检索结果-内蒙古大学图书馆

26th international conference on Industrial Technology, ICIT 2025

作者： Ma, Tianyu Du, Sheng Fan, Haipeng Huang, Cheng 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)9798331521950

Geological drilling process, owing to Complex geological environment and harsh downhole conditions, generates data including characteristics such as pressure, rotational speed, and depth, which are frequently high-dimensional and noisy. These characteristics make real-time monitoring more complex. Existing methods in the geological drilling process, such as rule-based systems and threshold techniques, struggle to handle the complexity and high dimensionality of drilling data, leading to high false alarm rates and low detection accuracy. This paper develops an integrated temporal dictionary learning with isometric mapping method for monitoring geological drilling process. Specifically, Isometric Mapping is employed to perform dimensionality reduction on high-dimensional data, thereby retaining the structural features in the lower-dimensional space. Subsequently, Lasso regularization is applied for sparse coding to extract essential features from the reduced data. To address the fluctuations arising from the iterative dictionary learning process, a temporal smoothing term is incorporated to ensure the stability of the dictionary across different time steps. After that, the reconstruction errors were adopted to achieve comprehensive statistical indicators. Then the overall monitoring was realized for the plant-wide process. The effectiveness and robustness of the proposed method are demonstrated through case studies on the Tennessee-Eastman process and the actual geothermal drilling process. © 2025 ieee.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Perceptual Learning Technology Based on Computer Vision and Machine Learning Algorithms

Perceptual Learning Technology Based on Computer Vision and ...

引用

international conference on Communication systems and Network Technologies (CSNT)

作者： Tianjian Wang School of Computer Science and Technology Wuhan Qingchuan University Wuhan China

ISBN: (数字)9798331531935

ISBN: (纸本)9798331531942

To address the issue of low accuracy and poor robustness of perceptual learning in complex scenarios, a new method integrating computer vision and machine learning is adopted, that is, by applying deep neural networks, transfer learning and self-supervised learning, combined with multimodal data fusion strategy, to improve target recognition efficiency and learning ability. First, based on the preprocessing algorithm of improved Gaussian filtering and image segmentation, the quality of image features is improved. data enhancement methods such as random rotation, flipping, and blurring are used to expand data distribution and improve model adaptability. Secondly, a convolutional neural network (CNN) is utilized in combination with an attention mechanism to extract multi-scale target features, and transfer learning is applied to transfer common features from pre-trained models to reduce dependence on large-scale labeled data. Finally, a contrastive learning framework is constructed to mine the correlation of unlabeled data. Transformer is used to realize the fusion of multimodal data of images and texts, and the model performance is optimized through multi-task learning. The mAP (Mean Average Precision) of the traditional method in dynamic occlusion scenarios is 60.5%, which is relatively weak. This may be because the traditional method cannot fully extract the effective features of the target under the occlusion of complex moving targets. The mAP of the method in this paper is 72.8%, which is higher than that of the traditional method. The perceptual learning method adopted in this paper effectively improves the accuracy and robustness in complex scenarios, and provides reliable technical support for intelligent applications. In the future, it can be combined with edge computing to further optimize the real-time processing capability and promote its application in the fields of unmanned driving and intelligent security.

关键词： Adaptation models Computer vision Image segmentation Machine learning algorithms Computational modeling Transfer learning Feature extraction data models Robustness Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Efficient Facial Expression Recognition Network Based on Spot-Adaptive Knowledge Distillation

Efficient Facial Expression Recognition Network Based on Spo...

引用

ieee international conference on Industrial Technology (ICIT)

作者： Xin Wen Zhen-Tao Liu Dan Chen School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education

ISBN: (数字)9798331521950

ISBN: (纸本)9798331521967

Facial expression recognition plays a key role in promoting the development of comprehensive intelligence and building friendly human-computer interaction. Due to the interference of feature noise in expression data, the lightweight facial expression recognition model with fewer parameters is difficult to learn more expression features through simple training, which limits the improvement of its recognition performance. An efficient facial expression recognition network based on Spot-adaptive Knowledge Distillation is proposed in this paper. Inspired by VoVNetV2, the network designed in this paper is lightweightly improved using Depthwise Separable Convolution and the parameter-free SimAM attention mechanism, reducing the number of parameters to 0.21 M. To further improve the recognition accuracy of the model, Spot-adaptive Knowledge Distillation is employed to improve the characterization ability of the model. The recognition accuracies of the student network designed in this paper on the KDEF and RAF-DB datasets are 93.05% and 81.17% respectively after spot-adaptive distillation.

关键词： Knowledge engineering Training Human computer interaction Accuracy Face recognition Computational modeling Noise Neural networks Interference data models

来源：评论

学校读者我要写书评

暂无评论

UNeLF: Unconstrained Neural Light Field for Self-Supervised Angular Super-Resolution

引用

ieee Transactions on Circuits and systems for Video Technology 2025年

作者： Zhao, Mingyuan Sheng, Hao Chen, Rongshan Cong, Ruixuan Cui, Zhenglong Yang, Da Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing100191 China Beihang University Data Science and Intelligent Computing Laboratory Hangzhou International Innovation Institute Hangzhou311115 China Macao Polytechnic University Faculty of Applied Sciences 999078 China

Compared to supervised learning methods, self-supervised learning methods address the domain gap problem between light field (LF) datasets collected under varying acquisition conditions, which typically leads to decreased performance when differences exist in the distribution between the training and test sets. However, current self-supervised light field angular super-resolution (LFASR) techniques primarily focus on exploiting discrete spatial-angular features while neglecting continuous LF information. In contrast to previous work, we propose a self-supervised unconstrained neural light field (UNeLF) to continuously represent LF for LFASR. Specifically, any LF can be described as the camera pose for each sub-aperture image (SAI) and the two-plane that captures these SAIs. To describe the former, we introduce a SAIs-dependent pose optimization method to solve the issue that arises from the narrow baseline of most LF data, which hinders robust camera pose estimation. This mechanism reduces the number of trainable camera parameters from a quadratic to a constant scale, thereby alleviating the complexity of joint optimization. For the latter, we propose a novel adaptive two-plane parameterization strategy to determine the two-plane that captures these SAIs, facilitating refocusing. Finally, we jointly optimize the camera parameters, near-far planes and neural light field, efficiently mapping each adaptive two-plane parameterized ray to its correspondence color in a continuous manner. Comprehensive experiments demonstrate that UNeLF achieves faster training and inference with fewer computational resources while exhibiting superior performance on both synthetic and real-world datasets. © 1991-2012 ieee.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing IoT-Driven Smart Home Security and Automation with a GCN Model

Enhancing IoT-Driven Smart Home Security and Automation with...

引用

Integrated Circuits and Communication systems (ICICACS), ieee international conference on

作者： Sreelakshmi Ganti Ravi Kumar Vankayalapati P. Krishnamoorthy Pallavi S Thakare Ullal Akshatha Nayak P Vignesh Department of Electronics and Communication Engineering Geethanjali College of Engineering and Technology Medchal India Equinix Texas USA Department of Computer Science and Engineering Sasi Institute of Technology & Engineering West Godavari India Department of Information Technology Dr D. Y. Patil Institute of Technology Pimpri India Department of Information Science and Engineering Nitte Meenakshi Institute of Technology Bangalore India Department of Mathematics KCG College of Technology Chennai India

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

A network of computing devices and sensors, the Internet of Things (IoT) rapidly exchanges data to assess circumstances and propose new services. intelligent home technologies rely on IoT. Contemporary smart home systems offer automatic lighting control, smoke detectors, temperature sensors, and smart lock installations. But these technologies raise serious privacy and security concerns. Security flaws let hackers access sensitive data, sendoff false alarms, and take control monitoring systems. Smart home technology is vulnerable to many threats because consumers are wary of it. Recommended steps are preprocessing, sensing, and model training. Preparing raw, unstructured data for analysis. DHT11 humidity and temperature sensors and HC-SR501 PIR motion detectors collect data. It trained the model using Multiscale DGCN data. Better than GCN and BiLSTM, Multiscale DGCN performs. It uses Internet of Things-based smart home security data well, with an average accuracy rate of 93.87%. Identifying outliers in sensor data solves major smart home security challenges. Increasing smart home system accuracy reduces security concerns and boosts user trust, which may drive adoption.

关键词： Temperature sensors Accuracy Bidirectional long short term memory Smart homes DH-HEMTs Safety Security Internet of Things Integrated circuit modeling intelligent sensors

来源：评论

学校读者我要写书评

暂无评论

intelligent Rail Sentinel a perspective of Indian Railway

Intelligent Rail Sentinel a perspective of Indian Railway

引用

ieee Students' conference on Electrical, Electronics and Computer Science (SCEECS)

作者： Arun D. Limgaokar Sharvari S. Hinge Yash S. Vinchu Vivek S. Rane Prashant B. Patel Anup Vibhute Department of Instrumentation Engineering Dr. D.Y. Patil Institute of Technology Pimpri Pune Maharashtra India Pune India

ISBN: (数字)9798331529833

ISBN: (纸本)9798331529840

The paper presents a PLC and SCADA-based advanced safety system design for railway signaling and interlocking. While the Indian Railway systems are infrequently beset by issues, a solitary mishap over an extended timeframe might profoundly adversely affect various facets of life and property. These issues can be resolved through the implementation of interlocking and railway signaling systems. In railways, railway personnel continue to supervise the signaling and interlocking systems, which remain partially manual. The implementation of PLC and SCADA can effectively address these challenges. The primary objective of this paper is to examine dispatcher telecommunications with crews, telecommunications with signals governing switchgears, signals monitoring track temperature, and the acquisition and storage of real-time video through CCTV for telecommunications in emergencies and automatic railway gates. The proposed solution depends on PLCs that can execute signaling and interlocking functions automatically. Moreover, these processes can be altered, monitored, and corrected through the use of a SCADA system, hence minimizing human participation and alleviating safety issues.

关键词： Temperature sensors Temperature measurement Automation SCADA systems Switches Logic gates Rail transportation Telecommunications Safety System analysis and design

来源：评论

学校读者我要写书评

暂无评论

Technology-based sports performance enhancement: A conference review

Intelligent Sports and Health

引用

intelligent Sports and Health 2025年第2期1卷 98-102页

作者： Hongyou Liu School of Physical Education & Sports Science South China Normal University Guangzhou China

This review synthesizes the keynote presentations delivered at the 2024 international conference on Sports Technology and Performance Analysis (ICSTPA 2024), highlighting advances in the interdisciplinary development of science and technology applied to health promotion, sports performance and physical education. Real-time physiological monitoring via AI-powered wearable technologies (e.g., wearable ECG shirts and cuffless blood pressure systems) enables personalized health and metabolic management. Measurement techniques for athletic performance (i.e., vertical jumps) have evolved from traditional jump mats to advanced automated systems based on deep neural networks, significantly improving accuracy and applicability in diverse environments. Additionally, machine learning-driven analyses of extensive match datasets in sports such as squash and soccer have identified hidden tactical patterns, thus providing quantitative foundations for tactical and training optimizations. Moreover, interactive educational innovations have emerged from the integration of wearable devices, mobile applications, and observational coaching tools. A novel psychological-fatigue threshold (PFT) concept has also been introduced, which incorporates psychological factors into the evaluation of decision-making and tactical performance of soccer players under high-intensity conditions. The ICSTPA 2024 conference demonstrated that technology-driven innovations are profoundly reshaping sports performance enhancement, health management, and motor skill development. Future research directions highlighted include expanding the application of AI-driven tools for real-time feedback, further refinement of psychological assessment frameworks, and enhanced integration of technology within practical sports training environments.

关键词： Sports performance Motor skill acquisition Multidisciplinary interaction data-driven analysis

来源：评论

学校读者我要写书评

暂无评论

data processing, analysis and Machine Learning of Electrical Atomic Force Microscopy (AFM) in data Cube mode: conduction of a nanomaterial for Lithium-ion battery electrodes

Data processing, analysis and Machine Learning of Electrical...

引用

international Image Processing, Applications and systems conference (IPAS)

作者： Rosine Coq Germanicus Peter De Wolf Petr Klapetek Unicaen Ensicaen CNRS CRISMAT UMR6508 Normandie Univ Caen France Bruker Nano Surfaces Santa Barbara CA USA Czech Metrology Institute Brno Czech Republic

ISBN: (数字)9798331506520

ISBN: (纸本)9798331506537

With the increasing integration of functional systems, nanoscale characterization has become crucial not only for material investigation but also for advancing the understanding of local behavior and optimizing performances. This paper details data processing techniques and machine learning methodologies for the analysis and prediction of advanced electrical Atomic Force Microscopy datasets. The datasets are acquired using a hyperspectral data Cube approach, which combines both mapping and spectroscopy acquisitions. In the context of decarbonization and electrification, current challenges are related to energy storage and transport. A cathode material used in Lithium-ion battery electrodes is investigated for its electrical transport properties. To comprehensively characterize the electrical properties, the conductive mode of Atomic Force Microscopy is employed using the data Cube method, which enables current-voltage spectroscopy at each pixel of the acquisition. The analysis of experimental datasets reveals localized electrical behavior of the material’s components as a function of applied voltage. Furthermore, machine learning algorithms are employed to predict current maps and cluster distinct regions based on their electrical characteristics.

关键词： Lithium-ion batteries Atomic measurements Atomic force microscopy Spectroscopy Microscopy Force Conductivity Nanoscale devices Cathodes Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

Big data Infrastructures Using Apache Storm for Real-Time data Processing

Big Data Infrastructures Using Apache Storm for Real-Time Da...

引用

2025 international conference on intelligent Control, computing and Communications, IC3 2025

作者： Ranganathan, Chitra Sabapathy Sampathrajan, Rajeshkumar Reddy, P. L. Kishan Kumar Parkavi, S. Meenakshi, B. Sujatha, S. Mphasis Corporation Tamil Nadu Chennai India McKinsey & Company Fort WorthTX United States Department of Computer Science and Engineering Andhra Pradesh Guntur India Vel Tech High Tech Dr. Rangarajan Dr. Sakunthala Engineering College Department of Computer Science and Engineering Tamil Nadu Chennai India Sri Sairam Engineering College Department of Electrical and Electronics Engineering Tamil Nadu Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Biomedical Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331527495

Apache Storm-based Big data infrastructures strive to provide a scalable and fault-tolerant platform that will transform real-time data processing. The goal is to use Apache Storm's features to handle and analyze massive amounts of data in real-time, guaranteeing correct insights that are delivered promptly. The objective is to provide a solid foundation that can manage data moving at high speeds from many sources, allowing for analytics in real-time and continuous computing. The goal is to maximize throughput while reducing delay via architectural optimization and efficient data flow methods. The goal is to improve Apache Storm's capabilities and make sure data processes smoothly across dispersed systems by combining it with other big data technologies. The end goal is a robust system that can provide analytics on data in real-time, which will aid in decision-making across several industries, including banking, telecoms, and social media. Efficiency, scalability, and dependability in managing massive data streams are key considerations. The data flow topology dataset for 5 distinct components and 5 streams shows throughput values ranging from 2500 to 4100 tuples per second. Similarly, the fault tolerance and reliability dataset for 5 distinct nodes and 5 different intervals shows throughput values ranging from 700 to 1050 tuples per second. All these results are derived from real-time sensor data used for traffic monitoring. © 2025 ieee.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Enhancing Patient Privacy and data Security in Remote Healthcare Monitoring Using IoT and Wearable Technologies

Enhancing Patient Privacy and Data Security in Remote Health...

引用

2025 international conference on intelligent Control, computing and Communications, IC3 2025

作者： Singh, Navdeep Swetha, K. Al-Rubaye, Taqi Bahar, Tarannum Rajalakshmi, B. Anuradha, Kodali Lovely Professional University Phagwara India Mlr Institute of Technology Department of Computer Science and Engineering Telangana Hyderabad India College of Medical Technologies The Islamic University Department of Medical Laboratory Technology Najaf Iraq Galgotias university Department of Electrical Electronics & Communication Engineering Uttar Pradesh Gerater Noida203201 India New Horizon College of Engineering Department of Computer Science Engineering Bangalore India Griet Department of Information Technology Bachupally Telangana Hyderabad India

ISBN: (纸本)9798331527495

'Enhancing Patient Privacy and data Security in Remote Healthcare Monitoring Using IoT and Wearable Technologies' is a new approach to healthcare IT's major privacy and data security issues. Security must be updated as wearable gadgets and the Internet of Things (IoT) becomes increasingly widespread in remote healthcare tracking. Many people worry about online patient data security;thus, this study develops a thorough security solution that fits with current healthcare IT systems. A full security architecture with cutting-edge encryption techniques, real-time data transmission protocols, and flexible privacy safeguards is used. The recommended solution outperforms current security methods. A stronger 256-bit key protects patient data at a higher security level. Getting connection latency down to 20 ms speeds up remote healthcare systems. The proposed technique is resilient enough to withstand hostile attacks while maintaining healthcare services. The approach also allows real-world data analysis while preserving patients' identities 92% of the time. The strategy may be employed in complex healthcare IT since it balances data security and research. Overall, this study's findings are promising for safe medical technologies. The recommended method's superior encryption, quicker transmission, and reliable system have raised telehealth tracking privacy requirements. In healthcare IT, wearable technology and the Internet of Things are connecting swiftly. Better security procedures that prioritize patient privacy and data protection are outlined in this study. © 2025 ieee.

关键词： Sensitive data

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：