检索结果-内蒙古大学图书馆

2nd International conference on Machine Learning and Autonomous systems, ICMLAS 2025

作者： Usha, V. Karagatla, Sandeep Gowr, P. Sheela Jegathambal, P.M.G. Lizy, A. Sathya, V. Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Dept. of CSE Chennai India Chennai India Vels Institute of Science Technology & Advanced Studies Chennai India Institute of Science and Technology Dept. of Artificial Intelligence and Machine Learning Chennai India Velammal Engineering College Dept of Information Technology Chennai India

ISBN: (纸本)9798331505745

The Internet of Things (IoT) grounded solution of Real Time Global Positioning System (GPS) tracking with Health Monitoring of Animals for Owners to track their animals like cows, buffaloes, dogs etc. This GPS module and a heartbeat sensor are attached to the animals in order to be able to follow them closely. This data is sent to a mobile app, and the owner can see their heart on the map as well as monitor its pulse. Based on analysis of such heart rate variations, the system determines when it is seeing an abnormal activity related to e.g. stress (increased heart rate) or potential health risks (no sign of a heartbeat), which could be interpreted as fear or death. Each animal has an initial heart rate level that is set, and when this rate exceeds it, the system sounds an alert to indicate danger. This method is especially helpful for keeping an eye on animals in urban areas, areas close to forests, and areas with high rates of theft and loss. The project demonstrates the successful execution of a reliable, real-time animal monitoring system with practical applications in both urban and rural environments. © 2025 IEEE.

关键词： Animal Safety GPS Tracking Heartbeat sensor LoRa device Mobile Application Real-time Monitoring

来源：评论

学校读者我要写书评

暂无评论

GIIDS: Generalized Intelligent Intrusion Detection System for Heterogeneous UAVs in UAM 27

GIIDS: Generalized Intelligent Intrusion Detection System fo...

引用

27th International conference on advanced Communications Technology, ICACT 2025

作者： Kabir, Fahmina Mowla, Nishat I. Doh, Inshil Division of Artificial Intelligence and Software Ewha Womans University Seoul Korea Republic of Department of Industrial Systems RISE Research Institutes of Sweden Sundsvall Sweden Department of Cyber Security Ewha Womans University Seoul Korea Republic of

ISBN: (纸本)9791188428137

Unmanned Aerial Vehicles (UAVs) are increasingly integral in various sectors, simultaneously encountering rising security threats as UAV and Urban Air Mobility (UAM) networks continue to expand. This paper addresses the challenge of securing UAM networks while also emphasizing generalizability of the security solution to protect heterogeneous UAVs against threats that compromise their stability, reliability and can cause catastrophic failures such as a crash landing. The deployment of traditional machine learning (ML) based intrusion detection systems (IDSs) is often hampered in real-world applications due to a lack of generalizability of the security solution. As a result, the system fails to provide adequate security across the varying models and platforms of UAVs, each with its unique statistical properties and data distributions. To address these challenges, we focus on employing a comprehensive set of UAV sensor parameters, tailored feature engineering and selection to develop multi-stage cross-validated ensemble learning systems to facilitate generalized detection of attack and non-attack cases. For additional analysis, we cross-validate the models using two different cross-validation techniques. The proposed stacking ensemble systems provide the overall best performance, with AUC within the range of 92% to 100% across different crossvalidations. Copyright 2025 Global IT Research Institute (GIRI). All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Lora-Enabled System for Smart Farming Management and Oversight, Utilizing Wireless sensor Networks 14

Lora-Enabled System for Smart Farming Management and Oversig...

引用

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

作者： Elumalai, J. Kumuthapriya, K. Hema, R. Sundaram, P. Sakthi Shunmuga Department of Electronics and Communication Engineering S.K.R Engineering College Ponamallee Chennai600123 India Department of Electronics and Communication Engineering Tagore Engineering College Rathinamangalam Kelambakkam - Vandalur Rd Tamil Nadu Chennai600127 India

ISBN: (纸本)9798331531935

The purpose of this study is to create a LoRa-based smart farming management and surveillance system. Utilizing Wireless sensor Networks (WSNs) in rural settings, with the aim of replacing the existing technology in agricultural monitoring systems. A dedicated private network server is established and connected to a gateway, which gathers information or signals from the nodes at the end and sends this data to the cloud without the need for routers. This data can then be utilized for various applications by the end users. The system overcomes issues related to communication failures and energy-efficient data transmission. This advanced farming platform enhances the effectiveness of farming methods. The proposed methodology is the application of resources including as water, fertilizers, and pesticides should be optimized in order to achieve maximum efficiency while simultaneously minimizing waste. Farming productivity and sustainability are both significantly improved because of its contribution, notably in terms of the efficient management of resources. And intelligent cities used to improve agriculture-comparing the planned weather station and the numerous developed patents. The technique here is like a cutting-edge, reasonably priced choice for local weather monitoring. © 2025 IEEE.

关键词： Agricultural robots

来源：评论

学校读者我要写书评

暂无评论

Piezoelectric MEMS Mirror Based SPAD LiDAR System Enabling Real-Time Monitoring Across Large Covered Areas for Smart Factory applications 24

Piezoelectric MEMS Mirror Based SPAD LiDAR System Enabling R...

引用

2025 conference on MOEMS and Miniaturized systems

作者： Hwang, J. -Y. Henschke, A. Wysocki, L. Raschdorf, P. Ligges, M. Kasischke, M. Mensing, M. Kapels, H. Gu-Stoppel, S. Fraunhofer Inst Silicon Technol Fraunhoferstr 1 D-25524 Itzehoe Germany Fraunhofer Inst Microelectron Circuits & Syst D-47057 Duisburg Germany

ISBN: (数字)9781510685130

ISBN: (纸本)9781510685123;9781510685130

This paper presents a MEMS mirror based SPAD LiDAR system that monitors the surrounding in smart factories. The proposed LiDAR system enables safety monitoring in real-time by acquiring spatial and depth information of the region of interest in a production scenario where workers and machines coexist. This sensor system features a MEMS mirror using piezoelectric material AlN and wafer-level packaging that steers the diverged laser beam with a wavelength of 915 nm for a large field of view. In addition, a CMOS based SPAD pixel array is deployed to detect the target region and thus the improved detector performance can be achieved. This study includes the lens system design for an effective LiDAR illumination part and the evaluation results of real-time object and human detection with the prototype LiDAR sensor system.

关键词： Light detection and ranging (LiDAR) laser beam steering (LBS) microelectromechanical systems (MEMS) mirror single-photon avalanche diode (SPAD) smart factory human-machine collaboration

来源：评论

学校读者我要写书评

暂无评论

AlloyStack: A Library Operating System for Serverless Workflow applications 25

AlloyStack: A Library Operating System for Serverless Workfl...

引用

20th European conference on Computer systems-EuroSys

作者： You, Jianing Chen, Kang Zhao, Laiping Li, Yiming Chen, Yichi Du, Yuxuan Wang, Yanjie Wen, Luhang Hu, Keyang Li, Keqiu Tianjin Univ Coll Intelligence & Comp Tianjin Key Lab Adv Networking Tianjin Peoples R China Tsinghua Univ Beijing Peoples R China

ISBN: (纸本)9798400711961

Serverless workflow applications, composed of multiple serverless functions, are increasingly popular in production. However, inter-function communication and cold start latency remain key performance bottlenecks. This paper introduces AlloyStack, a library operating system (LibOS) tailored for serverless workflows. AlloyStack addresses two major challenges: (1) reducing cold start latency through on-demand OS component loading and (2) minimizing data transfer overhead by enabling functions within the same workflow to share a single address space, eliminating unnecessary data copying. To ensure secure isolation, AlloyStack uses Memory Protection Keys (MPK) to separate user functions from the LibOS while maintaining efficient data sharing. Our evaluation shows that AlloyStack reduces cold start times by 98.5% to just 1.3ms. Compared to SOTA systems, AlloyStack achieves a 7.3x to 38.7x speedup in Rust end-to-end latency and a 4.8x to 78.3x speedup in other languages for intermediate data-intensive workflows.

关键词： Serverless Computing Cold Start Data Transfer

来源：评论

学校读者我要写书评

暂无评论

H∞ fusion estimation for sensor network systems under DoS attacks

H∞ fusion estimation for sensor network systems under DoS a...

引用

2024 International conference on Mechatronic Engineering and Artificial Intelligence, MEAI 2024

作者： Wang, Chun xie, Zuozhang Chen, xixing xue, Lisha Zhou, Ting xie, Li Institute of Digital Technology and Instrumentation Zhejiang University Hangzhou310027 China Zhejiang Institute of Public Safety Technology 88 Lianhui Rd. Hangzhou310051 China School of Economics Zhejiang University Hangzhou310058 China

ISBN: (纸本)9781510689176

sensor network systems are essential for numerous technological applications. However, the vulnerability to cyber threats can severely affect both performance and security of the systems. The problem of H∞ fusion estimation is explored for sensor network systems under the influence of Denial-of-Service (DoS) attacks. To address this problem, a Luenberger-type local state estimator is specifically designed to compensates for sensor data affected by DoS attacks using the estimated data. These estimations are subsequently forwarded to a fusion center for comprehensive analysis and processing, with the aim of improving the reliability and precision of the sensor networks systems. By use of Lyapunov stability analysis, the sufficient conditions are established to ensure the boundedness of fused estimation errors and H∞ performance. The required gains for the local estimator and fusion weight matrices are determined by solving a series of linear matrix inequalities, which guarantees the stability and convergence of the fusion estimation systems. Finally, the effectiveness of the proposed fusion scheme are authenticated via simulation experiments. © 2025 SPIE.

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

A MEMS Pressure sensor Array for Sleep Apnea Recognition and Monitoring Based on The Principle of Traditional Chinese Medicine 38

A MEMS Pressure Sensor Array for Sleep Apnea Recognition and...

引用

38th IEEE International conference on Micro Electro Mechanical systems, MEMS 2025

作者： Qin, Lin Cheng, Long Zeng, xianzhang xia, Yuanlin Wang, Zhuqing Sichuan University School of Mechanical Engineering China Sichuan University Med + X Center for Manufacturing West China Hospital Chengdu China

ISBN: (纸本)9798331508890

This paper reports a novel MEMS-based pressure sensor array, inspired by traditional Chinese medicine, for detecting and identifying pulse signals. A multi-dimensional pulse acquisition array was developed by emulating traditional Chinese pulse diagnosis techniques to capture pulse signals at the cun, guan, and chi positions along the radial artery. A database was created with pulse signals recorded under normal breathing and breath-holding conditions. These features were used to train a support vector machine (SVM) classification model. The experimental results show that the model achieved high accuracy (99.33%) and sensitivity (98%) in detecting sleep apnea. Overall, this system could offer innovative technical support and promising applications for modernizing traditional Chinese diagnostic methods and developing smart healthcare devices. © 2025 IEEE.

关键词： Sleep research

来源：评论

学校读者我要写书评

暂无评论

An electromagnetic indirect-driving scanning mirror for wide-field coaxial LiDAR applications 24

An electromagnetic indirect-driving scanning mirror for wide...

引用

2025 conference on MOEMS and Miniaturized systems

作者： Li, Shuangliang Wang, Di Song, Dezhen Zou, Jun Texas A&M Univ Dept Elect & Comp Engn College Stn TX 77843 USA Texas A&M Univ Dept Comp Sci & Engn College Stn TX 77843 USA

ISBN: (数字)9781510685130

ISBN: (纸本)9781510685123;9781510685130

This paper reports an electromagnetic indirect-driving scanning mirror with an enlarged mirror plate (17 mm x 17 mm) supported by high-strength polymer hinges for wide-field coaxial LiDAR (Light Detection and Ranging) applications. An indirect-driving mechanism was developed to achieve large tilting angle through mechanical amplification, while maintaining a relatively high resonance frequency of the enlarged mirror plate. A prototype mirror was designed, fabricated, and tested. A Hall scan position sensor was integrated to monitor the pose of the mirror in real time. The testing results show a coupled resonance frequency of 54.9 Hz with an optical tilting angle of +/- 60 degrees, corresponding to a field of view (FoV) of 120 degrees. A wide-field coaxial LiDAR setup was also built based on the indirect-driving scanning mirror, and 2D imaging was demonstrated.

关键词： Micro scanning mirrors LiDAR mechanical coupling indirect driving scan position sensing

来源：评论

学校读者我要写书评

暂无评论

TUNA: Tuning Unstable and Noisy Cloud applications 25

TUNA: Tuning Unstable and Noisy Cloud Applications

引用

20th European conference on Computer systems-EuroSys

作者： Freischuetz, Johannes Kanellis, Konstantinos Kroth, Brian Venkataraman, Shivaram Univ Wisconsin Madison Madison WI 53706 USA Microsoft Gray Syst Lab Madison WI USA

ISBN: (纸本)9798400711961

Autotuning plays a pivotal role in optimizing the performance of systems, particularly in large-scale cloud deployments. One of the main challenges in performing autotuning in the cloud arises from performance variability. We first investigate the extent to which noise slows autotuning and find that as little as 5% noise can lead to a 2.5x slowdown in converging to the best-performing configuration. We measure the magnitude of noise in cloud computing settings and find that while some components (CPU, disk) have almost no performance variability, there are still sources of significant variability (caches, memory). Furthermore, variability leads to autotuning finding unstable configurations. As many as 63.3% of the configurations selected as "best" during tuning can have their performance degrade by 30% or more when deployed. Using this as motivation, we propose a novel approach to improve the efficiency of autotuning systems by (a) detecting and removing outlier configurations and (b) using ML-based approaches to provide a more stable true signal of de-noised experiment results to the optimizer. The resulting system, TUNA (Tuning Unstable and Noisy Cloud applications) enables faster convergence and robust configurations. Tuning PostgreSQL running mssales, an enterprise production workload, we find that TUNA can lead to 1.88x lower running time on average with 2.58.. lower standard deviation compared to traditional sampling methodologies.

关键词： Bayesian Optimization Autotuning Performance Tuning Noise Reduction Performance Variability

来源：评论

学校读者我要写书评

暂无评论

Simultaneous enhancement of sensitivity, resonant frequency, and overload capability of piezoresistive accelerometers by heavily-doped fillet structures on sensing beams

引用

IEEE sensors Journal 2025年第11期25卷 19138-19146页

作者： xia, Yong Wang, Tao Lv, Yang Han, xiangguang Yu, Mingzhi Tan, Renjie Huang, Mimi Jia, Chen Zhao, Libo Sun, Lin Yang, Ping Lu, Dejiang Xi'an Jiaotong University School of Mechanical Engineering State Key Laboratory for Manufacturing Systems Engineering International Joint Laboratory for Micro/Nano Manufacturing and Measurement Technologies Xi'an710049 China Ningbo CRRC Times Transducer Technology Co. LTD Department of Basic Research and Development Ningbo315021 China Research Institute for Intelligent Sensing Technology and System School of Instrument Science and Technology State Key Laboratory for Manufacturing Systems Engineering State Industry-Education Integration Center for Medical Innovations International Joint Laboratory for Micro/Nano Manufacturing and Measurement Technologies Xi'an Jiaotong University Xi'an710049 China Shandong Laboratory of Advanced Materials and green Manufacturing at Yantai Yantai264000 China

High sensitivity, high natural frequency, and high overload capability are desired for accelerometers used in industrial applications, but simultaneously enhancing all is challenging. Here, via designing novel heavily-doped fillet structures, we prove the sensitivity, resonant frequency, and overload capability can be simultaneously enhanced. The enhancements are attributed to regulations of stress concentration and effective sensing regions by the heavily-doped fillets. The sensors with and without fillets are designed, fabricated, packaged, and tested. The results show a sensitivity of 0.31±0.02 mV/g@5V, a natural frequency of 37.87±2.09 kHz, and an overload of 10040.17±531.76 g for sensors with 10-μm fillets, which are superior to 0.27±0.01 mV/g@5V, 34.13±0.90 kHz, and 7368.55±843.92 g for those no-fillet counterparts. Additionally, the developed sensor further exhibited feasibility in air-bearing vibration monitoring. The proposed design is envisioned to give insights into the novel designs of high-performance stress-based sensors, including accelerometers, pressure sensors, and strain gauges. © 2001-2012 IEEE.

关键词： Strain gages

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：