检索结果-内蒙古大学图书馆

computer Vision and Machine Intelligence (CVMI), International Conference on

作者： Anand Verma Saurabh Agarwal K.V. Arya Ivan Petrlik Roberto Esparza Ciro Rodriguez Department of Information Technology ABV-IIITM Gwalior Madhya Pradesh India Department of Computer Science and Engineering Multimedia and Information Security Research Group ABV-Indian Institute of Information Technology and Management Gwalior India Faculty of Industrial and Systems Engineering National University Federico Villarreal Lima Peru Faculty of Systems Engineering and Informatics National University Mayor de San Marcos

Image captioning involves generating a natural language description that accurately represents the content and context of an image. To achieve this, image captioning utilises various machine learning techniques and fields, such as computer vision and natural language processing. In the field of image captioning, a lot of advances have been made with encoder-decoder models and reinforcement learning algorithms. However, there are still problems of imbalance between testing and training, as reinforcement learning only handles single comparator metrics such as CIDEr, SPICE, and BLEU and could not perform better in multiple metrics at once. Which is why a lack of diversity can be seen in generated captions. This idea proposes a general technique for collaborative updating that can bridge the gap between evaluation measures and test metrics to produce captions that are more human-like. To increase the precision of image captions, the approach involves using a compiled reward system that considers multiple evaluation metrics to compare the generated sentence with the provided sentences. We will evaluate the model's performance and the reward updating process on standard datasets like MS COCO.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Stability and dynamics of massive vortices in two-component Bose-Einstein condensates

引用

Physical Review E 2025年第3期111卷 034216-034216页

作者： J. D'Ambroise W. Wang C. Ticknor R. Carretero-González P. G. Kevrekidis Department of Mathematics Computer & Information Science State University of New York (SUNY) College at Old Westbury Westbury New York 11568 USA College of Physics Sichuan University Chengdu 610065 China Theoretical Division Los Alamos National Laboratory Los Alamos New Mexico 87545 USA Nonlinear Dynamical Systems Group Computational Sciences Research Center and Department of Mathematics and Statistics San Diego State University San Diego California 92182-7720 USA Department of Mathematics and Statistics University of Massachusetts Amherst Massachusetts 01003-4515 USA

The study of structures involving vortices in one component and bright solitary waves in another has a time-honored history in two-component atomic Bose-Einstein condensates. In the present work, we revisit this topic, extending considerations well past the near-integrable regime of nearly equal scattering lengths. Instead, we focus on stationary states and spectral stability of such structures for large values of the intercomponent interaction coefficient. We find that the state can manifest dynamical instabilities for suitable parameter values. We also explore a phenomenological, yet quantitatively accurate upon suitable tuning, particle model which, also in line with earlier works, offers the potential of accurately following the associated stability and dynamical features. Finally, we probe the dynamics of the unstable vortex-bright structure, observing an unprecedented, to our knowledge, instability scenario in which the oscillatory instability leads to a patch of vorticity that harbors and eventually ejects multiple vortex-bright structures.

关键词： Vortex flow

来源：评论

学校读者我要写书评

暂无评论

Cantilever Actuator Module for on-Command Drug Deployment from Ingestible Capsules

Cantilever Actuator Module for on-Command Drug Deployment fr...

引用

International Conference on Solid State Sensors and Actuators (TRANSDUCERS)

作者： Joshua A. Levy Michael A. Straker Luke A. Beardslee Reza Ghodssi Department of Materials Science and Engineering University of Maryland College Park Maryland USA Institute for Systems Research University of Maryland College Park Maryland USA Robert E. Fischell Institute for Biomedical Devices University of Maryland College Park Maryland USA Fischell Department of Bioengineering University of Maryland College Park Maryland USA Department of Electrical and Computer Engineering University of Maryland College Park Maryland USA

This manuscript demonstrates the first cantilever actuator for highly targeted and directionally specific delivery of drug-eluting microneedles to the gastrointestinal (GI) tract from ingestible devices. The actuator achieves the following advantages over current technology: on-command deployment in under 500 ms, low power consumption, spatial conservation, and prolonged deployment shelf life. These advancements enable integration of multiple actuators per device for multidirectional deployment. These attributes are achieved by the optimization of heater design and use of low-profile and highly relaxation resistant PEEK polymers. In all, these features enable higher delivery precision in both longitudinal and polar directions, potentiating site targeting in the GI tract.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The impact of digital transformation on the work of the Algerian local administration during the Corona-Covid 19 Pandemic

The impact of digital transformation on the work of the Alge...

引用

2021 International Conference on Artificial Intelligence for Cyber Security systems and Privacy, AI-CSP 2021

作者： Hani, Sadok Kiram, Pr Mohmmed Lakhdar Laouid, Abdelkader Alshaikh, Muath Faculty of Law and Political Science of Eloued University Detective Policies of Public and Improve the Service of the Public in Algeria Algeria El Oued University LIAP Laboratory El Oued39000 Algeria Saudi Electronic University College of Computing and Informatics Computer Science Department Riyadh11673 Saudi Arabia

ISBN: (纸本)9781665467148

During the Corona-Covid 19 pandemic, the digitalization of Algeria's administrative management system led to rapid and significant changes, including in the local administration, in order to preserve citizens' health. As in other countries, the Algerian government adheres to a health protocol that requires quarantine and social distancing. To maintain continuity in public service performance, the health protocal forced the public administration, including local administration, to perform digitization and distant work. Finally, we conclude that the rapid digital transformation of the work of the local administration, despite its shortcomings, has achieved a great deal of satisfaction and met the general needs of the citizen, not to mention its effective contribution to maintaining public health. © 2021 IEEE.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

LSTM deep learning model for Alzheimer’s disease prediction based on cost-effective time series cognitive scores

LSTM deep learning model for Alzheimer’s disease prediction...

引用

Novel Intelligent and Leading Emerging sciences Conference (NILES)

作者： Hager Saleh Nora El-Rashidy Tamer Abuhmed Shaker El-Sappagh Faculty of Computers and Artificial Intelligence South Valley University Hurghada Egypt Machine Learning and Information Retrieval Department Faculty of Artificial Intelligence Kafrelsheiksh University College of Computing and Informatics Sungkyunkwan University South Korea Faculty of Computer Science and Engineering Galala University Suez Egypt

Alzheimer’s disease (AD) is a complex chronic neurodegenerative disease that propagates over time. Deep learning (DL) models can be used to learn time series data to extract deep temporal features and make robust decisions. The fusion of multimodal time series data has been proven to enhance model performance [1]. For instance, cognitive scores (CSs) including clinical dementia rating, and Alzheimer’s disease assessment scores have been integrated with other modalities like MRI to predict the future status of AD patients [2]. They enhanced the performance of DL models. These scores can be collected easily and in a cost-effective way in hospitals. No study in the literature has built a deep learning model to predict AD based on the cost-effective and multimodal time series data of CSs. In this study, we propose an LSTM-based DL architecture to predict AD based on multiple time series CSs. The proposed model has been optimized using a Bayesian optimizer to select the best architecture, and it has been compared with multiple classical machine learning models like random forest and others. The proposed LSTM architecture achieved better results than other models and provided stable and robust performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On the Diversity and Coded Modulation Design of Fluid Antenna systems

arXiv

引用

arXiv 2022年

作者： Psomas, Constantinos Kraidy, Ghassan M. Wong, Kai-Kit Krikidis, Ioannis The Department of Electrical and Computer Engineering University of Cyprus Nicosia Cyprus The Department of Electronic Systems Norwegian University of Science and Technology Norway The Department of Electronic and Electrical Engineering University College London London United Kingdom

Reconfigurability is a desired characteristic of future communication networks. From a transceiver’s standpoint, this can be materialized through the implementation of fluid antennas (FAs). An FA consists of a dielectric holder, in which a radiating liquid moves between pre-defined locations (called ports) that serve as the transceiver’s antennas. Due to the nature of liquids, FAs can practically take any size and shape, making them both flexible and reconfigurable. In this paper, we deal with the outage probability of FAs under general fading channels, where a port is scheduled based on selection combining. An analytical framework is provided for the performance with and without errors due to post-scheduling delays. We show that although FAs achieve maximum diversity, this cannot be realized in the presence of delays. Hence, a linear prediction scheme is proposed that overcomes delays and restores the lost diversity by predicting the next scheduled port. Moreover, we design space-time coded modulations that exploit the FA’s sequential operation with space-time rotations and code diversity. The derived expressions for the pairwise error probability and average word error rate give an accurate estimate of the performance. We illustrate that the proposed design attains maximum diversity, while keeping a low-complexity receiver, thereby confirming the feasibility of FAs. Copyright © 2022, The Authors. All rights reserved.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

CloudAAE: Learning 6D object pose regression with on-line data synthesis on point clouds

arXiv

引用

arXiv 2021年

作者： Gao, Ge Lauri, Mikko Hu, Xiaolin Zhang, Jianwei Frintrop, Simone Department of Informatics University of Hamburg Germany State Key Laboratory of Intelligent Technology and Systems Department of Computer Science and Technology Tsinghua University China

It is often desired to train 6D pose estimation systems on synthetic data because manual annotation is expensive. However, due to the large domain gap between the synthetic and real images, synthesizing color images is expensive. In contrast, this domain gap is considerably smaller and easier to fill for depth information. In this work, we present a system that regresses 6D object pose from depth information represented by point clouds, and a lightweight data synthesis pipeline that creates synthetic point cloud segments for training. We use an augmented autoencoder (AAE) for learning a latent code that encodes 6D object pose information for pose regression. The data synthesis pipeline only requires texture-less 3D object models and desired viewpoints, and it is cheap in terms of both time and hardware storage. Our data synthesis process is up to three orders of magnitude faster than commonly applied approaches that render RGB image data. We show the effectiveness of our system on the LineMOD, LineMOD Occlusion, and YCB Video datasets. The implementation of our system is available at: https://***/GeeeG/CloudAAE. © 2021, CC BY.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Deep Neural Networks as Complex Networks

arXiv

引用

arXiv 2022年

作者： Malfa, Emanuele La Malfa, Gabriele La Caprioli, Claudio Nicosia, Giuseppe Latora, Vito Department of Computer Science University of Oxford United Kingdom Department of Informatics King's College London United Kingdom The Department of Biomedical & Biotechnological Sciences University of Catania Italy The Department of Physics and Astronomy"Ettore Majorana" University of Catania Italy

Deep Neural Networks are, from a physical perspective, graphs whose 'links'and 'vertices'iteratively process data and solve tasks sub-optimally. We use Complex Network Theory (CNT) to represents Deep Neural Networks (DNNs) as directed weighted graphs: within this framework, we introduce metrics to study DNNs as dynamical systems, with a granularity that spans from weights to layers, including neurons. CNT discriminates networks that differ in the number of parameters and neurons, the type of hidden layers and activations, and the objective task. We further show that our metrics discriminate low vs. high performing networks. CNT is a comprehensive method to reason about DNNs and a complementary approach to explain a model's behavior that is physically grounded to networks theory and goes beyond the well-studied input-output relation. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Utilising the Internet of Things to Enhance Customer Relationship Management in the field of Digital Marketing

Utilising the Internet of Things to Enhance Customer Relatio...

引用

Trends in Quantum Computing and Emerging Business Technologies (TQCEBT), International Conference on

作者： Mohammed Usman S. Gangadharan Muralidhar L B M.K. Murugesh Isac Gunday Mohit Tiwari Department of Management College of Economics Management and Information Systems University of Nizwa Sultanate of Oman Department of Management Studies St. Joseph's college of Engineering Chennai Department of Business Management Studies School of Commerce JAIN( Deemed to be University) Bengaluru Karnataka Hotel Management K.L. University Vijayawada Andhra Pradesh Jaipur School of Business JECRC University Jaipur Department of Computer Science and Engineering Bharati Vidyapeeth’s College of Engineering Delhi

ISBN: (数字)9798350384277

ISBN: (纸本)9798350384284

An increasing number of consumers are eager to invest in and benefit from the IoT. Research indicates that by 2020, there will be over 30 billion connected devices, and by 2024, the market for IoT systems is projected to reach $7.6 billion. This paper will focus on the ways in which internet of things (IoT) data could enhance customer relationship management (CRM). An empirical examination was conducted using research methods that utilised qualitative conversations with twelve CRM or innovation marketing experts in 2020 who actually had been engaged with retailer IoT projects. According to the results, companies can anticipate their client's actions and better meet their needs by analysing stored data. Furthermore, due to their lack of knowledge about programming and interaction options, the majority of organisations simply require the establishment of a conventional CRM system. This allows for the integration of data collected from particular IoT devices with data collected from other sources as well. When all of these moving parts are in sync, it's much easier to understand what the client preferences, requirements, and the products or services they're planning to buy.

关键词： Technological innovation Quantum computing Reviews Customer relationship management Psychology Programming Internet of Things

来源：评论

学校读者我要写书评

暂无评论

An Adaptive-Gain Recurrent Neural Network for Solving the Joint-Angle Drift Issues of Redundant Manipulators

An Adaptive-Gain Recurrent Neural Network for Solving the Jo...

引用

Complex systems and Intelligent science (CSIS-IAC), International Annual Conference on

作者： Boyu Zheng Chunquan Li Zhijun Zhang Junzhi Yu P. X. Liu School of Information Engineering Nanchang University Nanchang China School of Automation Science and Engineering South China University of Technology Guangzhou China College of Engineering Peking University Beijing China Department of Systems and Computer Engineering Carleton University Ottawa ON Canada

This paper proposes a new adaptive-gain recurrent neural network (AG-RNN) to effectively cope with the joint-angle drift issues in redundant manipulators. Specifically, a joint-angle drift-free with the feedback control of the velocity layer motion equation (JADF-FC) is proposed via an optimization criterion for synchronously optimizing linear terms and quadratic. Then, the JADF-FC is reasonably formulated into a standard quadratic programming (QP) issue. Different from the previous recurrent neural networks (RNNs), the AG-RNN proposed in this paper constructs an error-based differential equation with a new adaptive-gain. It should be noted that the proposed adaptive-gain does not gradually approach infinity as time increases, which is more in line with actual hardware implementation requirements than the existing time-variant-gain. The adaptive-gain can reduce the joint-angle drift errors of the redundant manipulator. Therefore, the proposed AG-RNN can solve the QP problem of the manipulator more effectively and quickly. To validate the performance of the proposed AG-RNN, it is compared with representative RNNs. The experimental results indicate that smaller joint-angle drift errors can be get by the proposed AG-RNN solving JADF-FC scheme than the other solutions when solving the joint-angle drift issues.

关键词：

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：