检索结果-内蒙古大学图书馆

3rd International conference on intelligent Systems and Applications, ICISA 2024

作者： Shaikh, Aman Ranjan, Nihar M. Rai, Satayush Rao, Pranil Ashok Shinde, Ganesh Department of Information Technology JSPM’s Rajarshi Shahu College of Engineering Pimpri-Chinchwad India

ISBN: (纸本)9789819798384

In the contemporary landscape, the agricultural sector has undergone transformational changes, embracing progressive dynamics through the integration of cutting-edge technologies and methodologies. The global adoption of IoT, AI/ML, and similar innovations reflects their capacity to furnish precise, reliable, and consistent outcomes, enabling data-driven decision-making. The amalgamation of IoT and ML models emerges as a strategic choice to enhance data analytics, aiming at a substantial improvement in both the quantity and quality of agricultural yields. This paper seeks to elucidate the synergistic interaction of various agrarian elements, orchestrating the computational prowess facilitated by ML models and data derived from IoT sensors transmitted through LoRa-based Wireless sensor Network (WSN) infrastructure. The proposed system advocates a comprehensive three-tier architectural framework, wherein ML and IoT systems collaborate seamlessly to process data for field management. The envisioned system extends its utility by translating these predictions into visually comprehensible representations. The integrated approach signifies a departure from conventional methods, offering a novel pathway to ensure the sustainability of yield, encompassing both production and grading standards. This paper thus contributes to the discourse on leveraging advanced technologies for agricultural optimization in response to evolving global demands. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

7th International Russian Automation conference, RusAutoCon 2024

7th International Russian Automation Conference, RusAutoCon ...

引用

7th International Russian Automation conference, RusAutoCon 2024

ISBN: (纸本)9783031824937

The proceedings contain 37 papers. The special focus in this conference is on Russian Automation. The topics include: Mapping and Path Planning Methods for Highly Automated Vehicles in Agriculture;morphological Analysis and Synthesis Features of Technological Processes;a Modern Method of Wireless Control of Unguarded Railway Crossings;duties and Obligations of the Railway Staff Concerned When the Microprocessorized Contactless Controlling Gauge Device Signal Is Triggered;integration of Automated Management Systems for Enterprises’ Transport and Technical Services;development of an Automation Module for Planning Trajectories for Painting Aircraft Fuselage Elements;identification of Metal Sheets in the Flow, Based on the Marking Imprint, Using Neural networks;study of the Performance of Adaptive sensor networks for Collecting and processing Thermoelectric Data;development and Research of a Cartographic Model for Municipal Planning as the Basis of an intelligent Geoinformation System;BIM Visual Programming of Bionic Architecture Construction Using Dynamo and Revit;development of a Model and Algorithms for Trigger Control of Technological Processes of Resource Provision;system for Statistical Assessment of Means of Controlling Engineers’ Qualification for information Support to Manage the Recruiting Process in Industry;smart Enumeration Technology;comparative Analysis of C-Band Conical Horn Antenna Sparse Structures Characteristics at Different Frequencies;software Implementation of Heuristic Methods of Optimization and Integration into a Cloud Service;computer System for Modeling Fluid Flow Around Bodies and Its Potential in Industry;the Effect of Regular and Irregular Segmentations on Characteristics and Charge Distribution Densities of Microstrip Lines;reinforcement Learning with External Teacher for Building Energy Management.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Stride Analysis Through Plantar Pressure

Comprehensive Stride Analysis Through Plantar Pressure

引用

International conference on Wireless Communications, Signal processing and Networking (WiSPNET)

作者： V Harsha Vardhan B Senthilnaathan Venkatasubramanian K Dept. of ECE Amrita Vishwa Vidyapeetham Chennai India

ISBN: (数字)9798331524227

ISBN: (纸本)9798331524234

The use of stride analysis extends to various domains, particularly in studying human plantar pressure. Most importantly, plantar pressure measurement is vital in the management and treatment of several conditions, including diabetes, trauma, stroke, ankle instability, sports injuries, and Parkinson’s disease. This study presents a comprehensive system for stride analysis using a smart insole embedded with piezoelectric sensors, capturing real-time pressure variations across different regions of the foot. The voltage signals generated by piezoelectric sensors in response to foot pressure are collected and then transmitted via Bluetooth to a Serial Bluetooth Terminal application for further processing, calibration, and mapping into meaningful pressure values. This system collects foot pressure changes from four essential regions, which it converts into heat maps to assist with the detection of gait and stride abnormalities. The results show that the developed system successfully measures foot pressure fluctuations as well as displays real-time information on walking patterns and weight distribution patterns. This system demonstrates its potential to support ongoing monitoring applications, which further benefits rehabilitation programs and helps reduce injuries and enhance athletic performance.

关键词： Wireless sensor networks Bluetooth sensor systems Real-time systems Pressure measurement Heat maps intelligent sensors Injuries Foot Diseases

来源：评论

学校读者我要写书评

暂无评论

A.I. at the Edge of the Edge: intelligent sensor Falling Detection for Humanoid Robot

A.I. at the Edge of the Edge: Intelligent Sensor Falling Det...

引用

IEEE International conference on Simulation, Modeling, and Programming for Autonomous Robots (SIMPAR)

作者： Giuseppe Messina Yuri Filistad Corrado Santoro System Research and Application STMicroelectronics Catania Italy Dep. of Mathematics and Comp.Science University of Catania Catania Italy

ISBN: (数字)9798331516857

ISBN: (纸本)9798331516864

This work addresses the problem of fall detection for humanoid robots using an intelligent sensor processing Unit (ISPU). The ISPU offloads the computational burden of robot movement tracking from the main microcontroller. An ad hoc dataset was created and used to train a Convolutional Neural Network (CNN) model for activity recognition. To accommodate the ISPU’s limited RAM, the CNN model was quantized. The system detects falls in real-time, enabling the robot to activate specific protection strategies based on the predicted fall direction. This innovative approach brings AI to the extreme edge, leveraging intelligent sensors to classify robot behaviors and reduce computational load on the microcontroller.

关键词： Microcontrollers Computational modeling Image edge detection Humanoid robots Robot sensing systems Real-time systems Convolutional neural networks Protection intelligent sensors Load modeling

来源：评论

学校读者我要写书评

暂无评论

Adaptive Asynchronous Gossip Algorithms for Consensus in Heterogeneous sensor networks

引用

IEEE Internet of Things Journal 2025年

作者： Ilic, Nemanja Vucetic, Miljan Makarov, Aleksej Petrovic, Ranko Punt, Marija College of Applied Technical Sciences School of Computing Union University Kruševac Belgrade Serbia Vlatacom Institute Belgrade Serbia VŠB - Technical University of Ostrava Ostrava Czech Republic University Singidunum Belgrade Serbia University of Belgrade School of Electrical Engineering Belgrade Serbia

The Internet of Things (IoT) connects a wide range of sensors and devices in environments that are often dynamic and resource-constrained, where efficient distributed solutions are essential for ensuring robust and scalable operation. This paper presents a novel adaptive consensus algorithm, tailored for distributed signal processing in heterogeneous sensor networks, with a focus on distributed estimation and target tracking. The algorithm addresses the challenge posed by networks where intelligent sensors have limited sensing, computation and communication capabilities, resulting in diverse quality of locally available information, and leading to neighbor-based information exchanges. It employs asynchronous gossip protocols to randomly exchange information between nodes, ensuring robustness to time synchronization and network topology uncertainties, while limiting computational and communication costs. The adaptation mechanism operates in two complementary ways. Firstly, we account for variations in the quality of local processing results, ensuring that asymptotic behavior of the consensus scheme accurately reflects this diversity. Secondly, we introduce a novel adaptation of the rates at which nodes initiate communication, using the available local information. This enables fast information dissemination, and provides a solution that is both effective and efficient. We show that, under appropriate network connectivity assumptions, the results obtained by the algorithm converge to the desired asymptotic values in the mean square sense. Numerical simulations demonstrate the algorithm's properties and effectiveness, particularly in modeling visual surveillance networks where fixed cameras are augmented by moving drones to extend the coverage area. © 2025 IEEE.

关键词： Adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

Multi-Resolution Mixer Network for Localization of Multiple sensors from Cumulative Power Measurements

Multi-Resolution Mixer Network for Localization of Multiple ...

引用

IEEE conference on Wireless Communications and Networking

作者： Md Mahmuddun Nabi Murad Daniel Kwabena Yirenya-Tawiah Thomas Weller Yasin Yilmaz Electrical Engineering Department University of South Florida Tampa USA Electrical Engineering Department Oregon State University Corvallis USA

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

Wireless sensor networks (WSNs) can consist of many inexpensive sensors that communicate using the same wireless channel. In some applications, localization of these sensors can be as crucial as collecting their monitoring data. As the number of sensors increases, the complexity of processing data in such large networks grows significantly. In general, localization methods in WSNs typically rely on data containing sensor-specific information. However, the problem becomes more challenging when data contains no sensor-specific information. To address this issue, we propose a mixer-based deep neural network to estimate sensor positions using the received cumulative signal strength that is devoid of explicit sensor-specific information. Our approach employs wavelet decomposition to extract information from the input time series, combined with patching, embedding, and mixer techniques for position estimation. We compare the performance of our model with a nonlinear Kalman filter-based state estimation method. Extensive evaluations using data generated from our simulator demonstrate that our method consistently outperforms the unscented Kalman filter (UKF) method across all scenarios.

关键词： Location awareness Wireless communication Wireless sensor networks Power measurement Time series analysis information filters sensors Kalman filters State estimation Mixers

来源：评论

学校读者我要写书评

暂无评论

Enhanced Infrared-Visible Image Fusion Method with an ISP Based Degradation Model

Enhanced Infrared-Visible Image Fusion Method with an ISP Ba...

引用

International conference on intelligent Control and information processing (ICICIP)

作者： Xueyi Guo Yisha Liu Weimin Xue Zhiwei Zhang Information Science and Technology College Dalian Maritime University Dalian China School of Control Science and Engineering Dalian University of Technology Dalian China

ISBN: (数字)9798331516147

ISBN: (纸本)9798331516154

The performance of infrared (IR) and visible (VIS) image fusion tasks depends on the quality of source images, which are usually impacted by various degradation factors in real-world scenarios, leading to poor quality and visual effects of the fused images. By learning the mapping from low-quality (LQ) source images to high-quality (HQ) fused images, neural networks can remove the impacts of degradation factors, generating HQ fused images. However, the lack of paired LQ source images and corresponding HQ fused images poses a significant challenge in training a fusion network. Considering the effectiveness of the image processing pipeline (ISP) in processing IR and VIS images, reversing specific steps of ISP can accurately simulate the image degradation process. Building upon this research, we propose a novel ISP-based degradation model that reverses several ISP steps while incorporating various degradation factors, thereby generating LQ IR and VIS images from source images to train the fusion network. Experimental results on multiple image fusion datasets demonstrate that our method significantly enhances the quality and visual effects of fused images.

关键词： Degradation Training Pipelines Neural networks Noise Process control sensor fusion Visual effects sensors Image fusion

来源：评论

学校读者我要写书评

暂无评论

Research on Multi-Target Tracking Method Based on Deep Learning

Research on Multi-Target Tracking Method Based on Deep Learn...

引用

sensors and information Technology (ICSI), International conference on

作者： Jingyi Luo Yongjie Zhang GuangXi Vocational Normal University China Guangxi Nanning Education Department of Guangxi Zhuang Autonomous Region Key Laboratory of Application Technology of intelligent connected vehicle (Guangxi Vocational Normal University)

ISBN: (数字)9798331542887

ISBN: (纸本)9798331542894

This paper investigates a deep learning-based multi-target tracking method, with the objective of addressing the challenges associated with target detection and tracking in high-density scenarios for self-driving cars. In a dynamically changing road environment, the target vehicle may become obscured, resulting in tracking failure. To address this challenge, this paper proposes a multi-sensor deep fusion technique. This technique aims to enhance the generalization of detection and tracking, thereby mitigating the impact of unexpected situations. Multi-sensor fusion technology is employed to systematically collect road information, which is then integrated with convolutional neural networks to achieve data fusion and obtain more comprehensive target information. In this paper, PreScan is utilized for the purpose of simulation and emulation experiments. The results of these experiments demonstrate that the deep learning-based multi-target tracking method can improve the generalization and accuracy of detection.

关键词： Deep learning Target tracking Accuracy Roads Urban areas Transportation sensor fusion Robustness Autonomous automobiles Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Enabled Secure IoT Module for Smart Agriculture in Diverse Environmental Conditions 14

Deep Learning Enabled Secure IoT Module for Smart Agricultur...

引用

14th IEEE International conference on Communication Systems and Network Technologies, CSNT 2025

作者： Ansari, Shaharyar Alam Ali, Salman Luqman, Mohammad Ahmad, Shahnawaz School of Computer Science Engineering and Technology Bennett University Greater Noida India Department of Computer Science Aligrah Muslim University Aligarh India

ISBN: (纸本)9798331531935

The Internet of Things (IoT) stands as a revolutionary technology which impacts smart agriculture and different sectors beyond it. The research describes an intelligent IoT-enabled monitoring system which uses sensors to bring improved agricultural performance through environmental real-time observations combined with artificial intelligence decision systems. The proposed system completes its operation by executing sensor data acquisition followed by deep learning-based analysis and secure data transmission procedures. The initial stage of IoT-enabled operation utilizes environment-sensing devices which collect essential parameters for precision farming. A Recurrent Neural Network (RNN) processing system applies classification methods to collected data to generate useful insights. Secure cloud data transmission takes place through an encryption system which combines Substitution-Caesar cipher with Improved Elliptic Curve Cryptography (IECC). The system demonstrates 99.64% accuracy, and the proposed encryption method proves efficiency through its average execution times of encryption at 0.3904 ms and decryption at 0.1102 ms which exceeds current models in speed and security performance. © 2025 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Vehicle information Monitoring and Identification on Highway Bridges Using an Array of Fiber Bragg Grating sensors and Deep Learning Algorithms 4

Vehicle Information Monitoring and Identification on Highway...

引用

4th International Computational Imaging conference, CITA 2024

作者： Duan, Zhenhui Zhang, Faxiang Jiang, Shaodong Sun, Zhihui Liu, Zhaoying Shen, Yongxu Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (纸本)9781510688834

Traditional traffic management methods are increasingly inadequate in coping with the growing pressure on traffic systems. Consequently, there is a need for a more intelligent and efficient approach to monitoring and identifying vehicle information. Current vehicle monitoring methods often suffer from environmental interference and limited coverage.. To address these challenges, we propose a novel method for monitoring and identifying vehicle information on bridges using an array of Fiber Bragg Grating (FBG) strain sensors, combined with a hybrid deep learning algorithm based on Discrete Wavelet Transform (DWT) and Convolutional Neural Network (CNN) with Long Short-Term Memory (LSTM). Strain data were collected from a continuous hollow slab beam on a section of a highway bridge. Vehicles were classified and labeled using on-site video data to create a dataset, which was subsequently used to train and test the proposed CNN-LSTM model. The results demonstrate that the proposed method can accurately identify and classify the lane position, vehicle type, and vehicle speed category, achieving detection accuracies of 94.0%, 93.11%, and 90.67%, respectively. The DWT-CNN-LSTM method, utilizing the FBG strain sensor array, leverages existing strain monitoring platforms, supplements current traffic monitoring systems, and offers high efficiency and cost-effectiveness. This approach provides valuable data references for management and statistical analysis. © 2025 SPIE.

关键词： Discrete wavelet transforms

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：