检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Esfahani, Arash Nasr Hosseini, Hamed Masouleh, Mehdi Tale Kalhor, Ahmad Sajedi, Hedieh Human and Robot Interaction Lab School of Electrical and Computer Engineering University of Tehran Tehran Iran School of Mathematics Statistics and Computer Science University of Tehran Tehran Iran

As smart homes become more prevalent in daily life, the ability to understand dynamic environments is essential which is increasingly dependent on AI systems. This study focuses on developing an intelligent algorithm which can navigate a robot through a kitchen, recognizing objects, and tracking their relocation. The kitchen was chosen as the testing ground due to its dynamic nature as objects are frequently moved, rearranged and replaced. Various techniques, such as SLAM feature-based tracking and deep learning-based object detection (e.g., Faster R-CNN), are commonly used for object tracking. Additionally, methods such as optical flow analysis and 3D reconstruction have also been used to track the relocation of objects. These approaches often face challenges when it comes to problems such as lighting variations and partial occlusions, where parts of the object are hidden in some frames but visible in others. The proposed method in this study leverages the YOLOv5 architecture, initialized with pre-trained weights and subsequently fine-tuned on a custom dataset. A novel method was developed, introducing a frame-scoring algorithm which calculates a score for each object based on its location and features within all frames. This scoring approach helps to identify changes by determining the best-associated frame for each object and comparing the results in each scene, overcoming limitations seen in other methods while maintaining simplicity in design. The experimental results demonstrate an accuracy of 97.72%, a precision of 95.83% and a recall of 96.84% for this algorithm, which highlights the efficacy of the model in detecting spatial changes. © 2025, CC BY.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Non-contact thermal characterization using IR camera for compact metal-oxide gas sensor 23

Non-contact thermal characterization using IR camera for com...

引用

23rd IEEE Electronics Packaging Technology Conference, EPTC 2021

作者： Stoukatch, S. Fagnard, J.-F. Dupont, F. Laurent, P. Redoute, J.-M. Liege University Microsys Lab Department of Electrical Engineering and Computer Science Seraing Belgium

ISBN: (纸本)9781665416191

Following a demand for thermal management there is need to measure precisely a temperature on the most critical part of microassembly. The widely-used contact type of measurements is often not suitable for micro parts of assembly as small as 0.5 mm and smaller. The non-contact measurements currently available are not always directly applicable on complex heterogeneous microassemblies structures such as miniaturized metal-oxide (MOX) gas sensor. In response to this, we have developed a simple technique using IR thermography for accurate and non-contact temperature measurements of electronic microassemblies, and validate this approach with MOX sensors heated to operating temperature of 250-300C. © 2021 IEEE.

关键词： Metals

来源：评论

学校读者我要写书评

暂无评论

Subject-independent emotion recognition of EEG signals using graph attention-based spatial-temporal pattern learning 41

Subject-independent emotion recognition of EEG signals using...

引用

第41届中国控制会议

作者： Yiwen Zhu Yeshuang Guo Wenzhe Zhu Lare Di Zhong Yin School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Engineering Research Center of Optical Instrument and System Ministry of EducationShanghai Key Lab of Modern Optical SystemUniversity of Shanghai for Science and Technology

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Electroencephalography(EEG) reveals human brain activities and becomes an essential solution for exploring human intrinsic emotional *** this study,we proposed a graph attention-based spatial-temporal pattern learning method called TAGAT to take full advantage of spatial structure of EEG channels and take the nonstationary of emotions into *** attention mechanism is applied to compute weight coefficients of different spatial and temporal *** alleviate differences between subjects,a domain discriminator is added to the model based on domain adaptation to tackle subject-independent EEG emotion recognition *** on the DEAP database,our method achieves the accuracy of 56.56% and 58.91% of arousal and valence dimensions for subject-independent emotion *** effectiveness of T-AGAT method has been demonstrated when compared to other existing common methods.

关键词： Emotion recognition electroencephalography deep learning transfer learning pattern learning

来源：评论

学校读者我要写书评

暂无评论

Non-Invasive Early Diagnosis of Obstructive Lung Diseases Leveraging Machine Learning Algorithms

引用

computers, Materials & Continua 2022年第9期72卷 5681-5697页

作者： Mujeeb Ur Rehman Maha Driss Abdukodir Khakimov Sohail Khalid Department of Electrical Engineering Riphah International UniversityIslamabad44000Pakistan Security Engineering Lab Prince Sultan UniversityRiyadh12435Saudi Arabia RIADI Laboratory National School of Computer ScienceUniversity of ManoubaManouba2010Tunisia Peoples’Friendship University of Russia(RUDN University) Moscow117198Russia

Lungs are a vital human body organ,and different Obstructive Lung Diseases(OLD)such as asthma,bronchitis,or lung cancer are caused by shortcomings within the ***,early diagnosis of OLD is crucial for such patients suffering from OLD since,after early diagnosis,breathing exercises and medical precautions can effectively improve their health state.A secure non-invasive early diagnosis of OLD is a primordial need,and in this context,digital image processing supported by Artificial Intelligence(AI)techniques is reliable and widely used in the medical field,especially for improving early disease ***,this article presents an AIbased non-invasive and secured diagnosis for OLD using physiological and iris *** research work implements different machine-learning-based techniques which classify various subjects,which are healthy and effective *** iris features include gray-level run-length matrix-based features,gray-level co-occurrence matrix,and statistical *** features are extracted from iris ***,ten different classifiers and voting techniques,including hard and soft voting,are implemented and tested,and their performances are evaluated using several parameters,which are precision,accuracy,specificity,F-score,and *** on the statistical analysis,it is concluded that the proposed approach offers promising techniques for the non-invasive early diagnosis of OLD with an accuracy of 97.6%.

关键词： Obstructive lung disease non-invasive diagnosis machine learning physiological features voting techniques

来源：评论

学校读者我要写书评

暂无评论

Automatic Assistance to Mitigate Rollback Inconsistencies in Collaborative Edits

Research Square

引用

Research Square 2025年

作者： Mondal, Saikat Uddin, Gias Roy, Chanchal K. York University Canada Software Research Lab Department of Computer Science University of Saskatchewan Canada Lab Department of Electrical and Software Engineering University of Calgary Canada

The success of technical Q&A sites such as Stack Overflow depends on two key factors: (a) active user participation and (b) the quality of the shared knowledge. Stack Overflow introduced an edit system that allows users to suggest improvements to posts (i.e., questions and answers) to enhance the quality of the content. However, users, such as post owners or site moderators, can reject these suggested edits by rollbacks due to unsatisfactory, low-quality edits or violating edit guidelines. Unfortunately, subjectivity bias in determining whether an edit is satisfactory or unsatisfactory can lead to inconsistencies in the rollback decisions. For example, one user might accept the formatting of a method name (e.g., getActivity()) as a code term, while another might reject it. Such inconsistencies can demotivate and frustrate users whose edits are rejected. Furthermore, several post owners prefer to keep their content unchanged and even resist necessary edits. As a result, they sometimes roll back necessary edits and revert posts to a flawed version, which violates editing guidelines. The problems mentioned above are further compounded by the lack of specific guidelines and tools to assist users in ensuring consistency in user rollback actions. In this study, we investigate the types, prevalence, and impact of rollback edit inconsistencies and propose a solution to address them. The outcomes of this research are fivefold. First, we manually investigated 764 rollback edits (382 questions + 382 answers) and identified eight types of inconsistent rollback. Second, we surveyed 44 practitioners to assess the impact of rollback inconsistencies. More than 80% of the participants found our identified inconsistency types detrimental to post quality. Third, we developed rule-based algorithms and Machine Learning (ML) models to detect the eight types of rollback inconsistencies. Both approaches achieve over 90% accuracy. Fourth, we introduced a tool, iEdit, which integrates these

关键词：

来源：评论

学校读者我要写书评

暂无评论

Thermometer: towards universal calibration for large language models 24

Thermometer: towards universal calibration for large languag...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Maohao Shen Subhro Das Kristjan Greenewald Prasanna Sattigeri Gregory Wornell Soumya Ghosh Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge MIT-IBM Watson AI Lab IBM Research

We consider the issue of calibration in large language models (LLM). Recent studies have found that common interventions such as instruction tuning often result in poorly calibrated LLMs. Although calibration is well-explored in traditional applications, calibrating LLMs is uniquely challenging. These challenges stem as much from the severe computational requirements of LLMs as from their versatility, which allows them to be applied to diverse tasks. Addressing these challenges, we propose THERMOMETER, a calibration approach tailored to LLMs. THERMOMETER learns an auxiliary model, given data from multiple tasks, for calibrating a LLM. It is computationally efficient, preserves the accuracy of the LLM, and produces better-calibrated responses for new tasks. Extensive empirical evaluations across various benchmarks demonstrate the effectiveness of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PCB Based Modulated Scatter with Enhanced Modulation Depth

PCB Based Modulated Scatter with Enhanced Modulation Depth

引用

2023 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio science Meeting, AP-S/URSI 2023

作者： Crocker, Dylan A. Donnell, Kristen M. Amazon Web Services Inc. SeattleWA98109 United States Missouri University of Science and Technology Microwave Sensing Lab. Dept. of Electrical and Computer Engineering RollaMO65409 United States

ISBN: (纸本)9781665442282

The modulated scatterer technique (MST) has shown promise for applications in microwave imaging, electric field mapping, and materials characterization. Traditionally, MST scatterers are dipoles centrally loaded with an element capable of modulation (e.g., a PIN diode). By modulating the load element state, the scattered fields are also modulated. However, due to the small size of such scatterers, it can be difficult to reliably detect the response. Increasing the modulation depth (MD) of the scattered signal may improve detectability. This paper presents simulations and measurements of PCB-based MST elements that, through reactive loading, are designed to be electrically invisible during the reverse bias state of the modulated element (a PIN diode in this case) while producing detectable scattering during the forward bias state. The results show a significant (> 90%) improvement in the MD of the scattered signal when compared to a traditional MST scatterer. © 2023 IEEE.

关键词： Polychlorinated biphenyls

来源：评论

学校读者我要写书评

暂无评论

Integration of Federated Learning and Blockchain in Healthcare: A Tutorial

arXiv

引用

arXiv 2024年

作者： Shahsavari, Yahya Dambri, Oussama A. Baseri, Yaser Hafid, Abdelhakim Senhaji Makrakis, Dimitrios Montreal Blockchain Lab University of Montreal Montreal Canada The School of Electrical Engineering and Computer Science University of Ottawa Ottawa Canada

Wearable devices and medical sensors revolutionize health monitoring, raising concerns about data privacy in Machine Learning (ML) for healthcare. This tutorial explores Federated Learning (FL) and Blockchain (BC) integration, offering a secure and privacy-preserving approach to healthcare analytics. FL enables decentralized model training on local devices at healthcare institutions, keeping patient data localized. This facilitates collaborative model development without compromising privacy. However, FL introduces vulnerabilities. BC, with its tamper-proof ledger and smart contracts, provides a robust framework for secure collaborative learning in FL. After presenting a taxonomy for the various types of data used in ML in medical applications, and a concise review of ML techniques for healthcare use cases, this tutorial explores three integration architectures for balancing decentralization, scalability, and reliability in healthcare data. Furthermore, it investigates how Blockchain-based Federated Learning (BCFL) enhances data security and collaboration in disease prediction, medical image analysis, patient monitoring, and drug discovery. By providing a tutorial on FL, blockchain, and their integration, along with a review of BCFL applications, this paper serves as a valuable resource for researchers and practitioners seeking to leverage these technologies for secure and privacy-preserving healthcare ML. It aims to accelerate advancements in secure and collaborative healthcare analytics, ultimately improving patient outcomes. © 2024, CC BY-NC-ND.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Going beyond linear mode connectivity: the layerwise linear feature connectivity 23

Going beyond linear mode connectivity: the layerwise linear ...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Zhanpeng Zhou Yongyi Yang Xiaojiang Yang Junchi Yan Wei Hu Dept. of Computer Science and Engineering & MoE Key Lab of AI Shanghai Jiao Tong University Dept. of Electrical Engineering & Computer Science University of Michigan

Recent work has revealed many intriguing empirical phenomena in neural network training, despite the poorly understood and highly complex loss landscapes and training dynamics. One of these phenomena, Linear Mode Connectivity (LMC), has gained considerable attention due to the intriguing observation that different solutions can be connected by a linear path in the parameter space while maintaining near-constant training and test losses. In this work, we introduce a stronger notion of linear connectivity, Layerwise Linear Feature Connectivity (LLFC), which says that the feature maps of every layer in different trained networks are also linearly connected. We provide comprehensive empirical evidence for LLFC across a wide range of settings, demonstrating that whenever two trained networks satisfy LMC (via either spawning or permutation methods), they also satisfy LLFC in nearly all the layers. Furthermore, we delve deeper into the underlying factors contributing to LLFC, which reveal new insights into the permutation approaches. The study of LLFC transcends and advances our understanding of LMC by adopting a feature-learning perspective. We released our source code at https://***/zzp1012/LLFC.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Calibrating Practical Privacy Risks for Differentially Private Machine Learning

Calibrating Practical Privacy Risks for Differentially Priva...

引用

IEEE International Conference on Big Data

作者： Yuechun Gu Keke Chen Trustworthy and Intelligent Computing Lab Computer Science and Electrical Engineering Cybersecurity Institute University of Maryland Baltimore County Baltimore USA

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

Differential privacy quantifies privacy through the privacy budget , yet its practical interpretation is complicated by variations across models and datasets. Recent research on differentially private machine learning and membership inference has highlighted that with the same theoretical setting, the likelihood-ratio-based membership inference (LiRA) attack success rate (ASR) may vary according to specific datasets and models, which might be a better indicator for evaluating real-world privacy risks. Inspired by this practical privacy measure, we study the positive correlation between the setting and ASR. We also find that for a specific dataset and a specific task we can lower the attack success rate by modifying the dataset. As a result, we may enable flexible privacy budget settings in model training. One dataset modification strategy is selectively suppressing privacy-sensitive features without significantly damaging application-specific data utility. We use the SHAP (or LIME) model explainer to evaluate features’ privacy sensitivity and utility importance and develop an optimized feature-masking algorithm. We have conducted extensive experiments to show (1) the inherent link between ASR and the dataset’s privacy risk in terms of a specific modeling task; (2) By carefully selecting features to mask, we can preserve more data utility with equivalent practical privacy protection and relaxed settings. The implementation details are shared online at https://***/RhincodonE/On-sensitive-features-and-empirical-epsilon-lower-bounds.

关键词： Training Data privacy Privacy Differential privacy Sensitivity Correlation Machine learning Big Data Data models Protection

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：