检索结果-内蒙古大学图书馆

22nd ieee International symposium on Parallel and Distributed Processing with applications, ISPA 2024

作者： Chen, Zidong Wang, Yan Cao, Sheng Zhang, Xiaosong School of Computer Science and Engineering China Yibin Park University of Electronic Science and Technology of China China

ISBN: (纸本)9798331509712

Federated learning has been introduced into network intrusion detection to address the data silos among intrusion detection systems in distributed environments. However, existing federated learning-based methods suffer from the problem of class-imbalanced traffic. Inspired by the Bayes theorem, we propose an adaptive cost weight-enabled federated distillation method for distributed network intrusion detection. The proposed method comprises a federated distillation module and a cost-sensitive module. The federated distillation module combines knowledge distillation and federated learning to establish a distributed intrusion detection system, ensuring data privacy while reducing the interaction overhead. The cost-sensitive module optimizes the federated distillation module by calculating posterior probabilities using prior probabilities and real-time observations from the client training process. By adjusting the model's attention to different samples based on the posterior probabilities, the method enhances the detection accuracy of intrusion detection models for classes with few samples. Experimental results show that the proposed method achieves state-of-the-art performance on the NSL-KDD dataset, with accuracy improvements of 5.6% and 3.6% compared to the FedAvg and FedProx algorithms, respectively. © 2024 ieee.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Simulating Synchronization Issues on a Multiprocessor embedded System for Testing 2

Simulating Synchronization Issues on a Multiprocessor Embedd...

引用

2nd International Conference on Business Analytics for technology and Security, ICBATS 2023

作者： Zafar, Fareeha Ahmad, Saeed Amjad, Muhammad Waqar, Nazish Al-Khasawneh, Mahmoud Ahmad Ali, Sehrish GC University Lahore Department of Computer Science Pakistan Riphah International University Lahore Pakistan Administration and Economics National College of Business Lahore Pakistan Applied Science Private University Applied Science Research Center Amman11937 Jordan Skyline University College School of Information Technology University City Sharjah Sharjah1797 United Arab Emirates

ISBN: (纸本)9798350335644

Widely used embedded systems are applied to conquer the rapidly increasing demands of embedded systems of today, which start with a simple home device to systems with extensive architecture. They can perform a number of complex jobs in a lot of working conditions. The most common issue faced by embedded software is synchronization and it is used to maintain system integrity while conducting applications, the processing. While testing multi-PEs-based embedded systems is more complex to undertake so these issues are focused on synchronous or asynchronous real-time inter-processor communication in order to improve accuracy and timing. The research introduces a method for possible synchronization challenges across PEs. © 2023 ieee.

关键词： embedded systems

来源：评论

学校读者我要写书评

暂无评论

A Robust Framework for Online Fault Detection in Environmental Monitoring Using Pretrained Probabilistic Models 17

A Robust Framework for Online Fault Detection in Environment...

引用

17th International Conference on COMmunication Systems and NETworkS, COMSNETS 2025

作者： Dash, Ritwik Sagar, Kasturi Gyanaguna Jenamani, Mamata Indian Institute of Technology Industrial & Systems Engineering Kharagpur India

ISBN: (纸本)9798331531195

Accurate detection and classification of sensor faults are vital for maintaining the integrity and reliability of air quality monitoring systems, where faulty data can degrade decision-making and hinder timely environmental interventions. Thus, early identification of such anomalies is critical for the deployment of fault-tolerant systems, specifically in environmental monitoring. The concept of pretrained probabilistic time series models is utilized to design a framework for online fault detection in the AQI(Air Quality Index) Monitoring applications. The framework tokenizes the multivariate sensor data through scaling and quantization into a fixed vocabulary and leverages transformer-based language model architectures trained via cross-entropy loss on these tokenized values. The performance of the proposed framework is also evaluated across a range of fault injection scenarios, testing its robustness and efficiency. The model consistently demonstrates strong fault detection capabilities, maintaining high accuracy and reliability even under varying levels of artificially induced sensor faults, further outperforming classical methods and specialized models for air quality monitoring. The evaluation results of the proposed method demonstrate a fault detection rate that exceeds 95% in all scenarios while effectively categorizing faults in data quality monitoring systems at the sensor node level. © 2025 ieee.

关键词： Environmental monitoring

来源：评论

学校读者我要写书评

暂无评论

Tiny Machine Learning for Damage Classification in Concrete Using Acoustic Emission Signals

Tiny Machine Learning for Damage Classification in Concrete ...

引用

ieee International Instrumentation and Measurement technology Conference (I2MTC) - Rising Above Covid-19

作者： Adin, Veysi Zhang, Yuxuan Oelmann, Bengt Bader, Sebastian Mid Sweden Univ Dept Elect Design Sundsvall Sweden

ISBN: (纸本)9781665453837

Acoustic emission (AE) is a widely used nondestructive test method in structural health monitoring applications to identify the damage type in the material. Usually, the analysis of the AE signal is done by using traditional parameter-based methods. Recently, machine learning methods showed promising results for the analysis of AE signals. However, these machine learning models are complex, slow, and consume significant amounts of energy. To address these limitations and to explore the trade-off between model complexity and the classification accuracy, this paper presents a lightweight artificial neural network model to classify damage types in concrete material using raw acoustic emission signals. The model consists of one hidden layer with four neurons and is trained on a public acoustic emission signal dataset. The created model is deployed to several microcontrollers and the performance of the model is evaluated and compared with a state-of-the-art machine learning model. The model achieves 98.4% accuracy on the test data with only 4019 parameters. In terms of evaluation metrics, the proposed tiny machine learning model outperforms previously proposed models 10 to 1000 times. The proposed model thus enables machine learning in real-time structural health monitoring applications.

关键词： TinyML damage classification acoustic emission structural-health-monitoring embedded systems IoT machine learning

来源：评论

学校读者我要写书评

暂无评论

Smart Early Fire and Smoke Detection with Transfer Learning

Smart Early Fire and Smoke Detection with Transfer Learning

引用

2024 ieee Region 10 symposium, TENSYMP 2024

作者： Srinivas, Padmasri Uma Maheshwari, D. Jha, Sanjeev Kumar Bajpai, Ishant Lalmohan, K.S. School of Transdisciplinary Innovation University of Technology Sydney Sydney Australia School of Computing Sastra University Thanjavur India Nielit Data Science dept. Chennai India Nielit Embedded Systems dept. Chennai India Nielit Chennai India

ISBN: (纸本)9798350364866

In this study, a low latent edge-based fire and smoke detection and alert system was designed to detect and prevent indoor fires caused by human or machine faults, or lack of appropriate fire safety measures. To live comfortably in this fast-paced society, safety is a must. To detect early signs of fire, smoke and flammable gases, a real-time fire detection system was developed by combining a Raspberry Pi and a Raspberry Pi camera v2. Images taken from an open-source fire and smoke dataset were annotated and fed to the models. The model selection involved training YOLOv4-tiny, YOLOv5s TensorFlow lite pre-trained models, and deploying the most feasible transfer learned model having a higher mean average precision (mAP) on Raspberry Pi, which acts as the edge device. It performs real-time analysis of live feed captured by a Raspberry Pi camera, sends email alerts to the user stating confirmation of the presence of fire or smoke, and prevents false alarms caused due to the data collected by IoT devices by conducting a double check with the captured feed for detection. The user can act upon this notification and ensure timely preventive action. The proposed state-of-the-art indoor alert system achieves a mean average precision (mAP) of 42.3 for fire, 35.4 for smoke classes;a precision of 58.5 for fire, 64.3 for smoke and a recall of 45.9 for fire and 33.3 for smoke respectively. If the system is improved in the future, it is expected that it will be able to give faster and more accurate alerts. © 2024 ieee.

关键词： Smoke detectors

来源：评论

学校读者我要写书评

暂无评论

Secure Coordinate Rotation in embedded Systems Using Homomorphic Encryption: Implementation and Evaluation on the AI-Saqr Platform 1

Secure Coordinate Rotation in Embedded Systems Using Homomor...

引用

1st International Conference on Cryptography and Information Security, VCRIS 2024

作者： Parmar, Yashrajsinh Caullery, Florian Kale, Sonali Secure Systems Research Center Technology Innovation Institute Abu Dhabi United Arab Emirates

ISBN: (纸本)9798331529949

This paper explores the viability of a method for performing coordinate rotation on encrypted data within a drone's mission computer. Utilizing the Joye-Libert additively Homomorphic Encryption scheme, we implement the CORDIC (COordinate-Rotation DIgital Computer) algorithm, optimized for addition operations, on the AI-Saqr system-on-chip platform, a RISC-V open-source SoC. This approach ensures data confiden-tiality and computational efficiency in real-time embedded applications. Our experimental results demonstrate the feasibility and performance trade-offs of integrating homomorphic encryption with the CORDIC algorithm, offering significant advancements in secure computations for unmanned aerial systems. To the best of our knowledge, this work, is the first of it's kind to present a vector rotation based computation scheme for encrypted vectors. © 2024 ieee.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Speech Emotion Recognition Using GRU and LSTM

Speech Emotion Recognition Using GRU and LSTM

引用

2024 ieee Region 10 symposium, TENSYMP 2024

作者： Sharma, Vriti Raushan, Ritik Verma, Ruchi Gupta, P.K. School of Computing and Electrical Engineering Iit Mandi HP India Jaypee University of Information Technology Department of Cse HP Solan173 234 India School of Computing Mohan Babu University Department of Data Science AP Tirupati517 102 India

ISBN: (纸本)9798350364866

Speech emotion recognition (SER) is a hot topic in research, with applications in human-computer interaction, mental health screening, and customer service. In this research, our objective is to develop an accurate and reliable SER system capable of emotion recognition in speech data. We address important issues such as feature extraction, model selection, data imbalance, robustness, and real-time inference using a labeled dataset of various emotional expressions in voice. To extract complicated shapes from auditory characteristics, our method combines deep learning techniques that include long-short-term memory (LSTM) and gated recurrent units (GRU). We carefully manage the data imbalance to ensure that emotions are fairly represented in the training set, and with the implementation of our functional LSTM and GRU models in the training set, we were able to achieve the precision of 62 % and 90 %, respectively. © 2024 ieee.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Adaptive Subsampling for ROI-Based Visual Tracking: Algorithms and FPGA Implementation

引用

ieee ACCESS 2022年 10卷 90507-90522页

作者： Iqbal, Odrika Muro, Victor Isaac Torres Katoch, Sameeksha Spanias, Andreas Jayasuriya, Suren Arizona State Univ Sch Elect Comp & Energy Engn Tempe AZ 85281 USA

There is tremendous scope for improving the energy efficiency of embedded vision systems by incorporating programmable region-of-interest (ROI) readout in the image sensor design. In this work, we study how ROI programmability can be leveraged for vision applications by anticipating where the ROI will be located in future frames and switching pixels off outside of this region. We refer to this process of ROI prediction and corresponding sensor configuration as adaptive subsampling. Our adaptive subsampling algorithms comprise an object detector and an ROI predictor (Kalman filter) which operate in conjunction to optimize the energy efficiency of the vision pipeline with the end task being object tracking. To further facilitate the implementation of our adaptive algorithms in real systems, we select a candidate algorithm and map it onto an FPGA. Leveraging Xilinx Vitis AI tools, we designed and accelerated a YOLO object detector-based adaptive subsampling algorithm. In order to further improve the algorithm post-deployment, we evaluated several competing baselines on the OTB100 and LaSOT datasets. We found that coupling the ECO tracker with the Kalman filter has a competitive AUC score of 0.4568 and 0.3471 on the OTB100 and LaSOT datasets respectively. Further, the power efficiency of this algorithm is on par with, and in a couple of instances superior to, the other baselines. The ECO-based algorithm incurs a power consumption of approximately 4 W averaged across both datasets while the YOLO-based approach requires power consumption of approximately 6 W (as per our power consumption model). In terms of accuracy-latency tradeoff, the ECO-based algorithm provides near-real-time performance (19.23 FPS) while managing to attain competitive tracking precision.

关键词： Field programmable gate arrays Kalman filters Energy efficiency embedded systems Power demand Image sensors Visualization Computer vision Hardware design languages Object tracking Adaptive subsampling embedded computer vision FPGA acceleration hardware software co-design single object tracking vision applications

来源：评论

学校读者我要写书评

暂无评论

Cache Behavior Analysis with SP-Relative Addressing for WCET Estimation 10th

Cache Behavior Analysis with SP-Relative Addressing for WC...

引用

10th International symposium on Dependable Software Engineering: Theories, Tools and applications, SETTA 2024

作者： Xiao, Shangshang Sun, Mengxia Zhang, Wei Zhan, Naijun Ju, Lei School of Cyber Science and Technology Shandong University Qingdao China Quan Cheng Laboratory Jinan China School of Computer Science Peking University Beijing China

ISBN: (纸本)9789819606016

Accurately bounding the worst-case execution time (WCET) is crucial for efficient real-time system design. Precisely analyzing whether a memory reference results in a cache miss or a cache hit significantly impacts the accuracy of the estimated WCET bound, as the latency of a cache miss is typically two orders of magnitude higher than that of a cache hit access. SP-relative addressing enables dynamic memory allocation on the stack, enhances thread safety, an therefore is widely adopted in embedded real-time systems. However, existing cache behavior analysis requires obtaining the exact address of each memory reference and pessimistically assumes that SP-relative addressing could access any memory address, resulting in an overestimated WCET bound. In this paper, we propose a new WCET analysis framework that first identifies the program segments in which the SP value remains constant for a accurate cache behavior analysis, and then comprehensively compute the WCET of the whole program based on the constraints between the SP value defined by the program’s control flow. Experimental results show that, our method can tighten the estimated WCET bound by up to 36.31% and achieve an average improvement of 11.85%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： embedded systems

来源：评论

学校读者我要写书评

暂无评论

Secure Communication in IoT-enabled embedded Systems for Military applications using Encryption 2

Secure Communication in IoT-enabled Embedded Systems for Mil...

引用

2nd International Conference on Edge Computing and applications, ICECAA 2023

作者： Kannan, B. Maruthu Solainayagi, P. Azath, H. Murugan, Subbiah Srinivasan, C. Sphoorthy Engineering College Department of Computer Science and Engineering Nadergul Telangana Hyderabad India Aarupadai Veedu Institute of Technology Department of Computer Science and Engineering Tamil Nadu Paiyanoor India School of Computer Science and Engineering Vit Bhopal University Madhya Pradesh Bhopal India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Biomedical Engineering Tamil Nadu Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350347579

real-time monitoring and analysis of data from various sources have been made possible due to the growth of Internet of Things (IoT)-enabled embedded systems in military applications. This has allowed improved situational awareness and the identification of potential threats. However, it is essential that the communication between these systems to be protected against illegal access and intervention to maintain their integrity. This research study investigates whether or not it is possible to have encrypted communication in embedded systems that make use of the IoT for military purposes. It gives an overview of the many security protocols and algorithms that may be used to secure communication, along with the problems and constraints that such protocols and algorithms provide. Case studies and examples of how secure transmission has been deployed in real-world military applications are covered along with the lessons learned and best practices for moving forward with the technology's development. This article emphasizes the significance of encrypted communication in military applications and its role in protecting the safety and security of soldiers and equipment. © 2023 ieee.

关键词： Cryptography

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：