检索结果-内蒙古大学图书馆

Bridging the Data Gap in AI Reliability Research and Establishing DR-AIR, a Comprehensive Data Repository for AI Reliability

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zheng, Simin Clark, Jared M. Salboukh, Fatemeh Silva, Priscila da Mata, Karen Pan, Fenglian Min, Jie Lian, Jiayi King, Caleb B. Fiondella, Lance Liu, Jian Deng, Xinwei Hong, Yili Department of Statistics Virginia Tech BlacksburgVA24061 United States Dept. of Engineering & Applied Science Univ. of Massachusetts DartmouthMA02747 United States Dept. of Electrical & Computer Engineering Univ. of Massachusetts DartmouthMA02747 United States Department of Systems & Industrial Engineering University of Arizona TucsonAZ85721 United States Department of Mathematics & Statistics University of South Florida TampaFL33620 United States Quantitative Analytics Wells Fargo CharlotteNC28262 United States JMP Division SAS CaryNC27513 United States

Artificial intelligence (AI) technology and systems have been advancing rapidly. However, ensuring the reliability of these systems is crucial for fostering public confidence in their use. This necessitates the modeling and analysis of reliability data specific to AI systems. A major challenge in AI reliability research, particularly for those in academia, is the lack of readily available AI reliability data. To address this gap, this paper focuses on conducting a comprehensive review of available AI reliability data and establishing DR-AIR: a data repository for AI reliability. Specifically, we introduce key measurements and data types for assessing AI reliability, along with the methodologies used to collect these data. We also provide a detailed description of the currently available datasets with illustrative examples. Furthermore, we outline the setup of the DR-AIR repository and demonstrate its practical applications. This repository provides easy access to datasets specifically curated for AI reliability research. We believe these efforts will significantly benefit the AI research community by facilitating access to valuable reliability data and promoting collaboration across various academic domains within AI. We conclude our paper with a call to action, encouraging the research community to contribute and share AI reliability data to further advance this critical field of study. Copyright © 2025, The Authors. All rights reserved.

关键词： Adversarial machine learning

Perturbed Gradient Descent via Convex Quadratic Approximation for Nonconvex Bilevel Optimization

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Abolfazli, Nazanin Sharifi, Sina Fazlyab, Mahyar Hamedani, Erfan Yazdandoost Dept. of Systems & Industrial Engineering University of Arizona TucsonAZ85721 United States Dept. of Electrical & Computer Engineering Johns Hopkins University BaltimoreMD21218 United States

Bilevel optimization is a fundamental tool in hierarchical decision-making and has been widely applied to machine learning tasks such as hyperparameter tuning, meta-learning, and continual learning. While significant progress has been made in bilevel optimization, existing methods predominantly focus on the nonconvex-strongly convex, or the nonconvex-PL settings, leaving the more general nonconvex-nonconvex framework underexplored. In this paper, we address this gap by developing an efficient gradient-based method inspired by the recently proposed Relaxed Gradient Flow (RXGF) framework with a continuous-time dynamic [1]. In particular, we introduce a discretized variant of RXGF and formulate convex quadratic program subproblems with closed-form solutions. We provide a rigorous convergence analysis, demonstrating that under the existence of a KKT point and a regularity assumption (lower-level gradient PL assumption), our method achieves an iteration complexity of O(1/ϵ1.5) in terms of the squared norm of the KKT residual for the reformulated problem. Moreover, even in the absence of the regularity assumption, we establish an iteration complexity of O(1/ϵ3) for the same metric. Through extensive numerical experiments on convex and nonconvex synthetic benchmarks and a hyper-data cleaning task, we illustrate the efficiency and scalability of our approach. Copyright © 2025, The Authors. All rights reserved.

关键词： Gradient methods

Certain Investigation on IoT Based Cotton Dust Pollution Monitoring in Textile Plants

学校读者我要写书评

暂无评论

Certain Investigation on IoT Based Cotton Dust Pollution Mon...

International Conference on Inventive Computation Technologies (ICICT)

作者： P Sivanesan Anand J V Trilok Sai Vaddanam Shaik Mohammad Irfan Department of Information Communication Technology School of Computing SASTRA University Thanjavur Tamilnadu India Sri Ramachandra Faculty of Engineering and Technology Sri Ramachandra Institute of Higher Education and Research Chennai Tamil Nadu India Dept. of Computer science and Business Systems SASTRA University Thanjavur Tamilnadu India Dept.of ECE Siddhartha Academy of Higher Education Vijayawada Andhra Pradesh India

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

The objective of the work is to track the level of cotton dust in the textile sector. The IoT-enabled cotton dust monitoring system deploys three sensors: Sharp GP2Y1010AU0F; Shinyei PPD42NS; and Honeywell HPMA115S0-XXX measuring the dust levels. The Optical dust sensor GP2Y1010AU0F has a threshold of 1 mg/mS, which is placed inside the mask and when that threshold is crossed, buzzer alerts the worker with the air contaminants. It measures inhaled cotton dust and sends data to IoT, real-time concentration height of dust into the mobile devices. Experimental results show that Sharp GP2Y1010AU0F sensor has achieved award for acquiring the highest mean dust concentration of 95.167 mg/mS with a standard deviation of 3.014 among the three sensors, while Honeywell HPMA115S0-XXX and Shinyei PPD42NS recorded a mean of 87.833 mg/mS and 77.500 mg/mS, respectively. The observed response times of the sensors as follows for GP2Y1010AU0F-8s, HPMA115S0-XXX-6s, and PPD42NS- 5s, recording the fastest response by Honeywell HPMA115S0-XXX. A comparative study in accuracy, precision and sensitivity, with a response time, shows the merits and demerits for each sensor. Results emphasize the effectiveness of the system proposed for monitoring in terms of airborne cotton dust exposure in improving safety in textile workplaces. A meta-analysis is performed with Bayesian framework using JASP software.

关键词： Sensor phenomena and characterization Software Real-time systems Sensors Safety Bayes methods Pollution measurement Cotton Time factors Monitoring

An Efficient GPU-based Implementation for Noise Robust Sound Source Localization

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Lin, Zirui Takigahira, Masayuki Terakado, Naoya Gulzar, Haris Busto, Monikka Roslianna Eda, Takeharu Itoyama, Katsutoshi Nakadai, Kazuhiro Amano, Hideharu Dept. of Systems and Control Engineering School of Engineering Tokyo Institute of Technology Tokyo Japan Honda Research Institute Japan Co. Ltd. Saitama Japan NTT Software Innovation Center Tokyo Japan Dept. of Information and Computer Science Keio University Kanagawa Japan

Robot audition, encompassing Sound Source Localization (SSL), Sound Source Separation (SSS), and Automatic Speech Recognition (ASR), enables robots and smart devices to acquire auditory capabilities similar to human hearing. Despite their wide applicability, processing multi-channel audio signals from microphone arrays in SSL involves computationally intensive matrix operations, which can hinder efficient deployment on Central Processing Units (CPUs), particularly in embedded systems with limited CPU resources. This paper introduces a GPU-based implementation of SSL for robot audition, utilizing the Generalized Singular Value Decomposition-based Multiple Signal Classification (GSVD-MUSIC), a noise-robust algorithm, within the HARK platform, an open-source software suite. For a 60-channel microphone array, the proposed implementation achieves significant performance improvements. On the Jetson AGX Orin, an embedded device powered by an NVIDIA GPU and ARM®Cortex™-A78AE v8.2 64-bit CPUs, we observe speedups of 4645.1× for GSVD calculations and 8.8× for the SSL module, while speedups of 2223.4× for GSVD calculation and 8.95× for the entire SSL module on a server configured with an NVIDIA A100 GPU and AMD EPYC™ 7352 CPUs, making real-time processing feasible for large-scale microphone arrays and providing ample capacity for real-time processing of potential subsequent machine learning or deep learning tasks. © 2025, CC BY-NC-ND.

关键词： Acoustic generators

controller design for off-tracking elimination in multi-articulated vehicles 15th

学校读者我要写书评

暂无评论

Controller design for off-tracking elimination in multi-arti...

15th World Congress of the International Federation of Automatic control, 2002

作者： Manesis, S.A. Davrazos, G.N. Koussoulas, N.T. Electrical and Computer Engineering Dept. Division of Systems and Control University of Patras Greece

ISBN: (纸本)9783902661746

The motion of a multi-body autonomous robot as well as of a train-like multi-articulated transportation vehicle is characterized by the deviation of the path of each intermediate vehicle from that of the leading one (off-tracking). In this paper, we make use of an innovative junction technique, which allows the kingpin to slide along the axis of the leading vehicle, something that proved to be very effective in reducing off-tracking. We propose two controllers for the elimination of the off-tracking phenomenon, in both robotic and transportation multi-articulated vehicles;the one is heuristically derived while the other one is based on steady-state off-tracking when an n-trailer vehicle moves on a circular trajectory. Simulation results for various cases, without and with the sliding kingpin system, showed that significant off-tracking reduction or even elimination can be achieved. Copyright © 2002 IFAC.

关键词： Vehicles

Building automata - Type simulation models for undergraduate teaching industrial systems analysis

学校读者我要写书评

暂无评论

Building automata - Type simulation models for undergraduate...

作者： Deligiannis, Vasileios Manesis, Stamatis Electrical and Computer Engineering Dept. Division of Systems and Control University of Patras Greece

ISBN: (纸本)9783902661074

Simulation has a significant role in control engineering. It provides the best solution for educating new engineers without expensive experimentation on real systems. This paper presents a guide for constructing simulation models based on a recently presented hyper-class of hybrid automata. New type's definition is given jointly with some examples of guide's use. Guide is applicable in various programming environments and is oriented for undergraduate teaching purposes. Copyright © 2006 IFAC.

关键词： systems analysis

Introducing a new mathematical abstraction for modeling real time systems

学校读者我要写书评

暂无评论

Introducing a new mathematical abstraction for modeling real...

作者： Deligiannis, Vasileios Manesis, Stamatis Electrical and Computer Engineering Dept. Division of Systems and Control University of Patras Greece

ISBN: (纸本)008045108X

Due to the increasing complexity of industrial production systems, there exists a need for the development of efficient formal approaches for their analysis and control. Various methods have been proposed and examined from researchers, without being widely adopted for direct industrial use. in general, an industrial production line can be modelled as a Discrete Event System, but a more accurate representation would result, if we considered it as a real-time system. This paper presents a new mathematical abstraction for modelling real-time systems. in comparison with the conventional methods, the proposed method introduces new formulation parameters and handles variables in a different manner. It gives the opportunity to handle both discrete and real valued variables as inputs, outputs or both. A formal definition of the method is given and some examples of computations or runs of two typical examples are also presented. Copyright © 2005 IFAC.

关键词： Discrete event simulation

A novel explainable ECG classification with spatio-temporal transformers and hybrid loss optimization

学校读者我要写书评

暂无评论

Biomedical Signal Processing and control 2025年 110卷

作者： Inam Abousaber Hany El-Ghaish Haitham F. Abdallah Dept. of Information Technology Faculty of Computers and Information Technology University of Tabuk Tabuk Saudi Arabia Dept. of Computer and Control Faculty of Engineering Tanta University 31526 Gharbiya Tanta Egypt Dept. of Electrical Engineering Higher Institute of Engineering and Technology Kafrelsheikh 33511 Egypt

This paper presents a novel deep learning framework for ECG arrhythmias detection, integrating Spatio-Temporal Adaptive Embedding (STAE) Transformers and Variational Autoencoders (VAEs) to improve classification accuracy and address class imbalance. Traditional ECG classification models struggle to capture long-range temporal dependencies and handle imbalanced datasets, leading to poor sensitivity for rare arrhythmias. The proposed system employs STAE Transformers to model intricate temporal and spatial relationships within ECG signals to overcome these challenges. At the same time, VAEs generate diverse and realistic ECG samples to enhance model generalization, particularly for underrepresented arrhythmias. Additionally, combining Focal Loss and Dice Loss, a Hybrid Loss Function further optimizes performance by focusing on hard-to-classify arrhythmias. The model is evaluated on the MIT-BIH Arrhythmias Database and PTB Diagnostic ECG Database using 5-fold cross-validation, achieving an accuracy of 99.56% and a macro F1-score of 95.40%, outperforming existing state-of-the-art methods, with a 3.5% improvement in sensitivity for rare arrhythmias. To ensure interpretability, SHapley Additive exPlanations (SHAP) and Gradient-weighted Class Activation Mapping (Grad-CAM) are utilized, highlighting the QRS complex and RR intervals as the most critical features and confirming that the model focuses on clinically relevant waveform regions. These results demonstrate the effectiveness of our approach in developing an accurate, interpretable, and robust deep learning system for ECG arrhythmias detection, paving the way for more reliable clinical decision support systems.

关键词：

SOLAS: Superpositioning an Optical Lens in Automotive Simulation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Jakab, Daniel Barthel, Julian Braun, Alexander Mohandas, Reenu Deegan, Brian Michael Kumbham, Mahendar Molloy, Dara Collins, Fiachra Scanlan, Anthony Eising, Ciarán Dept. of Electronic and Computer Engineering University of Limerick Castletroy Co. Limerick V94 T9PX Ireland Faculty of Electrical Engineering & Information Technology University of Applied Sciences Düsseldorf40476 Germany Dept. of Electrical and Electronic Engineering University of Galway GalwayH91 TK33 Ireland Valeo Vision Systems Tuam GalwayDY1 22DJ Ireland Lero the Science Foundation Ireland Research Centre for Software University of Limerick LimerickV94 T9PX Ireland

Automotive Simulation is a potentially cost-effective strategy to identify and test corner case scenarios in automotive perception. Recent work has shown a significant shift in creating realistic synthetic data for road traffic scenarios using a video graphics engine. However, a gap exists in modeling realistic optical aberrations associated with cameras in automotive simulation. This paper builds on the concept from existing literature to model optical degradations in simulated environments using the Python-based ray-tracing library KrakenOS. As a novel pipeline, we degrade automotive fisheye simulation using an optical doublet with +/-2◦ Field of View(FOV), introducing realistic optical artifacts into two simulation images from SynWoodscape and Parallel Domain Woodscape. We evaluate KrakenOS by calculating the Root Mean Square Error (RMSE), which averaged around 0.023 across the RGB light spectrum compared to Ansys Zemax OpticStudio, an industrial benchmark for optical design and simulation. Lastly, we measure the image sharpness of the degraded simulation using the ISO12233:2023 Slanted Edge Method and show how both qualitative and measured results indicate the extent of the spatial variation in image sharpness from the periphery to the center of the degradations. © 2025, CC BY.

关键词： Ray tracing