写书评

暂无评论

Robotic Arm control System Based on Brain-Muscle Mixed Signals

Research Square

引用

Research Square 2021年

作者： Cheng, Li-Wei Li, Duan-Ling Yu, Gong-Jing Zhang, Zhong-Hai Yu, Shu-Yue Key Laboratory of Measurement and Control of Complex Engineering Systems China School of Modern Post School of Automation Beijing University of Posts and Telecommunications Beijing100876 China Beijing Aerospace Measurement & Control Technology Co. Ltd. Beijing100041 China

Aiming at the existing problems of BCI (brain computer interface), such as single input signal source, low accuracy of feature recognition, and less output control instructions, this paper proposes a robotic arm control system based on EEG (electroencephalogram) and EMG (electromyogram) mixed signals. The system flow is as follows: Firstly, the EMG signal of the unilateral arm and the EEG signal of the left and right hand motor imagery is collected synchronously. Then the collected EEG and EMG signals are extracted and classified, and the corresponding classification instructions are obtained. Finally, the multi-instruction real-time control of the robotic arm is realized under the classification instruction. The experimental verification results show that: The 10 subjects all realized the real-time multicommand control of the robotic arm, and the average recognition accuracy of each action reached more than 94%. The proposed system enriches the diversity of hybrid BCI and provides a theoretical basis and application foundation for the extended application of BCI in robotic arm control. © 2021, CC BY.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Accelerometer optimization based on real-time measurement of Hole Deviation INS with While-Drilling

Accelerometer optimization based on real-time measurement of...

引用

2021 China Automation Congress, CAC 2021

作者： Liu, Yuan-Qiu Jin, Fang Song, Jun-Lei Dong, Kai-Feng Mo, Wen-Qin Hui, Ya-Juan School of Automation China University of Geosciences Wuhan420074 China Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China

ISBN: (纸本)9781665426473

Well deviation measurement of While-Drilling(MWD) refers to the real-time measurement of well deviation and azimuth While-Drilling is the key for navigation in automatic drilling, real-time detection of drilling direction and automatic drilling control. In this paper, we solve the problem that the accelerometer could not accurately measure gravity because of the high-speed rotation caused by the eccentric installation of INS (Inertial Navigation System) and the acceleration of vibration line in the real-time measurement of borehole deviation and azimuth angle while drilling. Firstly, the dynamic physical model of accelerometer and gyroscope under eccentric installation is built, the non-gravity error of accelerometer measurement under eccentric motion is analyzed, and the algorithm optimization is made. Secondly, a calibration scheme for the compensation coefficients of centrifugal and tangential forces is given, which enables the carrier to make eccentric pure rotational motion on the rotating platform to determine the compensation calibration coefficient matrix. Finally, the first-order complementary filter algorithm is used to fuse the gyroscope angular velocity with the corrected acceleration for attitude calculation, and the algorithm is experimented. In this study, MPU6050 is selected as the chip of INS, and the attitude algorithm is realized by STM32. The experimental results show that the high dynamic error of the accelerometer measurement caused by eccentric motion is effectively reduced by the algorithm compensation. © 2021 IEEE

关键词： Accelerometers

来源：评论

学校读者我要写书评

暂无评论

A Multi-modal Panoramic Speaker Localization Method

A Multi-modal Panoramic Speaker Localization Method

引用

2021 China Automation Congress, CAC 2021

作者： Long, Y.Z. Jian, Y.W. Liu, Z.T. School of Automation China University of Geosciences WuHan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems WuHan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China

ISBN: (纸本)9781665426473

As a supporting technology in the field of human-computer interaction, speaker localization method has been a research hotspot in recent years. However, the existing single-mode speaker location methods cannot meet the requirements of stability and rapidity. For improve the accuracy and effective positioning range of speaker localization system, a multi-modal panoramic speaker localization method is proposed in this paper. Firstly, the coarse position of the speaker was preliminarily obtained by sound source localization. Then, according to the initial positioning of the speaker, whether the image used for face recognition need to be stitched is decided. What's more, the position of speaker is calculated by face detection and calibration. Finally, the results of voice and image localization are fused by coordinate transformation. The proposal is tested on self-built experimental system, and the experimental results prove the effectiveness of the proposed method. © 2021 IEEE

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Adaptation Via Proxy: Building Instance-Aware Proxy for Unsupervised Domain Adaptive 3d Object Detection

SSRN

引用

SSRN 2023年

作者： Li, Ziyu Yao, Yuncong Quan, Zhibin Qi, Lei Feng, Zhenhua Yang, Wankou School of Automation Southeast University Nanjing210096 China Key Lab of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China School of Computer Science and Engineering Southeast University Nanjing210096 China Department of Computer Science University of Surrey GuildfordGU2 7XH United Kingdom

LiDAR-based 3D detectors perform well on particular autonomous driving benchmarks, but may poorly generalize to other domains. Existing 3D domain adaptive detection methods usually require annotation-related statistics or continuous refinement of pseudo-labels. The former is not always feasible for practical applications, while the latter lacks sufficient accurate supervision. In this work, we propose a novel unsupervised domain adaptive framework, namely Adaptation Via Proxy (AVP), that explicitly leverages cross-domain relationships to generate adequate high-quality samples without any target statistics, thus mitigating domain shifts for existing LiDAR-based 3D detectors. Specifically, we first train the detector on the source domain with curriculum example mining to enhance its generalization capability. Then, we fine-tune the pre-trained detector on the instance-aware proxy that is a data collection with stronger supervision. The instance-aware proxy utilizes the profitable instances from the source domain to provide more robust supervision for optimizing the detector to overcome domain gaps. Note that AVP is architecture-agnostic thus it can be easily injected with any LiDAR-based 3D detectors. Extensive experiments on Waymo, nuScenes, KITTI and Lyft demonstrate the superiority of the proposed method over the state-of-the-art approaches for different adaptation scenarios. © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing Image Classification Based on Lightweight Network and Pruning

Remote Sensing Image Classification Based on Lightweight Net...

引用

Chinese Automation Congress (CAC)

作者： Zexi Wang Wei Xue Kehui Chen Shaopeng Ma School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China

In recent years, deep neural network has continuously improved the performance of remote sensing image classification. Though The deep neural network model is powerful, it is difficult to deploy on resource-constrained hardware platforms such as mobile terminal devices and embedded devices due to the large number of network parameters. In this paper, a novel lightweight network (LW-Net) model and a network pruning method are used for remote sensing image classification. This LW-Net model adopts a net block unit to obtain more characteristic graphs with less computational complexity. The proposed network pruning method uses the sparsity regularization on the influence factor in BN layer to automatically identified and pruned unimportant channels to make the model structure simpler. Experimental results demonstrate compared with traditional deep neural networks, the proposed model with the network pruning method can greatly reduce the computational complexity and model parameters with a little accuracy loss.

关键词： Deep learning Training Performance evaluation Runtime Computational modeling Neural networks Sensors

来源：评论

学校读者我要写书评

暂无评论

Syllable Level Speech Emotion Recognition Based on Formant Attention 1st

Syllable Level Speech Emotion Recognition Based on Formant ...

引用

1st CAAI International Conference on Artificial Intelligence, CICAI 2021

作者： Rehman, Abdul Liu, Zhen-Tao Xu, Jin-Meng School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China

ISBN: (纸本)9783030930486

The performance of speech emotion recognition (SER) systems can be significantly compromised by the sentence structure of words being spoken. Since the relation between affective content and the lexical content of speech is difficult to determine in a small training sample, the temporal sequence based pattern recognition methods fail to generalize over different sentences in the wild. In this paper, a method to recognize emotion for each syllable separately instead of using a pattern recognition for a whole utterance is proposed. The work emphasizes the preprocessing of the received audio samples where the skeleton structure of Mel-spectrum is extracted using formant attention method, then utterances are sliced into syllables based on the contextual changes in the formants. The proposed syllable onset detection and feature extraction method is validated on two databases for the accuracy of emotional class prediction. The suggested SER method achieves up to 67% and 55% unweighted accuracy on IEMOCAP and MSP-Improv datasets, respectively. The effectiveness of the method is proved by the experimentation results and compared to the state-of-the-art SER methods. © 2021, Springer Nature Switzerland AG.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Reinforcement Learning Based Dynamic Multi-Objective Constrained Evolutionary Algorithm for Open-Pit Mine Truck Scheduling

A Reinforcement Learning Based Dynamic Multi-Objective Const...

引用

Chinese Automation Congress (CAC)

作者： Junxiang Qiu Changhe Li Shengxiang Yang Engineering Research Center of Intelligent Technology for Geo- Exploration Ministry of Education School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China School of Computer Science and Informatics De Montfort University Leicester UK

Aiming at the truck scheduling problem in the open-pit mine scenario, a truck scheduling model based on real-time ore blending is established, and an adaptive evolution algorithm for truck scheduling based on DCNSGA-III is proposed. In the established scheduling model, the real-time grade variance of the crushing plant is minimized as one of the optimization objectives, and the Q-learning algorithm is introduced to adaptively select one of the most effective operators during the search process. Experiments show that the proposed method can effectively control the grade fluctuation of the ore flow and better scheduling schemes are obtained in comparison with algorithms equipped with the traditional search operator selection methods.

关键词：

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：