检索结果-内蒙古大学图书馆

International Conference on Image Information Processing

作者： N V Sai Manoj M Rithani R S SyamDev Department of Computer Science and Engineering (AIE) Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India Department of AI & ML New Horizon College of Engineering Bangalore

ISBN: (数字)9798350371406

ISBN: (纸本)9798350371413

Even with the present state of medical imaging technology, accurately and quickly detecting stomach cancer is still a major difficulty. Even though many detection techniques have advanced, current research noticeably lacks a cohesive strategy that integrates multiple models for reliable detection. In response, this research uses stacking ensembling methods to present a unique paradigm for stomach cancer diagnosis. Our goal is to increase the accuracy of stomach cancer diagnosis by using the power of many sophisticated semantic segmentation models, such as U-Net, DeepLab, and SegNet, in order to overcome the current constraints. We comprehensively examine the effectiveness of the various models and the ensemble technique via a rigorous review of important performance measures, such as accuracy (Ensemble: 97.8%, U-Net: 95.8%, DeepLab: 93.3%, SegNet: 92.5%), F1 score, ROC-AUC, precision, recall, and IoU. According to our findings, the ensemble model—which is enabled by a Random Forest Classifier—performs better than the individual models in identifying stomach cancer. By offering a complete and accurate method for the accurate and dependable identification of stomach cancer, this research contributes significantly to the area of medical image analysis and facilitates early diagnosis and better patient outcomes.

关键词： Deep learning Solid modeling Stomach Analytical models Image analysis Semantic segmentation Stacking

来源：评论

学校读者我要写书评

暂无评论

Aligning diffusion behaviors with Q-functions for efficient continuous control 24

Aligning diffusion behaviors with Q-functions for efficient ...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Huayu Chen Kaiwen Zheng Hang Su Jun Zhu Department of Computer Science and Technology Tsinghua University and Institute for AI BNRist Center Tsinghua-Bosch Joint ML Center THBI Lab Tsinghua University Department of Computer Science and Technology Tsinghua University and Institute for AI BNRist Center Tsinghua-Bosch Joint ML Center THBI Lab Tsinghua University and Pazhou Lab (Huangpu) Guangzhou China

ISBN: (纸本)9798331314385

Drawing upon recent advances in language model alignment, we formulate offline Reinforcement Learning as a two-stage optimization problem: First pretraining expressive generative policies on reward-free behavior datasets, then fine-tuning these policies to align with task-specific annotations like Q-values. This strategy allows us to leverage abundant and diverse behavior data to enhance generalization and enable rapid adaptation to downstream tasks using minimal annotations. In particular, we introduce Efficient Diffusion Alignment (EDA) for solving continuous control problems. EDA utilizes diffusion models for behavior modeling. However, unlike previous approaches, we represent diffusion policies as the derivative of a scalar neural network with respect to action inputs. This representation is critical because it enables direct density calculation for diffusion models, making them compatible with existing LLM alignment theories. During policy fine-tuning, we extend preference-based alignment methods like Direct Preference Optimization (DPO) to align diffusion behaviors with continuous Q-functions. Our evaluation on the D4RL benchmark shows that EDA exceeds all baseline methods in overall performance. Notably, EDA maintains about 95% of performance and still outperforms several baselines given only 1% of Q-labelled data during fine-tuning. Code: https://***/thu-ml/Efficient-Diffusion-Alignment

关键词：

来源：评论

学校读者我要写书评

暂无评论

Advancing Non-intrusive Suppression on Enhancement Distortion for Noise Robust ASR

Advancing Non-intrusive Suppression on Enhancement Distortio...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Wang, Wei Zhao, Siyi Qian, Yanmin Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence AI Institute Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9798350368741

Recent advancements in speech enhancement (SE) techniques have greatly improved speech clarity and intelligibility in challenging acoustic environments. However, integrating SE into automatic speech recognition (ASR) systems often results in performance degradation due to artifacts introduced during the enhancement process. While various methods have enhanced recognition accuracy in SE-ASR systems, they often require fine-tuning or re-training of SE or ASR models, which is impractical in many real-world applications. In this paper, we propose a lightweight distortion suppression (DS) network that addresses these artifacts without modifying the SE or ASR models, treating them as fixed black boxes. The DS module operates on the time-frequency (T-F) bands of the original and enhanced complex spectrograms, efficiently compensating for SE distortions using the original T-F information. We validate our approach through experiments on both Mandarin and English ASR tasks using monaural and multi-channel SE frontends, across various ASR backends. Results show that the DS module significantly improves the performance of SE-ASR systems, even when used with robust commercial ASR backends. © 2025 IEEE.

关键词： non-intrusive robust speech recognition speech distortion speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Terahertz Communications and Sensing Overview 3

Terahertz Communications and Sensing Overview

引用

3rd International Conference on Advancement in Electronics and Communication engineering, AECE 2023

作者： Salama, Ramiz Altrjman, Chadi Al-Turjman, Fadi Yadav, Satya Prakash Vats, Satvik Gupta, Richa Ai and Robotics Institute Research Center for Ai and IoT Near East University Department of Computer Engineering Near East Boulevard TRNC Mersin 10 Nicosia99138 Turkey Waterloo University Department of Chemical Engineering ONN2L 3G1 Canada Ai and Robotics Institute Near East University Artificial Intelligence Engineering Dept Mersin10 Nicosia Turkey Department of Computer Science and Engineering Greater Noida201306 India Graphic Era Hill University Department of Computer Science and Engineering Dehradun India Raj Kumar Goel Institute of Technology Department of Electronics & Communication Engineering India

ISBN: (纸本)9798350330724

Terahertz (THz) (0.1-10 THz) wireless communication is one of the cornerstones of the next 6G wireless networks. THz frequencies have the ability to dramatically increase wireless capacity performance and enable high-resolution environment sensing if applied properly due to the enormous quantity of accessible bandwidth. However, the usage of wireless devices in high-frequency bands like THz is constrained by a very unpredictable and dynamic channel. The ultimate result is essentially unreliable intermittent connections since these channel constraints have a naturally restricted communication range and a high susceptibility to blocking and chemical absorption. Because of this, the THz band's potential for high-rate communications and high-resolution sensing may be hindered. This study thoroughly examines the steps necessary to build up and operate next-generation THz wireless networks that will work together to deliver a variety of communication and sensing services in this environment. We first lay the groundwork for this by defining the THz frequency range's fundamentals. Using these fundamentals as a foundation, we outline and carefully investigate seven specific qualities that characterize THz wireless systems: Some of the subjects discussed include the quasi-opticality of the band, wireless architectures suited for THz, synergy with lower frequency bands, cooperative sensing and communication systems, PHY-layer protocols, spectrum access techniques, and real-time network optimization. These seven distinctive features enable our understanding of how to re-engineer wireless systems as we know them today to fit THz bands and their specific settings. On the one hand, THz systems make use of its quasi-optimality and may turn any sensing opportunity into a communication problem, aiding in the development of a new breed of flexible wireless systems that can do many jobs beyond straightforward communications. THz systems can alternatively use intelligent surfaces, lower

关键词： Internet of Everything

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Impact of Security Measures on Wi-Fi Quality of Service 2

Analyzing the Impact of Security Measures on Wi-Fi Quality o...

引用

2nd International Conference on Artificial Intelligence, Blockchain, and Internet of Things, aiBThings 2024

作者： Kopcho, Thomas J. Fouda, Mostafa M. Krome, Cameron J. Quach, Anna T. Olaveson, Israel G. Idaho State University Department of Computer Science PocatelloID United States Idaho State University Department of Electrical and Computer Engineering PocatelloID United States Ai Data & Visualization Idaho National Laboratory Idaho FallsID United States

ISBN: (纸本)9798331529529

This study examines the relationship between Quality of Service (QoS) and security in Wi-Fi networks. Using a detailed dataset consisting of QoS metrics of file transfers under various security configurations, we analyze the impact of these settings on network performance. Our findings provide a quantification to accurately show that different encryption protocols, such as TKIP and CCMP, significantly affect QoS, with disabling security generally improving performance. The study provides a framework for optimizing security settings to enhance both security and QoS in future wireless networks. © 2024 IEEE.

关键词： Wireless local area networks (WLAN)

来源：评论

学校读者我要写书评

暂无评论

Zero-shot Commonsense Reasoning over Machine Imagination

Zero-shot Commonsense Reasoning over Machine Imagination

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Park, Hyuntae Kim, Yeachan Park, Jun-Hyung Lee, SangKeun Department of Artificial Intelligence Korea University Seoul Korea Republic of Division of Language & AI Hankuk University of Foreign Studies Seoul Korea Republic of Department of Computer Science and Engineering Korea University Seoul Korea Republic of

ISBN: (纸本)9798891761681

Recent approaches to zero-shot commonsense reasoning have enabled Pre-trained Language Models (PLMs) to learn a broad range of commonsense knowledge without being tailored to specific situations. However, they often suffer from human reporting bias inherent in textual commonsense knowledge, leading to discrepancies in understanding between PLMs and humans. In this work, we aim to bridge this gap by introducing an additional information channel to PLMs. We propose IMAGINE (Machine Imagination-based Reasoning), a novel zero-shot commonsense reasoning framework designed to complement textual inputs with visual signals derived from machine-generated images. To achieve this, we enhance PLMs with imagination capabilities by incorporating an image generator into the reasoning process. To guide PLMs in effectively leveraging machine imagination, we create a synthetic pretraining dataset that simulates visual question-answering. Our extensive experiments on diverse reasoning benchmarks and analysis show that IMAGINE outperforms existing methods by a large margin, highlighting the strength of machine imagination in mitigating reporting bias and enhancing generalization capabilities. © 2024 Association for Computational Linguistics.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

A Lightweight ai Model for Anomaly Detection in Wireless Networks 2

A Lightweight AI Model for Anomaly Detection in Wireless Net...

引用

2nd International Conference on Artificial Intelligence, Blockchain, and Internet of Things, aiBThings 2024

作者： Kopcho, Thomas J. Fouda, Mostafa M. Krome, Cameron J. Idaho State University Department of Computer Science PocatelloID United States Idaho State University Department of Electrical and Computer Engineering PocatelloID United States Idaho National Laboratory Ai Data & Visualization Idaho FallsID United States

ISBN: (纸本)9798331529529

Detecting network anomalies is critical for wireless network security and reliability. Traditional ai methods often require substantial computational resources, particularly when deployed on cloud servers, leading to increased network load and latency. In contrast, deploying ai models directly on end devices enables real-time data processing at the source, facilitating faster anomaly detection and mitigation. We propose a lightweight hierarchical ai model where initial inferences are made by a simple model and outputs confidence scores. Using a modified TOPSIS-based method, we determine an optimal confidence score threshold. Inferences below this threshold are forwarded to a more complex model for accurate analysis, reducing overall computational demands while maintaining high detection performance. Our approach is tested on a 5 G network dataset, demonstrating competitive performance compared to other anomaly detection models. © 2024 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Deep learning model for pleural effusion detection via active learning and pseudo-labeling: a multisite study

引用

BMC Medical Imaging 2024年第1期24卷 1-10页

作者： Chang, Joseph Lin, Bo-Ru Wang, Ti-Hao Chen, Chung-Ming Department of Biomedical Engineering College of Medicine and College of Engineering National Taiwan University No. 1 Sec. 1 Jen-Ai Road Taipei 100 Taipei 100 Taiwan EverFortune.AI Co. Ltd Taichung Taiwan The Data Science Degree Program College of Electrical Engineering and Computer Science National Taiwan University and Academia Sinica Taipei Taiwan Department of Radiation Oncology China Medical University Hospital Taichung Taiwan Department of Medicine China Medical University Taichung Taiwan

Background: The study aimed to develop and validate a deep learning-based computer aided Triage (CADt) algorithm for detecting pleural effusion in chest radiographs using an active learning (AL) framework. This is aimed at addressing the critical need for a clinical grade algorithm that can timely diagnose pleural effusion, which affects approximately 1.5 million people annually in the United States. Methods: In this multisite study, 10,599 chest radiographs from 2006 to 2018 were retrospectively collected from an institution in Taiwan to train the deep learning algorithm. The AL framework utilized significantly reduced the need for expert annotations. For external validation, the algorithm was tested on a multisite dataset of 600 chest radiographs from 22 clinical sites in the United States and Taiwan, which were annotated by three U.S. board-certified radiologists. Results: The CADt algorithm demonstrated high effectiveness in identifying pleural effusion, achieving a sensitivity of 0.95 (95% CI: [0.92, 0.97]) and a specificity of 0.97 (95% CI: [0.95, 0.99]). The area under the receiver operating characteristic curve (AUC) was 0.97 (95% DeLong’s CI: [0.95, 0.99]). Subgroup analyses showed that the algorithm maintained robust performance across various demographics and clinical settings. Conclusion: This study presents a novel approach in developing clinical grade CADt solutions for the diagnosis of pleural effusion. The AL-based CADt algorithm not only achieved high accuracy in detecting pleural effusion but also significantly reduced the workload required for clinical experts in annotating medical data. This method enhances the feasibility of employing advanced technological solutions for prompt and accurate diagnosis in medical settings. © The Author(s) 2024.

关键词： Active learning Chest radiographs Deep learning Pleural effusion X-rays

来源：评论

学校读者我要写书评

暂无评论

Convergence of Monte Carlo Exploring Starts with TD-Learning 63

Convergence of Monte Carlo Exploring Starts with TD-Learning

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Winnicki, Anna Srikant, R. University of Illinois at Urbana-Champaign Coordinated Science Laboratory Department of Electrical and Computer Engineering United States Uiuc C3.ai Digital Transformation Institute United States

ISBN: (纸本)9798350316339

The use of TD-learning has been widely employed in reinforcement learning algorithms due to its efficiency and practicality. Herein, we study the convergence of a variant of Monte Carlo Exploring Starts when operatornameTD(λ) is used in policy evaluation and policy improvement, and lookahead is used in the policy improvement step. Our results provide a threshold for the amount of lookahead that ensures convergence of Monte Carlo Exploring Starts with T D(λ) as a function of λ in[0,1]. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Classification Technique for Online Shoppers' Purchasing Intention 1

A Classification Technique for Online Shoppers' Purchasing I...

引用

1st International Conference on Logistics, ICL 2024

作者： Mostafa, Salama A. Al-Dayyeni, Wisam Subhi Fadel, Ali Hussein Abbas, Ali Hashim Jaber, Mustafa Musa Ali, Rabei Raad Universiti Tun Hussein Onn Malaysia Faculty of Computer Science and Information Technology Johor86400 Malaysia School of Information Technologies and Engineering ADA University BakuAZ1008 Azerbaijan University of Diyala Department of Computer Science Diyala32001 Iraq Imam Ja'afar Al-Sadiq University Department of Computer Engineering and Information Technology AI-Muthanna Iraq Al-Farahidi University Department of Medical Instruments Engineering Techniques Baghdad10021 Iraq Northern Technical University Department of Computer Engineering Technology Mosul41000 Iraq

ISBN: (纸本)9798331518844

Online shopping has become a recent outburst using electronic devices that allow consumers to shop online, as there are factors that influence shopping intention. The factors include consumers' attitudes, subject norms, behavior control, perception of usefulness, considered risks, and trust. This study aims to classify the intent of online consumers' shopping. Subsequently, based on these measures, this classification can provide fundamental and prioritized suggestions for performance improvements in online shopping. The classification is performed by using four data mining algorithms, which are random forest (RF), decision tree (DT), support vector machines (SVMs), and k-nearest neighbors (k-NN). Classification of online shoppers has been implemented based on the online shopping behavior dataset and critical performance metrics, including accuracy, precision, recall, and F1-measure. Essential factors have been considered in the online shopping behavior dataset that was used. The dataset has been preprocessed to check missing values and change the data to an appropriate numerical type. Then, the classification algorithms are applied to extract the required results. The results of detecting consumer shopping behavior showed that RF has outperformed other algorithms and achieved an average accuracy of 90.24%. The average classification accuracies of the DT, SVM, and k-NN are 89.59%, 89.38%, and 87.06%, respectively. The result of this work is hoped to assist in identifying online shoppers' behavior categories in practical aspects. © 2024 IEEE.

关键词： Support vector machines

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：