检索结果-内蒙古大学图书馆

Supervised Learning for Real-time Model Predictive Control Leveraging Multi-parametric Mixed Integer Quadratic Programming

引用

Journal of Institute of Control, Robotics and Systems 2025年第2期31卷 98-105页

作者： Yoo, Seungjun Gwon, Minwoo Kim, Kwang-Ki Department of Electrical and Computer Engineering Inha University Korea Republic of

This paper presents a novel supervised learning framework for real-time optimization of multi-parametric mixed-integer quadratic programming (mp-MIQP) problems. The framework utilizes a multi-layer perceptron (MLP) model to efficiently predict both continuous and binary control inputs while classifying the feasibility of the optimization problem. To address the computational burden of branch-and-bound methods and the memory limitations of explicit model predictive control (MPC), this framework learns optimal control inputs across diverse system states and prediction horizons through offline training. Comparative evaluations reveal that the proposed method significantly outperforms traditional approaches in computational speed and memory efficiency while maintaining high accuracy in approximating optimal solutions. These advancements position the framework as a transformative solution for real-time control applications, offering a robust and efficient alternative for online optimization in mp-MIQP problems. © ICROS 2025.

关键词： Mixed-integer linear programming

来源：评论

学校读者我要写书评

暂无评论

Privacy-preserving explainable AI: a survey

引用

science China(Information sciences) 2025年第1期68卷 23-56页

作者： Thanh Tam NGUYEN Thanh Trung HUYNH Zhao REN Thanh Toan NGUYEN Phi Le NGUYEN Hongzhi YIN Quoc Viet Hung NGUYEN School of Information and Communication Technology Griffith University School of Computer and Communication Sciences Ecole Polytechnique Federale de Lausanne Faculty of Mathematics and Computer Science University of Bremen Faculty of Information Technology HUTECH University Department of Computer Science Hanoi University of Science and Technology School of Electrical Engineering and Computer Science The University of Queensland

As the adoption of explainable AI(XAI) continues to expand, the urgency to address its privacy implications intensifies. Despite a growing corpus of research in AI privacy and explainability, there is little attention on privacy-preserving model explanations. This article presents the first thorough survey about privacy attacks on model explanations and their countermeasures. Our contribution to this field comprises a thorough analysis of research papers with a connected taxonomy that facilitates the categorization of privacy attacks and countermeasures based on the targeted explanations. This work also includes an initial investigation into the causes of privacy leaks. Finally, we discuss unresolved issues and prospective research directions uncovered in our analysis. This survey aims to be a valuable resource for the research community and offers clear insights for those new to this domain. To support ongoing research, we have established an online resource repository, which will be continuously updated with new and relevant findings.

关键词： privacy-preserving explainable AI privacy attacks privacy defences PrivEx PPXAI

来源：评论

学校读者我要写书评

暂无评论

Optimizing BERT for Bengali Emotion Classification: Evaluating Knowledge Distillation, Pruning, and Quantization

引用

computer Modeling in engineering & sciences 2025年第2期142卷 1637-1666页

作者： Md Hasibur Rahman Mohammed Arif Uddin Zinnat Fowzia Ria Rashedur M.Rahman Department of Electrical and Computer Engineering North South UniversityDhaka1229Bangladesh

The rapid growth of digital data necessitates advanced natural language processing(NLP)models like BERT(Bidi-rectional Encoder Representations from Transformers),known for its superior performance in text ***,BERT’s size and computational demands limit its practicality,especially in resource-constrained *** research compresses the BERT base model for Bengali emotion classification through knowledge distillation(KD),pruning,and quantization *** Bengali being the sixth most spoken language globally,NLP research in this area is *** approach addresses this gap by creating an efficient BERT-based model for Bengali *** have explored 20 combinations for KD,quantization,and pruning,resulting in improved speedup,fewer parameters,and reduced memory *** best results demonstrate significant improvements in both speed and *** instance,in the case of mBERT,we achieved a 3.87×speedup and 4×compression ratio with a combination of Distil+Prune+Quant that reduced parameters from 178 to 46 M,while the memory size decreased from 711 to 178 *** results offer scalable solutions for NLP tasks in various languages and advance the field of model compression,making these models suitable for real-world applications in resource-limited environments.

关键词： Bengali NLP black-box distillation emotion classification model compression post-training quantization unstructured pruning

来源：评论

学校读者我要写书评

暂无评论

Impact of Memory Motors on an IGBT-Based Inverter Efficiency

引用

IEEE Transactions on Industry Applications 2025年第3期61卷 4214-4225页

作者： Aljehaimi, Akrem M. Abdel-Mageed, Bassam Samy Pillay, Pragasen Department of Electrical and Computer Engineering Concordia University Montreal Canada

This paper investigates the impact of hybrid memory motors on an IGBT-based inverter in the field-weakening region. Hybrid variable-flux motors have been introduced to overcome the limitations of conventional IPMSMs in traction applications. Different memory motor topologies have been introduced and compared in the literature. Yet, their impact on the drive inverter has not been reported. An existing prototyped ten-horsepower series-hybrid variable motor has been used as a case study in this paper. In the field weakening region, comparing the operation with partially demagnetized magnets to fully magnetized magnets, it is found that not only does the motor current decrease, but the motor power factor also improves. This unique finding of improved power factor operation positively impacts the inverter conduction loss. This has significant practical implications, suggesting that hybrid memory motors can lead to more efficient traction inverters. An air-cooled IGBT-based three-phase 750 VDC, 30 ARMS, is used in this study. In the simulation, the switch characteristics from the datasheet have been used for loss calculations. Also, the inverter power loss and efficiency have been measured at different speeds, loads, and magnetization states. A two to three percent improvement in inverter efficiency was noted in the high-speed region beyond two per unit speed. © 2025 IEEE.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

Video captioning using transformer-based GAN

引用

Multimedia Tools and Applications 2025年第10期84卷 7091-7113页

作者： Babavalian, Mohammad Reza Kiani, Kourosh Electrical and Computer Engineering Department Semnan University Semnan Iran

Video captioning is the process of automatically generating natural language descriptions of video content. Historically, most video captioning methods have relied on extending Sequence-to-Sequence (Seq2Seq) models. However, such approaches possess limitations due to the sequential nature of the captions, which leads to less accurate captions. To address this limitation, this paper introduces a novel end-to-end architecture for video captioning that combines conditional Wasserstein Generative Adversarial Networks (cWGAN) with a transformer model. The proposed architecture consists of two modules: feature extraction and caption generation. The feature extraction module aims to obtain an encoded feature vector representing the video contents, while the caption generation module generates human-readable captions from encoded feature vector. To the best of our knowledge, this is the first architecture for generative video captioning that integrates a transformer model with GAN. The results of the proposed model based on the BLEU-4, METEOR, ROUGE-L, and CIDEr metrics, on two datasets, MSVD (BLEU-4 = 61.2, METEOR = 41.6) and MSR-VTT (BLEU-4 = 61.2, METEOR = 31.1), compared to state-of-the-art approaches, demonstrate the effectiveness of the transformer with generative model in generating accurate and human-readable captions. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Realtime and Integrated Framework for LiDAR-based Object Tracking

引用

Journal of Institute of Control, Robotics and Systems 2025年第3期31卷 196-205页

作者： Lee, Gyuseok Kim, Kana Lee, Jejun Kim, Hakil Department of Electrical and Computer Engineering Inha University Korea Republic of

This study proposes a real-time integrated framework for LiDAR-based object tracking in autonomous driving environments. Advancements in LiDAR sensors are increasing point cloud data collection, leading to a demand for reliable real-time processing methods. The proposed framework applies voxelization and ground removal techniques to reduce computational load and integrates clustering and deep learning-based object recognition to ensure stability. Combining the point cloud data from LiDAR and the IMU data corrects distortions and refines real-time object movement, enabling accurate tracking in dynamic environments. This framework supports a maximum detection range of 100 m, with a computation time of 52 ms, a positional error of 1.06 m, a heading error of 3.79°, a relative velocity error of 1.46 m/s, and an average tracking frame count of 101, thereby improving object recognition accuracy and tracking performance while fulfilling real-time processing requirements. © ICROS 2025.

关键词： 3D object detection autonomous driving LiDAR object tracking

来源：评论

学校读者我要写书评

暂无评论

MCVL: Multi-directional Camera-based Visual Localization Resistant to Seasonal and Illumination Changes

引用

Journal of Institute of Control, Robotics and Systems 2025年第2期31卷 153-159页

作者： Mun, Giyoung Kim, Hakil Department of Electrical and Computer Engineering Inha University Korea Republic of

The global navigation satellite system-based technology has inherent limitations due to its reliance on radio signals. In contrast, visual localization operates independently of radio communication, presenting a viable solution to overcome these limitations. However, it is susceptible to seasonal and illumination variations, highlighting the need for research to address these challenges. Therefore, this paper proposes the multi-directional camera-based visual localization, which is robust against seasonal and illumination changes. The proposed method combines image from multiple directions and extracts global deep learning features. Subsequently, local deep learning features are extracted to preserve the characteristics of each combined image, allowing for the identification of geographically similar images. This approach utilize multi-directional cameras, enabling resilient performance under various constraints. Moreover, it demonstrates an improvement of 7.56% in recall rate at 1-meter threshold compared to existing methods. © ICROS 2025.

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Data Description for LoRaWAN Path Loss Measurements in an Indoor Office Setting: Effects of Environmental Factors

引用

IEEE Access 2025年 13卷 83148-83170页

作者： Obiri, Nahshon Mokua Laerhoven, Kristof Van University of Siegen Department of Electrical Engineering and Computer Science Germany

This paper presents a comprehensive dataset of LoRaWAN technology path loss measurements collected in an indoor office environment, focusing on quantifying the effects of environmental factors on signal propagation. Utilizing a network of six strategically placed LoRaWAN end devices (EDs) and a single indoor gateway (GW) at the University of Siegen's Hölderlinstraße Campus in the City of Siegen, Germany, we systematically measured signal strength indicators such as the Received Signal Strength Indicator (RSSI) and the Signal-to-Noise Ratio (SNR) under various environmental conditions, including temperature, relative humidity, carbon dioxide (CO₂) concentration, barometric pressure, and particulate matter levels (PM_2.5). Our empirical analysis confirms that transient phenomena such as reflections, scattering, interference, occupancy patterns (induced by environmental parameter variations), and furniture rearrangements can alter signal attenuation by as much as 10.58 dB, highlighting the dynamic nature of indoor propagation. As an example of how this dataset can be utilized, we tested and evaluated a refined Log-Distance Path Loss and Shadowing Model that integrates both structural obstructions (Multiple Walls) and Environmental Parameters (LDPLSM-MW-EP). Compared to a baseline model that considers only Multiple Walls (LDPLSMMW), the enhanced approach reduced the root mean square error (RMSE) from 10.58 dB to 8.04 dB and increased the coefficient of determination (R2) from 0.6917 to 0.8222. By capturing the extra effects of environmental conditions and occupancy dynamics, this improved model provides valuable insights for optimizing power usage and prolonging device battery life, enhancing network reliability in indoor Internet of Things (IoT) deployments, among other applications. The dataset, accessible upon reasonable request, offers a solid foundation for future research and development in indoor wireless communication. © 2013 IEEE.

关键词： dataset environmental factors indoor propagation internet of things (IoT) LoRaWAN low-power wide area network (LPWAN) path loss

来源：评论

学校读者我要写书评

暂无评论

Monitoring COVID-19 environment: a real-time facial mask detection using YOLO models

引用

Research on Biomedical engineering 2025年第1期41卷 1-18页

作者： Pandiyan, P. Thangaraj, Rajasekaran V, Balasubramanian V. K, Manavalasundaram S, Balakrishnan Department of Electrical and Electronics Engineering KPR Institute of Engineering and Technology Coimbatore India Department of Computer Science and Engineering Nandha Engineering College Erode India Department of Information Technology Velalar College of Engineering and Technology Erode India Department of Computer Science and Engineering Aarupadai Veedu Institute of Technology Chennai India Department of Computer Science and Engineering Sri Ramakrishna Institute of Technology Coimbatore India

Purpose: The rapid spread of COVID-19 has resulted in significant harm and impacted tens of millions of people globally. In order to prevent the transmission of the virus, individuals often wear masks as a protective measure for themselves and others. Coronavirus protection guidelines have been published by the World Health Organization (WHO). According to WHO standards, COVID-19 can be prevented by wearing a mask in public places and congested regions. In these places, it is very difficult to personally check to see if people are wearing face masks or not. Methods: The objective of this research work is to build a powerful, efficient, and real-time approach for detecting people not wearing masks. Three cutting-edge object identification models, namely YOLOv4, Tiny-YOLOv4, and YOLOv5, are employed in this study for the identification of masked faces. Result: The proposed YOLOv5 model is evaluated using real-time images captured using a smartphone or tablet. The test images include both single and multiple people with and without masks. The YOLOv5 model achieved recognition accuracy of 88.90% with an average detection speed of 0.0316 s per image, whereas the YOLOv4 and Tiny-YOLOv4 produced recognition accuracy of 82.24% and 74.80% with an average detection speed of 0.0530 s and 0.0541 s per image, respectively. Conclusion: The comparative performance suggests that the YOLOv5 model has a maximum recognition accuracy of 88.90% in face mask identification tasks compared to other models such as the YOLOv4 and Tiny-YOLOv4. © The Author(s), under exclusive licence to The Brazilian Society of Biomedical engineering 2025.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Derandomizing Codes for the Adversarial Wiretap Channel of Type II

引用

IEEE Transactions on Information Theory 2025年第6期71卷 4686-4707页

作者： Ruzomberka, Eric Nikbakht, Homa Brinton, Christopher G. Love, David J. Poor, H. Vincent Air Force Institute of Technology Department of Electrical and Computer Engineering United States Princeton University Department of Electrical and Computer Engineering United States Purdue University Elmore Family School of Electrical and Computer Engineering West Lafayette United States

The adversarial wiretap channel of type II (AWTC-II) is a communication channel that can a) read a fraction of the transmitted symbols up to a given bound and b) induce both errors and erasures in a fraction of the symbols up to given bounds. The channel is controlled by an adversary who can freely choose the locations of the symbol reads, errors and erasures via a process with unbounded computational power. The AWTC-II is an extension of Ozarow’s and Wyner’s wiretap channel of type II to the adversarial channel setting. The semantic-secrecy (SS) capacity of the AWTC-II is partially known, where the best-known lower bound is non-constructive and proven via a random coding argument that uses a large number (that is, exponential in blocklength n) of random bits to describe the random code. In this work, we establish a new derandomization result in which we match the best-known lower bound via a non-constructive random code that uses only O(n2) random bits. Unlike fully random codes, our derandomized code admits an efficient encoding algorithm and benefits from some linear structure. Our derandomization result is a novel application of random pseudolinear codes – a class of non-linear codes first proposed for applications outside the AWTC-II setting, which have k-wise independent codewords where k is a design parameter. As the key technical tool in our analysis, we provide a novel concentration inequality for sums of random variables with limited independence, as well as a soft-covering lemma similar to that of Goldfeld, Cuff and Permuter that holds for random codes with k-wise independent codewords. © 1963-2012 IEEE.

关键词： Signal encoding

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：