检索结果-内蒙古大学图书馆

12th International Conference on Learning Representations, ICLR 2024

作者： Kesen, Ilker Pedrotti, Andrea Dogan, Mustafa Cafagna, Michele Acikgoz, Emre Can Parcalabescu, Letitia Calixto, Iacer Frank, Anette Gatt, Albert Erdem, Aykut Erdem, Erkut Koç University KUIS AI Center Turkey Koç University Department of Computer Engineering Turkey University of Pisa Department of Computer Science Italy Institute of Information Science and Technologies Italian National Council of Research Italy Hacettepe University Department of Computer Engineering Turkey Aselsan Research Turkey University of Malta Institute of Linguistics and Language Technology Malta Heidelberg University Department of Computational Linguistics Germany Amsterdam UMC University of Amsterdam Department of Medical Informatics Netherlands Amsterdam Public Health Methodology & Mental Health Amsterdam Netherlands Utrecht University Department of Information and Computing Sciences Netherlands

With the ever-increasing popularity of pretrained Video-Language Models (VidLMs), there is a pressing need to develop robust evaluation methodologies that delve deeper into their visio-linguistic capabilities. To address this challenge, we present VILMA), a task-agnostic benchmark that places the assessment of fine-grained capabilities of these models on a firm footing. Task-based evaluations, while valuable, fail to capture the complexities and specific temporal aspects of moving images that VidLMs need to process. Through carefully curated counterfactuals, VILMA offers a controlled evaluation suite that sheds light on the true potential of these models, as well as their performance gaps compared to human-level understanding. VILMA also includes proficiency tests, which assess basic capabilities deemed essential to solving the main counterfactual tests. We show that current VidLMs' grounding abilities are no better than those of vision-language models which use static images. This is especially striking once the performance on proficiency tests is factored in. Our benchmark serves as a catalyst for future research on VidLMs, helping to highlight areas that still need to be explored. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： computational linguistics

来源：评论

学校读者我要写书评

暂无评论

An Effective Two-Stage Column Generation Strategy for Solving Unit Commitment

An Effective Two-Stage Column Generation Strategy for Solvin...

引用

IEEE Conference on Energy Internet and Energy System Integration (EI2)

作者： Zhao-Gang Su Sheng-Jie Chen Yu-Fei Li Liang Chen Jia-Yi Deng Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China Institute of Applied Mathematics Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China College of Sciences Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9798331523527

ISBN: (纸本)9798331523534

Unit commitment (UC) has been extensively studied in power systems literature and is typically formulated as a mixed-integer programming (MIP) problem. However, existing methods and commercial MIP solvers often struggle to efficiently solve large-scale UC instances. This paper proposes a novel MIP model for addressing UC by employing an innovative column generation-based two-stage approach to efficiently compute high-quality solutions. Our method leverages parallel computing to solve pricing problems and generate columns effectively. Following column generation, we solve the master problem as a MIP model to obtain high-quality feasible solutions for the UC problem. Comprehensive numerical experiments demonstrate that our proposed method can effectively tackle large-scale UC problems involving over 1,000 units, significantly outperforming state-of-the-art MIP solvers in both solution quality and computational efficiency. The results underscore the potential of our approach for practical application in large-scale power system scheduling.

关键词： Processor scheduling computational modeling Refining Pricing System integration Parallel processing Programming computational efficiency Power system reliability Reliability

来源：评论

学校读者我要写书评

暂无评论

AI-Driven CASGN Framework for Evaluating Descriptive Answers in Online Education

AI-Driven CASGN Framework for Evaluating Descriptive Answers...

引用

Innovative computing, Intelligent Communication and Smart Electrical Systems (ICSES), International Conference on

作者： Sridevi Ponmalar. P Vinodini S V. Srithar Gouri Morankar S D Sundarsingh Jebaseelan Harikrishnan. R Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Chennai Faculty of Arts (English) Sathyabama Institute of Science and Technology Chennai Department of Computer Applications PeriyarManiammai Institute of Science & Technology Thanjavur Shri Ramdeobaba College of Engineering and Management Nagpur Department of EEE Sathyabama Institute of Science and Technology Chennai Symbiosis Institute of Technology Pune Campus Symbiosis International Deemed University Pune

ISBN: (数字)9798331543624

ISBN: (纸本)9798331543631

There is an enormous demand for automated assessment systems, which can handle the bulk assessments efficiently and effectively. While existing systems perform well in grading objective questions, they break down with subjective or descriptive answers that require a deeper analysis of context and understanding. To address this challenge, we have proposed the AI-Enhanced Context-Aware Semantic Grading Network-state-of-the-art algorithm for instant auto-descriptive response scoring in e-assessments. The AI-CASGN utilizes state-of-the-art AI technologies, particularly NLP and deep learning models-very specifically transformer architectures-during context-based semantic analysis. Beyond mere keyword matching, the system scores what students say and how relevant it is. This takes the concept of grading to an even more fine-tuned art. Scores change with depth and accuracy in the answer given to show complete evaluation. With the dynamic grading framework, adaptation on scores both regarding the accuracy and depth of the answer for a precise evaluation is possible. Inbuilt adaptive learning within the system performance evolves day by day by learning from the new data. AI-CASGN is designed to handle biases in mitigation by considering that there may be different patterns for a response to ensure that responses with varied wording but conceptually correct are fairly graded. It will have to deal with the volumes at scale, hence it is envisaged to process large volumes of responses in minimum time and with high accuracy to be deployed in real time in any educational institution. In future, the system will also provide personalized feedback to students for the purpose of continuous learning and improvement. This represents a scalable, real-time, unbiased tool that assesses subjective answers in modern online learning environments.

关键词： Deep learning Adaptive learning Accuracy System performance Prevention and mitigation Semantics Transformers Real-time systems Natural language processing Context modeling

来源：评论

学校读者我要写书评

暂无评论

Automation Intervention for Monitoring Agriculture Farming Scale: A Review 14

Automation Intervention for Monitoring Agriculture Farming S...

引用

14th International Conference on computing Communication and Networking Technologies, ICCCNT 2023

作者： Joshi, Kapil Kumar, Santosh Bhatla, Shruti Kaushik, Vishal Anandaram, Harishchander Kumar, Anil Uttaranchal University Department of Cse Uttaranchal Institute of Technology Dehradun India Sharda University Department of Mathematics Sharda School of Basic Sciences and Research UP Greater Noida India Graphic Era Hill University Department of Computer Science and Engineering Uttarakhand Dehradun India Upes School of Computer Science Dehradun India Amrita Vishwa Vidyapeetham Centre for Computational Engineering and Networking Tamil Nadu Coimbatore India Dit University School of Computing Dehradun India

ISBN: (纸本)9798350335095

Agricultural data is only valuable when it has been managed successfully. As data has evolved into the fundamental ingredient in contemporary agriculture to assist farmers with vital decision, latest developments in managing data are causing Smart Agriculture to rise dramatically. With factual information obtained by sensors, significant advantages emerge with the goal of enhancing production and ecology. This type of data-driven farm management is built on information that can boost efficiency by preventing resource waste and contamination of the ecosystem. Data-driven farming, with the assistance of automated solutions using artificial intelligence techniques, lays the groundwork for potential sustainable *** article analyses the current state of sophisticated agricultural systems by rehashing each critical step, from data processing in field crops to variable interest rate implementations, so that farmers can make optimised decision making to save funds while safeguarding the natural environment and converting how meal would be generated to meet the upcoming population explosion. © 2023 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Subspace method based on neural networks for eigenvalue problems

arXiv

引用

arXiv 2024年

作者： Dai, Xiaoying Fan, Yunying Sheng, Zhiqiang LSEC Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China School of Mathematical Sciences University of Chinese Academy of Sciences Beijing100049 China National Key Laboratory of Computational Physics Institute of Applied Physics and Computational Mathematics Beijing100088 China HEDPS Center for Applied Physics and Technology College of Engineering Peking University Beijing100871 China

With the rapid development of machine learning, numerical discretization methods based on deep neural networks have been widely used in many fields, especially in solving high-dimensional problems where traditional methods face bottlenecks. However, for low-dimensional problems, existing machine learning methods are not as accurate and efficient as traditional methods. In this paper, we propose a subspace method based on neural networks for eigenvalue problems with high accuracy and low cost. Our basic idea is to use neural network based basis functions to span a subspace, then calculate the parameters of the neural network based basis functions through appropriate training, and finally calculate the Galerkin projection of the eigenvalue problem onto the subspace and obtain an approximate solution. In addition, we reduce the dimension of the subspace by applying some dimensionality reduction technique, which can improve the accuracy of the approximate solution in further. Numerical experiments show that we can obtain approximate eigenvalues with accuracy of 10−11 but with less then 400 epochs, which is significantly superior to other existing neural network based *** Codes 65N25, 65L15, 68T07 Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Convolutional Neural Network Framework for Brain Tumor Classification using MRI Images 2

Deep Convolutional Neural Network Framework for Brain Tumor ...

引用

2nd International Conference on Automation, computing and Renewable Systems, ICACRS 2023

作者： Sakthi, U. Thangaraj, K. Tamizhselvi, A. Kirubakaran, M.K. Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur Chengalpattu TN Chennai603203 India Department of Information Technology Sona College of Technology Junction Main Road TN Salem636005 India Department of Information Technology St. Joseph's College of Engineering TN Chennai600119 India Department of Artificial Intelligence and Data Science St. Joseph's Institute of Technology TN Chennai600119 India

ISBN: (纸本)9798350340235

Brain cancer is one of the high-risk diseases and increases the death rate in all countries, affecting both men and women. The early diagnosis and severity of brain cancer leads to better medical treatment and save people's lives. The machine learning procedure has been applied for early detection and treatment of brain cancer in the biomedical field by classifying them into low-risk and high-risk groups. In cancer research, the predictive and classification model has been developed using Deep Convolutional Neural Network (DCNN) algorithms for accurate decision making. The Magnetic Resonance Image (MRI) classification technique DCNN is advanced to detect and match feature points of training and test images. The DCNN classifier based on the outcome of feature points then classifies images. The key notion of this proposed research effort is to implement and execute the proposed DCNN algorithm on cancer patient datasets for risk level classification. The brain cancer affected patient details are collected from UCI machine learning data repository for experimental analysis. In this research study, the DCNN algorithm is proposed and it gives better accuracy and faster than the KNN, CNN and SVM. © 2023 IEEE.

关键词： Brain Cancer Convolutional Neural Convolutional Network Deep Learning Medical Resonance Image Classification

来源：评论

学校读者我要写书评

暂无评论

Efficient Global Algorithms for Transmit Beamforming Design in ISAC Systems

arXiv

引用

arXiv 2024年

作者： Wu, Jiageng Wang, Zhiguo Liu, Ya-Feng Liu, Fan The School of Mathematics Jilin University Changchun130012 China The College of Mathematics Sichuan University Sichuan Chengdu610064 China The State Key Laboratory of Scientific and Engineering Computing Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China The Department of Electrical and Electronic Engineering Southern University of Science and Technology Shenzhen518055 China

In this paper, we propose a multi-input multi-output transmit beamforming optimization model for joint radar sensing and multi-user communications, where the design of the beamformers is formulated as an optimization problem whose objective is a weighted combination of the sum rate and the Cramér-Rao bound, subject to the transmit power budget. Obtaining the global solution for the formulated nonconvex problem is a challenging task, since the sum-rate maximization problem itself (even without considering the sensing metric) is known to be NP-hard. The main contributions of this paper are threefold. Firstly, we derive an optimal closed-form solution to the formulated problem in the single-user case and the multi-user case where the channel vectors of different users are orthogonal. Secondly, for the general multi-user case, we propose a novel branch and bound (B&B) algorithm based on the McCormick envelope relaxation. The proposed algorithm is guaranteed to find the globally optimal solution to the formulated problem. Thirdly, we design a graph neural network (GNN) based pruning policy to determine irrelevant nodes that can be directly pruned in the proposed B&B algorithm, thereby significantly reducing the number of unnecessary enumerations therein and improving its computational efficiency. Simulation results show the efficiency of the proposed vanilla and GNN-based accelerated B&B algorithms. Copyright © 2024, The Authors. All rights reserved.

关键词： computational efficiency

来源：评论

学校读者我要写书评

暂无评论

QoS-based Beamforming and Compression Design for Cooperative Cellular Networks via Lagrangian Duality

arXiv

引用

arXiv 2023年

作者： Fan, Xilai Liu, Ya-Feng Liu, Liang Chang, Tsung-Hui State Key Laboratory of Scientific and Engineering Computing Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China Department of Electronic and Information Engineering The Hong Kong Polytechnic University Hong Kong School of Science and Engineering The Chinese University of Hong Kong Shenzhen Research Institute of Big Data Shenzhen Shenzhen China

This paper considers the quality-of-service (QoS)based joint beamforming and compression design problem in the downlink cooperative cellular network, where multiple relay-like base stations (BSs), connected to the central processor via rate-limited fronthaul links, cooperatively transmit messages to the users. The problem of interest is formulated as the minimization of the total transmit power of the BSs, subject to all users’ signal-to-interference-plus-noise ratio (SINR) constraints and all BSs’ fronthaul rate constraints. In this paper, we first show that there is no duality gap between the considered joint optimization problem and its Lagrangian dual by showing the tightness of its semidefinite relaxation (SDR). Then, we propose an efficient algorithm based on the above duality result for solving the considered problem. The proposed algorithm judiciously exploits the special structure of an enhanced Karush-Kuhn-Tucker (KKT) conditions of the considered problem and finds the solution that satisfies the enhanced KKT conditions via two fixed point iterations. Two key features of the proposed algorithm are: (1) it is able to detect whether the considered problem is feasible or not and find its globally optimal solution when it is feasible;(2) it is highly efficient because both of the fixed point iterations in the proposed algorithm are linearly convergent and evaluating the functions in the fixed point iterations are computationally cheap. Numerical results show the global optimality and efficiency of the proposed algorithm. Copyright © 2023, The Authors. All rights reserved.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Detection of Military Vehicles based on Edge Devices from Unmanned Aerial Vehicle

Detection of Military Vehicles based on Edge Devices from Un...

引用

Distributed computing and Optimization Techniques (ICDCOT), International Conference on

作者： L Umasankar Anitha D S Trisheela Hassan M. Al-Jawahry Subba Reddy Borra Electrical and Electronics Engineering S.A.Engineering College Poonamallee Tiruvallur India Department of Computational Intelligence School of computing SRM Institute of Science and Technology Kattankulathur Tamilnadu India Dept of CSE Nitte Meenakshi Institute of Technology Bengaluru India The Islamic university Najaf Iraq Computer Science And Engineering Malla Reddy Engineering College for Women (Ugc-Autonomous) Maisammaguda Hyderabad India

The recent technology in surveillance for military vehicle parts forms the basis of intelligence warfare through information realized through monitoring and tracking operations in complex situations. Therefore, the process of identifying and classifying vehicles by an aerial vehicle installed with a resource-limited device and an intelligent object detection algorithm significantly assists security agencies. It is possible to make use of this vehicle either manually or autonomously. To overcome these issues, edge device based military vehicle detection from Unmanned Aerial Vehicle (UAV) is proposed. At present, no publicly available dataset exists that includes different military classes. Therefore, the proposed approach use a dataset consisting of 6772 images labeled as Tanks, Military Trucks, Helicopters, Aircraft, Civilian Cars and Civilian Aircraft. This data set is used to train deep learning models such as Quantized SSD Mobilenetv2 and Tiny Yolo v5 that are then compared with resource limited edge devices. The results reveal that Tiny Yolo v5 outperforms other models, showing high efficiency and suitability for edge-based devices due to its lightweight design.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Secure E-Voting System using Deep Learning Techniques

Secure E-Voting System using Deep Learning Techniques

引用

International Conference on Innovative Sustainable computational Technologies (CISCT)

作者： Kanchana M Gopirajan P. V Kaladevi Ramar Shanmugasundaram Hariharan Department of Computing Technologies School of Computing SRM Institute of Science and Technology Tamil Nadu India Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Chennai India Department of Computer Science and Engineering Saveetha Engineering College (Autonomous) Chennai India Department of Computer Science and Engineering Vardhaman College of Engineering Hyderabad India

ISBN: (纸本)9781665474177

Democracy is vital in many emerging economies because it places power in control of the general public, who choose government via the electoral procedure. Elections rely heavily on polling places and people. Numerous changes have happened in electoral processes since the year of the republic till now. Subsequently, Ballot sheets were implemented as a voting medium, but this was later replaced by electronic voting machines, in which voters must select from a list of buttons, each symbolizing a symbol. This paper proposes techniques for ensuring voter identification and privacy through fingerprint scanners and other biometric identification techniques-based machine learning algorithms. As a result, we offered a new approach to speed up the voting process and eliminate similar issues. For face identification, we employed Convolutional Neural Network (CNN) architectures such as Alex Net, Visual Geometry Group (VGG-16), and Random Forest Algorithms in this study. The accuracy provided by Alex Net, VGG-16, and Random Forest (R.F.) Algorithms was 94.16%, 98.45%, and 92%, respectively. VGG-16 architecture outperformed all other algorithms with a 98.45% accuracy. We utilized an ATmega328-based Arduino for finger detection.

关键词： Visualization Machine learning algorithms Symbols Computer architecture Fingerprint recognition Security Convolutional neural networks

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：