检索结果-内蒙古大学图书馆

59th Annual Conference on Information Sciences and Systems, CISS 2025

作者： Detore, Ian Samsundar, John Davis, Cleon Johns Hopkins University Electrical and Computer Engineering Program BaltimoreMD United States Johns Hopkins University Electrical and Computer Engineering Program LaurelMD United States

ISBN: (纸本)9798331513269

This study introduces two novel hybrid machine-learning architectures for multilabel anomaly detection in electrocardiograms (EKGs): a 1D modified ResNet combined with a transformer encoder and an equivalent 2D ResNet-Transformer hybrid. This work is among the first to utilize two separate CNN-transformer architectures tailored specifically for temporal and spatial features in multilabel EKG data. Our models address the challenges of imbalanced data and multilabel classification by leveraging the PTB-XL dataset, containing over 21,000 annotated samples across five diagnostic superclasses, namely myocardial infarction, conduction disturbances, hypertrophy, ST-T wave changes, and normal EKGs. We applied advanced data augmentation techniques to mitigate class imbalance, including the Multilabel Synthetic Minority Over-Sampling Technique (ML-SMOTE). Additionally, we employed digital signal processing to denoise the EKG signals and convert time-series data into time-frequency representations for 2D modeling. Experimental results demonstrate the effectiveness of our approach, with the 1D model achieving an area under the curve (AUC) of 91.5% and the 2D model achieving an AUC of 87.2%. These findings demonstrate the potential of specialized architectures for comprehensive multilabel EKG anomaly detection. © 2025 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Diagnosis via Swarm-Optimized Adaptive Neuro-Fuzzy Inference System 59

Breast Cancer Diagnosis via Swarm-Optimized Adaptive Neuro-F...

引用

59th Annual Conference on Information Sciences and Systems, CISS 2025

作者： Greenlee, Aidan Palumbo, Neil F. Johns Hopkins University Electrical and Computer Engineering Program BaltimoreMD United States

ISBN: (纸本)9798331513269

This paper discusses a method for classification of breast cancer imaging data through the application of an adaptive neuro-fuzzy inference system (ANFIS) and particle swarm optimization (PSO) for hyperparameter optimization of the ANFIS system. A robust parameter tuning method is used to select the optimal configuration for the ANFIS and PSO components without expert knowledge of the dataset. Using these methods, high classification accuracies can be achieved for both the original and diagnostic versions of the Wisconsin Breast Cancer Dataset. These results demonstrate the flexibility and potential of a joint ANFIS-PSO system for automated diagnosis while retaining system simplicity and linguistic interpretability to support clinical decision-making. © 2025 IEEE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

GAMing the Brain: Investigating the Cross-Modal Relationships Between Functional Connectivity and Structural Features Using Generalized Additive Models 7th

GAMing the Brain: Investigating the Cross-Modal Relationsh...

引用

7th International Workshop on Machine Learning in Clinical Neuroimaging, MLCN 2024, Held in Conjunction with 27th International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2024

作者： Kannan, Arunkumar Caffo, Brian Venkataraman, Archana Department of Electrical and Computer Engineering Johns Hopkins University Baltimore United States Department of Biostatistics Johns Hopkins University Baltimore United States Department of Electrical and Computer Engineering Boston University Boston United States

ISBN: (纸本)9783031787607

Functional connectivity, reflecting synchronized brain activity across distinct regions, is crucial for understanding cognitive processes. Despite the recent interest in exploring the relationship between functional connectivity and structural brain features, understanding the precise link remains challenging. We propose a novel analysis method that integrates structural factors-such as anatomical morphology summaries, voxel intensity, diffusion-weighted information, and geographic distance to explain variation in functional connectivity. Our method employs generalized additive model (GAM), leveraging region-pair or vertex-pair information, while accommodating individual subject differences in both template and subject spaces. Furthermore, we assess repeatability via the so called discriminability of subjects under our approach, quantifying the probability of similarities between measurements for the same subject versus different subjects. Utilizing data from the Human Connectome Project, we analyze brain connectivity in twin pairs and non-twin pairs to evaluate the repeatability of model-based connectivity patterns estimated via GAMs. Our findings suggest that direct structure/function regression models enhances our understanding of functional connectivity variation, providing insights into underlying mechanisms and discriminability of brain connections. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

Sparse parity random linear codes for URLLC in channels with memory 59

Sparse parity random linear codes for URLLC in channels with...

引用

59th Annual Conference on Information Sciences and Systems, CISS 2025

作者： Jones, Steven Cooper, A. Brinton Johns Hopkins University Department of Electrical and Computer Engineering BaltimoreMD21218 United States

ISBN: (纸本)9798331513269

The use of short error-correcting codes is vital for achieving an Ultra-Reliable Low Latency Communications capability for supporting the Internet of Things with minimal decoding complexity. Here we examine the performance and decoding complexity of two code-agnostic decoders for a new class of full-rank sparse random linear codes derived from the MacKay-Neal LDPC construction. We consider decoding by a noise guessing decoder such as GRAND-MO and by a binary matching pursuit decoder to which list decoding is added. Comparisons are made in the context of error correction performance and computational complexity. © 2025 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Prescribing Decision Conservativeness in Two-Stage Power Markets: A Distributionally Robust End-to-End Approach 59

Prescribing Decision Conservativeness in Two-Stage Power Mar...

引用

59th Annual Conference on Information Sciences and Systems, CISS 2025

作者： Liang, Zhirui Li, Qi Liu, Anqi Dvorkin, Yury Johns Hopkins University Department of Applied Mathematics and Statistics BaltimoreMD United States Johns Hopkins University Department of Computer Science BaltimoreMD United States Johns Hopkins University Department of Electrical and Computer Engineering BaltimoreMD United States Johns Hopkins University Department of Civil and System Engineering BaltimoreMD United States

ISBN: (纸本)9798331513269

This paper presents an end-to-end framework for calibrating wind power forecast models to minimize operational costs in two-stage power markets, where the first stage involves a distributionally robust optimal power flow (DR-OPF) model. Unlike traditional methods that adjust forecast parameters and uncertainty quantification (UQ) separately, this framework jointly optimizes both the forecast model parameters and the decision conservativeness, which determines the size of the ambiguity set in the DR-OPF model. The framework aligns UQ with actual uncertainty realizations by directly optimizing downstream operational costs, a process referred to as cost-oriented calibration. The calibration is achieved using a gradient descent approach. To enable efficient differentiation, the DR-OPF problem is reformulated into a convex form, and the Envelope Theorem is leveraged to simplify gradient derivation in the two-stage setting. Additionally, the framework supports distributed implementation, effectively reducing computational overhead and enhancing efficiency. By proactively calibrating forecast parameters and prescribing optimal decision conservativeness, the framework significantly enhances cost efficiency and reliability in power system operations. Numerical experiments on an IEEE 5-bus system demonstrate the effectiveness and efficiency of the proposed approach. © 2025 IEEE.

关键词： Wind forecasting

来源：评论

学校读者我要写书评

暂无评论

Hybrid 1D and 2D CNN-Transformer Architectures for Multilabel 12-Lead EKG Anomaly Detection

Hybrid 1D and 2D CNN-Transformer Architectures for Multilabe...

引用

Annual Conference on Information Sciences and Systems (CISS)

作者： Ian DeTore John Samsundar Cleon Davis Electrical and Computer Engineering Program Johns Hopkins University Baltimore MD USA Electrical and Computer Engineering Program Johns Hopkins University Laurel MD USA

ISBN: (数字)9798331513269

ISBN: (纸本)9798331513276

关键词： Time-frequency analysis Multi label classification Machine learning Electrocardiography Myocardium Brain modeling Transformers Data models Electromyography Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Diagnosis via Swarm-Optimized Adaptive Neuro-Fuzzy Inference System

Breast Cancer Diagnosis via Swarm-Optimized Adaptive Neuro-F...

引用

Annual Conference on Information Sciences and Systems (CISS)

作者： Aidan Greenlee Neil F. Palumbo Electrical and Computer Engineering Program Johns Hopkins University Baltimore MD

ISBN: (数字)9798331513269

ISBN: (纸本)9798331513276

关键词： Training Adaptive systems Accuracy Sensitivity Linguistics Breast cancer Particle swarm optimization System analysis and design Tuning Testing

来源：评论

学校读者我要写书评

暂无评论

Low-Rank Adaptation of Segment Anything Model for Surgical Scene Segmentation 27th

Low-Rank Adaptation of Segment Anything Model for Surgical S...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Paranjape, Jay N. Sikder, Shameema Vedula, S. Swaroop Patel, Vishal M. Electrical and Computer Engineering Department Johns Hopkins University BaltimoreMD21218 United States Wilmer Eye Institute Johns Hopkins School of Medicine BaltimoreMD21287 United States Malone Center for Engineering in Healthcare Johns Hopkins University BaltimoreMD21218 United States

ISBN: (纸本)9783031781971

Surgical scene segmentation is an important task in the automated analysis of surgical videos and medical images. Traditional techniques for this task suffer from severe data scarcity characteristic of the medical domain. To address this challenge, contemporary research utilizes pre-trained models, which are finetuned using available data. Nonetheless, this approach involves repeated training of models with millions of parameters whenever new data becomes available. A recent foundational model called Segment Anything (SAM) has demonstrated impressive generalization capability in natural images, offering a potential resolution to this challenge. However, its applicability to the medical domain is hindered by its compute-intensive training along with need for task-specific prompts. These prompts can be bounding-boxes or foreground/background points, mandating expert annotation of every image. Expert annotation is not feasible as data volume increases. In this study, we propose LoRASAM - a highly efficient adaptation of SAM that enables text-guided segmentation of medical images. LoRASAM uses the labelname for precise image segmentation. To facilitate finetuning of LoRASAM, we utilize low-rank adaptation, which reduces the number of training parameters by more than 99% as compared to SAM, while significantly improving performance (about 70%). Extensive experimentation over three public surgical-scene datasets validates the superiority of LoRASAM over existing state-of-the-art methodologies. In addition, we show similar gains for non-surgical modalities such as x-ray and ultrasound. Our approach has the potential to enhance the segmentation performance and curtail expert involvement while adapting SAM for niche applications. Code: https://***/JayParanjape/LoRASAM © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Survey

引用

ACM Computing Surveys 2025年第8期57卷 1-37页

作者： Xu, Huali Zhi, Shuaifeng Sun, Shuzhou Patel, Vishal Liu, Li College of Computer Science Nankai University Tianjin China College of Electronic Science and Technology National University of Defense Technology Changsha China Faculty of Information Technology and Electrical Engineering University of Oulu Oulu Finland Johns Hopkins University Baltimore United States

While deep learning excels in computer vision tasks with abundant labeled data, its performance diminishes significantly in scenarios with limited labeled samples. To address this, Few-shot learning (FSL) enables models to perform the target tasks with very few labeled examples by leveraging prior knowledge from related tasks. However, traditional FSL assumes that both the related and target tasks come from the same domain, which is a restrictive assumption in many real-world scenarios where domain differences are common. To overcome this limitation, Cross-domain few-shot learning (CDFSL) has gained attention, as it allows source and target data to come from different domains and label spaces. This article presents the first comprehensive review of Cross-domain Few-shot Learning (CDFSL), a field that has received less attention compared to traditional FSL due to its unique challenges. We aim at providing both a position article and a tutorial for researchers, covering key problems, existing methods, and future research directions. The review begins with a formal definition of CDFSL, outlining its core challenges, followed by a systematic analysis of current approaches, organized under a clear taxonomy. Finally, we discuss promising future directions in terms of problem setups, applications, and theoretical advancements. © 2025 Copyright held by the owner/author(s).

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Advanced Facial Emotion Classification with 135 Classes for Enhanced Cybersecurity Applications 4

Advanced Facial Emotion Classification with 135 Classes for ...

引用

4th IEEE International Conference on Artificial Intelligence in Cybersecurity, ICAIC 2025

作者： Powers, Gregory Jin, Aobo Tonmoy, Abdul Basit Cao, Haowei Gohel, Hardik Deng, Qixin Wabash College Mathematics and Computer Science Crawfordsville United States University of Houston Victoria Computer Science Victoria United States Johns Hopkins University Electrical and Computer Engineering Baltimore United States

ISBN: (纸本)9798331518882

A key component of behavior analysis and human-computer interaction (HCI) is facial expression detection, which helps systems understand and react to human emotions more effectively and nuancedly. While previous research predominantly focuses on classifying seven or eight primary emotions, there has been limited exploration into more detailed and varied emotional expressions. In this paper, we address this gap by utilizing a recently published dataset that includes 135 distinct emotional classes, significantly increasing the complexity and granularity of emotion recognition tasks. To tackle this challenge, we propose a novel framework that combines U-Net and ResNet architectures, leveraging the strengths of each to capture intricate emotional cues and spatial features. Our approach achieves higher accuracy than current state-of-the-art (SOTA) methods, demonstrating its effectiveness for high-dimensional emotion classification in complex, real-world applications. © 2025 IEEE.

关键词： computer vision deep learning facial emotion recognition

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：