检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Abdar, Moloud Salari, Soorena Qahremani, Sina Lam, Hak-Keung Karray, Fakhri Hussain, Sadiq Khosravi, Abbas Acharya, U. Rajendra Makarenkov, Vladimir Nahavandi, Saeid Deakin University Australia The Harvard Paulson School of Engineering and Applied Sciences Harvard University AllstonMA02134 United States The Department of Electrical Engineering Sharif University of Technology Tehran Iran The Centre for Robotics Research Department of Engineering King’s College London London United Kingdom The Centre for Pattern Analysis and Machine Intelligence Department of Electrical and Computer Engineering University of Waterloo WaterlooON Canada The Department of Machine Learning Mohamed Bin Zayed University of Artificial Intelligence Abu Dhabi United Arab Emirates The System Administrator Dibrugarh University Dibrugarh India The Department of Electronics and Computer Engineering Ngee Ann Polytechnic Clementi Singapore The Department of Computer Science University of Quebec in Montreal MontrealQC Canada

The COVID-19 (Coronavirus disease 2019) pandemic has become a major global threat to human health and well-being Thus, the development of computer-aided detection (CAD) systems that are capable to accurately distinguish COVID-19 from other diseases using chest computed tomography (CT) and X-ray data is of immediate priority Such automatic systems are usually based on traditional machine learning or deep learning methods Differently from most of existing studies, which used either CT scan or X-ray images in COVID-19-case classification, we present a simple but efficient deep learning feature fusion model, called UncertaintyFuseNet, which is able to classify accurately large datasets of both of these types of images We argue that the uncertainty of the model’s predictions should be taken into account in the learning process, even though most of existing studies have overlooked it We quantify the prediction uncertainty in our feature fusion model using effective Ensemble MC Dropout (EMCD) technique A comprehensive simulation study has been conducted to compare the results of our new model to the existing approaches, evaluating the performance of competing models in terms of Precision, Recall, F-Measure, Accuracy and ROC curves The obtained results prove the efficiency of our model which provided the prediction accuracy of 99.08% and 96.35% for the considered CT scan and X-ray datasets, respectively Moreover, our UncertaintyFuseNet model was generally robust to noise and performed well with previously unseen data The source code of our implementation is freely available at: https://***/moloud1987/UncertaintyFuseNet-for-COVID-19-Classification. Copyright © 2021, The Authors. All rights reserved.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Designing a Vertical Gallium Arsenide (GaAs) Channel High Electron Mobility Transistor (HEMT) for power applications in integrated circuit (IC) technology

引用

AIP Conference Proceedings 2024年第1期3149卷

作者： B. S. Hari Bhaskar Roy M. Elangovan S. Kaliappan G. Pavithra T. C. Manjunath Department of Mechanical Engineering Kongu Engineering College Perundurai Erode Tamilnadu India Department of Artificial Intelligence and Machine Learning Asansol Engineering College Vivekananda Sarani Asansol West Bengal India Department of Aerospace Engineering SNS College of Technology Coimbatore Tamilnadu India Division of Research and Development Lovely Professional University Jalandhar - Delhi G.T. Road Phagwara Punjab India Department of Electronics & Communication Engg. Dayananda Sagar College of Engg. Bengaluru Karnataka India

The research article investigates the development of Vertical Gallium Arsenide (GaAs) Channel High Electron Mobility Transistor (HEMT) for Power Applications in IC technology. This specialized transistor, the Vertical GaAs Channel HEMT, is designed with unique properties enabling its application in high-frequency and high-power operations, particularly in power-related contexts. The abstract succinctly encapsulates the ongoing progress in this development, emphasizing its primary focus on enhancing power efficiency and performance within integrated circuits (ICs). The innovation seeks to facilitate the creation of more compact and efficient electronic devices by integrating power applications seamlessly into ICs. Notably, the technology’s ability to operate at higher frequencies renders it pertinent for applications in communication and radar systems. The study also explores the potential for reducing power consumption, aligning with the industry’s overarching commitment to energy-efficient electronics. The broader applications of Vertical GaAs Channel HEMT extend into emerging fields such as 5G communication and satellite technology, signifying substantial advancements in the realm of advanced and efficient electronic systems. The abstract concludes by recommending researchers refer to recent academic journals and industry publications for the latest updates on semiconductor advancements.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Integrating Speech-to-Text for Image Generation Using Generative Adversarial Networks

引用

Computer Modeling in engineering & Sciences 2025年第5期143卷 2001-2026页

作者： Smita Mahajan Shilpa Gite Biswajeet Pradhan Abdullah Alamri Shaunak Inamdar Deva Shriyansh Akshat Ashish Shah Shruti Agarwal Artificial Intelligence and Machine Learning Department Symbiosis Institute of TechnologyPune412115India Symbiosis Centre of Applied AI(SCAAI) Symbiosis Institute of TechnologyPune412115India Centre for Advanced Modelling and Geospatial Information Systems(CAMGIS) School of Civil and Environmental EngineeringUniversity of Technology SydneySydneyNSW 2007Australia Department of Geology and Geophysics College of ScienceKing Saud UniversityRiyadhl451Saudi Arabia Department of Computer Science and Enginering Symbiosis Institute of TechnologyPune412115India

The development of generative architectures has resulted in numerous novel deep-learning models that generate images using text ***,humans naturally use speech for visualization ***,this paper proposes an architecture that integrates speech prompts as input to image-generation Generative Adversarial Networks(GANs)model,leveraging Speech-to-Text translation along with the CLIP+VQGAN *** proposed method involves translating speech prompts into text,which is then used by the Contrastive Language-Image Pretraining(CLIP)+Vector Quantized Generative Adversarial Network(VQGAN)model to generate *** paper outlines the steps required to implement such a model and describes in detail the methods used for evaluating the *** GAN model successfully generates artwork from descriptions using speech and text *** outcomes of synthesized images demonstrate that the proposed methodology can produce beautiful abstract visuals containing elements from the input *** model achieved a Frechet Inception Distance(FID)score of 28.75,showcasing its capability to produce high-quality and diverse *** proposed model can find numerous applications in educational,artistic,and design spaces due to its ability to generate images using speech and the distinct abstract artistry of the output *** capability is demonstrated by giving the model out-of-the-box prompts to generate never-before-seen images with plausible realistic qualities.

关键词： Generative adversarial networks speech-to-image translation visualization transformers prompt engineering

来源：评论

学校读者我要写书评

暂无评论

FXAM: A Unified and Fast Interpretable Model for Predictive Analytics

arXiv

引用

arXiv 2021年

作者： Jiang, Yuanyuan Ding, Rui Qiao, Tianchi Zhu, Yunan Han, Shi Zhang, Dongmei School of Statistics Renmin University of China Haidian District Beijing100872 China Microsoft Research Asia Haidian District Beijing100080 China School of Computer Science and Engineering Southeast University Jiangsu Province Nanjing211189 China School of Information Science and Technology University of Science and Technology of China Anhui Province He Fei230031 China Department of Machine Learning Mohamed bin Zayed University of Artificial Intelligence Masdar City Abu Dhabi United Arab Emirates

Predictive analytics aims to build machine learning models to predict behavior patterns and use predictions to guide decision-making. Predictive analytics is human involved, thus the machine learning model is preferred to be interpretable. In literature, Generalized Additive Model (GAM) is a standard for interpretability. However, due to the one-to-many and many-to-one phenomena which appear commonly in real-world scenarios, existing GAMs have limitations to serve predictive analytics in terms of both accuracy and training efficiency. In this paper, we propose FXAM (Fast and eXplainable Additive Model), a unified and fast interpretable model for predictive analytics. FXAM extends GAM’s modeling capability with a unified additive model for numerical, categorical, and temporal features. FXAM conducts a novel training procedure called Three-Stage Iteration (TSI). TSI corresponds to learning over numerical, categorical, and temporal features respectively. Each stage learns a local optimum by fixing the parameters of other stages. We design joint learning over categorical features and partial learning over temporal features to achieve high accuracy and training efficiency. We prove that TSI is guaranteed to converge to the global optimum. We further propose a set of optimization techniques to speed up FXAM’s training algorithm to meet the needs of interactive analysis. Thorough evaluations conducted on diverse data sets verify that FXAM significantly outperforms existing GAMs in terms of training speed, and modeling categorical and temporal features. In terms of interpretability, we compare FXAM with the typical post-hoc approach XGBoost+SHAP on two real-world scenarios, which shows the superiority of FXAM’s inherent interpretability for predictive analytics. Copyright © 2021, The Authors. All rights reserved.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Mixture of Experts-Enabled Parallel Scheduling and Processing for Vehicular Generative AI Services

引用

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Xie, Gaochang Xiong, Zehui Xie, Renchao Deng, Xiumei Guo, Song Guizani, Mohsen Han, Zhu Beijing University of Posts and Telecommunication State Key Laboratory of Networking and Switching Technology Beijing100876 China Purple Mountain Laboratories Nanjing211111 China Singapore University of Technology and Design Information Systems Technology and Design Pillar 487372 Singapore The Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong Mohammad Bin Zayed University of Artificial Intelligence Machine Learning Department Abu Dhabi United Arab Emirates University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

Foundation models (FMs) have revolutionized generative AI (GAI) lifecycle with their pre-trained intelligence capabilities. While the recent success of web-based models like GPT-4 has spurred interest in extending FMs to edge scenarios like the Internet of Vehicles (IoV), challenges such as data privacy, network congestion, and limited edge resource awareness hinder the direct application of cloud-based FMs. To address these challenges, this paper reconfigures the mixture of experts (MoE) architecture to deploy Transformer-based FM experts across vehicles for distributed GAI inference. Specifically, we propose an MoE-empowered vehicular FM system with two key innovations: a physical gating network that dynamically adapts to wireless environments, and a vehicle-to-vehicle (V2V) communication-based expert parallelism mechanism to enhance efficiency and resource utilization. Then, we formulate the communication, computation, and memory models for analyzing inference latency. Furthermore, to optimize the computational resource allocation for enhancing inference performance, we establish a Stackelberg game and propose the Gradient Ascent and Evolutionary Optimization-based Competitive Pricing and Allocation (GECPA) algorithm, which balances resource allocation and usage costs by combining the rapid convergence of gradient ascent with the broader exploration capability of evolutionary optimization. Simulation results demonstrate the superior parallel processing efficiency and reduced latency of the proposed MoE-based FM inference scheme. Compared with the best-performing benchmark algorithm, GECPA improves the average utility of infrastructure vehicles by up to 2.01 times, reduces inference latency by 16.58%, and increases the successful execution rate of GAI tasks by 10.66%, thereby achieving a better balance between efficiency and incentive compatibility in dynamic IoV environments. © 2015 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Multi-label Classification with High-rank and High-order Label Correlations

arXiv

引用

arXiv 2022年

作者： Si, Chongjie Jia, Yuheng Wang, Ran Zhang, Min-Ling Feng, Yanghe Qu, Chongxiao The Chien-Shiung Wu College Southeast University Nanjing210096 China The MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai200240 China The School of Computer Science and Engineering Southeast University Nanjing210096 China Ministry of Education China School of Computing & Information Sciences Caritas Institute of Higher Education Hong Kong The Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China The School of Mathematical Science Shenzhen University Shenzhen518060 China Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen University Shenzhen518060 China The College of Systems Engineering National University of Defense Technology China The 52nd Research Institute of China Electronics Technology Group China

Exploiting label correlations is important to multi-label classification. Previous methods capture the high-order label correlations mainly by transforming the label matrix to a latent label space with low-rank matrix factorization. However, the label matrix is generally a full-rank or approximate full-rank matrix, making the low-rank factorization inappropriate. Besides, in the latent space, the label correlations will become implicit. To this end, we propose a simple yet effective method to depict the high-order label correlations explicitly, and at the same time maintain the high-rank of the label matrix. Moreover, we estimate the label correlations and infer model parameters simultaneously via the local geometric structure of the input to achieve mutual enhancement. Comparative studies over twelve benchmark data sets validate the effectiveness of the proposed algorithm in multi-label classification. The exploited high-order label correlations are consistent with common sense empirically. Our code is publicly available at https://***/Chongjie-Si/HOMI. Copyright © 2022, The Authors. All rights reserved.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Enhancing mobility for the visually impaired with artificial intelligence and machine learning in IKSHANA

引用

AIP Conference Proceedings 2024年第1期3149卷

作者： Praveen Rathod D. N. Kavya Atul Gupta S. Kaliappan G. Pavithra T. C. Manjunath Dept. of Mechanical Engineering Vishwakarma Institute of Information Technology Pune India Dept. of Artificial Intelligence and Machine Learning Dayananda Sagar College of Engineering Banglore India Higher Education Madhya Pradesh Govt. College Ashoknagar Madhya Pradesh India Division of Research and Development Lovely Professional University Phagwara Punjab India Dept. of Electronics & Communication Engg. Dayananda Sagar College of Engg. Bengaluru Karnataka India

This paper explores the utilization of artificial intelligence and machine learning algorithms to empower visually impaired individuals, enabling satisfactory movement in their daily lives. The research focuses on enhancing the lives of the visually impaired by addressing challenges they face in unexpected situations. In today’s highly technological society, the need for independent living is crucial, especially for visually impaired individuals who often experience social exclusion detection of objects, facial based recognitions, emotion-based recognitions, currency-based recognitions, web type automations, screen readings & emergency callings, we enhance the quality of life for the visually impaired. Implemented through ML, DL, speech to text & vice-versa, Selenium based web type automation frameworks, these technologies empower individuals to effectively adapt and respond to their environment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LNQ 2023 challenge: Benchmark of weakly-supervised techniques for mediastinal lymph node quantification

arXiv

引用

arXiv 2024年

作者： Dorent, Reuben Khajavi, Roya Idris, Tagwa Ziegler, Erik Somarouthu, Bhanusupriya Jacene, Heather LaCasce, Ann Deissler, Jonathan Ehrhardt, Jan Engelson, Sofija Fischer, Stefan M. Gu, Yun Handels, Heinz Kasai, Satoshi Kondo, Satoshi Maier-Hein, Klaus Schnabel, Julia A. Wang, Guotai Wang, Litingyu Wald, Tassilo Yang, Guang-Zhong Zhang, Hanxiao Zhang, Minghui Pieper, Steve Harris, Gordon Kikinis, Ron Kapur, Tina Brigham and Women’s Hospital Harvard Medical School BostonMA United States Massachusetts General Hospital Harvard Medical School BostonMA United States Yunu Inc. CaryNC United States Isomics Inc CambridgeMA United States Dana-Farber Cancer Institute BostonMA United States Technical University Munich Munich Germany Institute of Machine Learning in Biomedical Imaging Helmholtz Munich Munich Germany Munich Germany School of Biomedical Engineering and Imaging Sciences King’s College London London United Kingdom Institute of Medical Informatics University of Lübeck Lübeck Germany German Research Center for Artificial Intelligence Lübeck Germany Niigata University of Health and Welfare Niigata Japan Muroran Institute of Technology Hokkaido Japan Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China University of Electronic Science and Technology of China Chengdu China Heidelberg Germany University of Heidelberg Heidelberg Germany Shanghai AI laboratory Shanghai China

Accurate assessment of lymph node size in 3D CT scans is crucial for cancer staging, therapeutic management, and monitoring treatment response. Existing state-of-the-art segmentation frameworks in medical imaging often rely on fully annotated datasets. However, for lymph node segmentation, these datasets are typically small due to the extensive time and expertise required to annotate the numerous lymph nodes in 3D CT scans. Weakly-supervised learning, which leverages incomplete or noisy annotations, has recently gained interest in the medical imaging community as a potential solution. Despite the variety of weakly-supervised techniques proposed, most have been validated only on private datasets or small publicly available datasets. To address this limitation, the Mediastinal Lymph Node Quantification (LNQ) challenge was organized in conjunction with the 26th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2023). This challenge aimed to advance weakly-supervised segmentation methods by providing a new, partially annotated dataset and a robust evaluation framework. A total of 16 teams from 5 countries submitted predictions to the validation leaderboard, and 6 teams from 3 countries participated in the evaluation phase. The results highlighted both the potential and the current limitations of weakly-supervised approaches. On one hand, weakly-supervised approaches obtained relatively good performance with a median Dice score of 61.0%. On the other hand, top-ranked teams, with a median Dice score exceeding 70%, boosted their performance by leveraging smaller but fully annotated datasets to combine weak supervision and full supervision. This highlights both the promise of weakly-supervised methods and the ongoing need for high-quality, fully annotated data to achieve higher segmentation performance. . . © 2024, CC BY.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Supervised learning in the presence of concept drift a modelling framework

arXiv

引用

arXiv 2020年

作者： Straat, Michiel Abadi, Fthi Kan, Zhuoyun Göpfert, Christina Hammer, Barbara Biehl, Michael Bernoulli Institute for Mathematics Computer Science and Artificial Intelligence University of Groningen Nijenborgh 9 Groningen9747 AG Netherlands Aksum University Institute of Engineering and Technology Computing Science Department Axum Tigray Ethiopia Bielefeld University CITEC Machine Learning Group Bielefeld33594 Germany

We present a modelling framework for the investigation of supervised learning in non-stationary environments. Specifically, we model two example types of learning systems: prototype-based learning Vector Quantization (LVQ) for classification and shallow, layered neural networks for regression tasks. We investigate so-called student teacher scenarios in which the systems are trained from a stream of high-dimensional, labeled data. Properties of the target task are considered to be non-stationary due to drift processes while the training is performed. Different types of concept drift are studied, which affect the density of example inputs only, the target rule itself, or both. By applying methods from statistical physics, we develop a modelling framework for the mathematical analysis of the training dynamics in non-stationary environments. Our results show that standard LVQ algorithms are already suitable for the training in non-stationary environments to a certain extent. However, the application of weight decay as an explicit mechanism of forgetting does not improve the performance under the considered drift processes. Furthermore, we investigate gradient-based training of layered neural networks with sigmoidal activation functions and compare with the use of rectified linear units (ReLU). Our findings show that the sensitivity to concept drift and the effectiveness of weight decay differs significantly between the two types of activation function. Copyright © 2020, The Authors. All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Extensions of the open-source framework Aerostack 3.0 for the development of more interactive flights between UAVs

Extensions of the open-source framework Aerostack 3.0 for th...

引用

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Wojciech Giernacki Jacek Cieślak Martin Molina Pascual Campoy Institute of Robotics and Machine Intelligence Faculty of Control Robotics and Electrical Engineering Poznan University of Technology Poznań Poland Department of Artificial Intelligence Technical University of Madrid (UPM) Madrid Spain Computer Vision and Aerial Robotics (CVAR) Centre for Automation and Robotics Technical University of Madrid (UPM) Madrid Spain

ISBN: (数字)9781728142784

ISBN: (纸本)9781728142791

The basis for properly verified R&D works is to provide reliable prototyping tools at three most important stages: computer simulation, laboratory tests and real-world experiments. In the laboratory-limited conditions, particular importance is attributed to the first two stages, especially in the context of the safety development of autonomous flights of unmanned aerial vehicle (UAV) groups in various missions. The open-source framework Aerostack support those needs and its effectiveness has been proven in the International Micro Air Vehicle Indoor Competitions (IMAV 2013, 2016, 2017) and Mohammed Bin Zayed International Robotics Challenge (MBZIRC 2020). In the paper, the exemplary functionalities for the new version of Aerostack Version 3.0 Distribution Sirocco (Aerial robotics framework for the industry), extended additionally with a library of new behaviors, are presented. The mission of UAVs can be developed fast and effectively in order to conduct test flights with real drones in lab, before one will decide to fly autonomously outdoor. The representative results obtained for low-cost *** 2.0 UAV models in two missions, are presented. The first mission is autonomous patrolling the area by a pair of UAVs, the second - intercepting the intruder in guarded area by the guard UAV.

关键词： Robots Trajectory Drones Libraries Software Computer architecture

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：