检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Moniri, Behrad Lee, Donghwan Hassani, Hamed Dobriban, Edgar Department of Electrical and Systems Engineering University of Pennsylvania PA United States Graduate Group in Applied Mathematics and Computational Science University of Pennsylvania PA United States Department of Statistics and Data Science University of Pennsylvania PA United States

Feature learning is thought to be one of the fundamental reasons for the success of deep neural networks. It is rigorously known that in two-layer fully-connected neural networks under certain conditions, one step of gradient descent on the first layer can lead to feature learning;characterized by the appearance of a separated rank-one component-spike-in the spectrum of the feature matrix. However, with a constant gradient descent step size, this spike only carries information from the linear component of the target function and therefore learning non-linear components is impossible. We show that with a learning rate that grows with the sample size, such training in fact introduces multiple rank-one components, each corresponding to a specific polynomial feature. We further prove that the limiting large-dimensional and large sample training and test errors of the updated neural networks are fully characterized by these spikes. By precisely analyzing the improvement in the training and test errors, we demonstrate that these non-linear features can enhance learning. Copyright 2024 by the author(s)

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Renewable Energy Assessment: A Comparative Study of Saudi Arabia and Greensboro-NC 6

Renewable Energy Assessment: A Comparative Study of Saudi Ar...

引用

6th International Symposium on Advanced Electrical and Communication Technologies, ISAECT 2024

作者： Darwish, Hiba Alhuwaidi, Sadiq Alhmoud, Issa W. Alsumady, Mohammed Gokaraju, Balakrishna North Carolina Agricultural and Technical State University Computational Data Science and Engineering Greensboro United States Prince Mohammad Bin Fahd University Department of Electrical Engineering Al-Khobar Saudi Arabia Yarmouk University Department of Electronics Engineering Irbid Jordan

ISBN: (纸本)9798331529987

This paper comprehensively assesses wind and solar energy potential in the Kingdom of Saudi Arabia (KSA), focusing on five strategically selected locations: Al-Ahsa, Riyadh, Rafha, Tabuk, and Unayzah. The analysis was extended, and a comparison was made between the results of the investigated locations in KSA and the city of Greensboro North Carolina State in USA. The study aims to estimate the amount of energy that can be extracted from wind and solar resources, leveraging advance d computational tools for precise evaluation. The "Distribution Fitter"app in MATLAB was utilized to fit the parameters of the used probability density functions PDFs. In parallel, the RETScreen software was utilized to estimate the annual extractable energy from solar photovoltaic (PV) systems, offering a reliable simulation of solar irradiance and system performance. Greensboro stands out as the most promising site for wind energy extraction with an annual amount of 21,022.02 MWh by 10 Vestas turbines, while Al-Ahsa demonstrates the highest potential for solar energy harvesting with an annual estimated amount of 257.426 MWh by a 100 kW PV system. This dual-resource assessment highlights the regional variability in renewable energy potential across KSA, emphasizing the importance of site-specific analysis for optimal energy resource utilization. The results serve as a valuable reference for policymakers and stakeholders in the renewable energy sector, guiding future investments and development plans toward sustainable energy solutions in the region. © 2024 IEEE.

关键词： Clean energy

来源：评论

学校读者我要写书评

暂无评论

Guardian of the Ensembles: Introducing Pairwise Adversarially Robust Loss for Resisting Adversarial Attacks in DNN Ensembles

Guardian of the Ensembles: Introducing Pairwise Adversariall...

引用

2025 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2025

作者： Shukla, Shubhi Dalui, Subhadeep Alam, Manaar Datta, Shubhajit Mondal, Arijit Mukhopadhyay, Debdeep Chakrabarti, Partha Pratim Centre for Computational and Data Sciences Iit Kharagpur India Iit Kharagpur Computer Science and Engineering Department India Center for Cyber Security New York University Abu Dhabi United Arab Emirates Iit Kharagpur Department of Artificial Intelligence India Iit Patna Computer Science and Engineering Department India

ISBN: (纸本)9798331510831

Adversarial attacks rely on transferability, where an adversarial example (AE) crafted on a surrogate classifier tends to mislead a target classifier. Recent ensemble methods demonstrate that AEs are less likely to mislead multiple classifiers in an ensemble. This paper proposes a new ensemble training using a Pairwise Adversarially Robust Loss (PARL) that by construction produces an ensemble of classifiers with diverse decision boundaries. PARL utilizes outputs and gradients of each layer with respect to network parameters in every classifier within the ensemble simultaneously. PARL is demonstrated to achieve higher robustness against black-box transfer attacks than previous ensemble methods as well as adversarial training without adversely affecting clean example accuracy. Extensive experiments using standard Resnet20, WideResnet28-10 classifiers demonstrate the robustness of PARL against state-of-the-art adversarial attacks. While maintaining similar clean accuracy and lesser training time, the proposed architecture has a 24.8% increase in robust accuracy (= 0.07) from the state-of-the art method. Code is available at: https://***/shubhishukla10/PARL © 2025 IEEE.

关键词： adversarial attack decision-boundary diversity defense ensemble models

来源：评论

学校读者我要写书评

暂无评论

Autonomous Robot Navigation in Unknown Terrains using Generative Adversarial Networks 4

Autonomous Robot Navigation in Unknown Terrains using Genera...

引用

4th International Conference on Soft Computing for Security Applications, ICSCSA 2024

作者： Chitra, P. Sridar, K. Govindan, Sudha Britto Raj, S. Akshya, J. Choudhry, Mani Deepak Sundarrajan, M. St Joseph's Institute of Technology Department of Artificial Intelligence and Data Science Chennai India Veerammal Engineering College Department of Computer Science and Engineering Dindigul India Sona College of Technology Department of Computer Science and Engineering Salem India RRASE College of Engineering Department of Computer Science and Engineering Chennai India SRM Institute of Science and Technology Department of Computational Intelligence Chennai India SRM Institute of Science and Technology Department of Computing Technologies Chennai India SRM Institute of Science and Technology Department of Networking and Communications Chennai India

ISBN: (纸本)9798331515720

Autonomous Robot Navigation in unknown and dynamic environments is considered one of the grand challenges in robotics. These motions that guide it span from rescue operations to planetary exploration. Classical methods for path planning, including A*, Dijkstra, and RRT, were unable to balance the efficiency and adaptability of motion planning over complex terrain. This may have a powerful solution using Generative Adversarial Networks (GANs) with advanced machine learning techniques to improve the ability of robotic navigation. This study proposes a GAN-based approach for designing an effective self-adaptive path planning and obstacle avoidance system for autonomous robots. Despite performing well in structured environments, traditional techniques normally fail in analysing the unstructured terrains with real-time adjustments and dynamic changes due to the high computational costs and lack of flexibility involved. In this regard, the proposed GAN-based system resolves these issues by rating navigation paths concerning safety and efficiency. Quantitative analysis demonstrates that within a forest, desert, urban, or off-road environment, the computational times by using the developed strategy turn out to be 0.12 seconds, 0.10 seconds, 0.14 seconds, and 0.13 seconds, respectively, behaving much lower than what can be achieved with other algorithms. This approach proves much superior in terms of computational efficiency path smoothness and adaptability under different environmental conditions in applications related to autonomous robot navigation systems. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Leveraging Instruction-based Learning for Effective UAV Traffic Management in Dynamic Environment

Leveraging Instruction-based Learning for Effective UAV Traf...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Ramya, R.S. Daniel, Keren Lois Rajkumar, S. Madhavan, Sruthi S. Akshya, J. Choudhry, Mani Deepak Sri Ramakrishna Engineering College Department of Computer Science and Engineering Coimbatore India KGiSL Institute of Technology Department of Computer Science and Business Systems Coimbatore India Sona College of Technology Department of Information Technology Salem India Nehru Institute of Engineering and Technology Department of Artificial Intelligence and Data Science Coimbatore India Srm Institute of Science and Technology Department of Computational Intelligence Chennai India Srm Institute of Science and Technology Department of Computing Technologies Chennai India

ISBN: (纸本)9798331509828

With the popularization of UAVs (Unmanned Aerial Vehicles) in surveillance, delivery services, environmental monitoring, and increasingly other operational aspects, besides the need to take off and land, efficient traffic management becomes integral for assuring and securing further development and exploitation. Most of the existing traffic management systems for UAVs depend on traditional rule-based algorithms or simpler machine learning techniques, such as DQN or PPO. However, these systems also have enormous challenges: dynamic environments, high-density traffic, and robust decision-making over unpredictable weather and network conditions. In addition, the above traditional models usually experience difficulties in balancing exploration and exploitation, leading to suboptimal routing and enlarged collision risks in complicated urban airspaces. These challenges have driven us to develop a new proposal: a UA V traffic management framework based on Double Deep Q-Network (DDQN) combined with Instruction-Based Learning. In this approach, advanced learning for DDQN optimizes processes at decision-making points for UAVs. The model proposed herein, along with comprehensive simulations and quantitative analyses, demonstrated higher performance in terms of leadership and cumulative rewards while keeping lower training loss compared to the classical algorithms such as DQN, A3C, and PPO. At the same time, the DDQN model presented a better success rate (95%), as also reflected in the balanced precision-recall curve showing an area under the curve of 0.90, over others in the on-point prediction of UAVstate and safety margin of collision. Our experimental results demonstrate that the proposed DDQN-based framework significantly enhances UA V traffic management by optimizing energy consumption in complex airspaces and reducing the risk of collision. © 2025 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Coordination of Autonomous Vehicles for Smart Logistics in Industrial Environments 13

Multi-Agent Coordination of Autonomous Vehicles for Smart Lo...

引用

13th International Conference on System Modeling and Advancement in Research Trends, SMART 2024

作者： Kirubhakaran Karthikeswaran, D. Arun, M. Chakravarthy, R. Arun Akshya, J. Sundarrajan, M. Choudhry, Mani Deepak Surya Engineering College Department of Computer Science and Engineering Erode India Nehru Institute of Engineering and Technology Department of Artificial Intelligence and Data Science Coimbatore India KGiSL Institute of Technology Department of Electronics and Communication Engineering Coimbatore India Srm Institute of Science and Technology Department of Computational Intelligence Chennai India Srm Institute of Science and Technology Department of Networking and Communications Chennai India Srm Institute of Science and Technology Department of Computing Technologies Chennai India

ISBN: (纸本)9798350380583

Dynamic effects in industrial logistics demand more creative solutions towards the pursuit of efficiency and agility in evolving environments. Though static path-planning and taskallocation algorithms have provided the basis for how autonomous vehicles are guided within structured environments, those approaches usually fail to contend with indeterminacy outside of their modelled world, where there is dynamic obstacle appearance and changing task requirements, thus raising inefficiencies and costs of operations. To address these issues, the paper introduces a new multi-agent coordination system that uses a hybrid A∗ algorithm, integrating path planning with sophisticated detection methods for dynamic obstacles and improving superior task allocation. The system is supposed to provide improvements in real-time coordination in industries of autonomous vehicles to achieve efficient management of tasks and paths in changing environments. We integrate the latest in machine learning techniques for improved and real-time updates within the changes of the vehicle routing process based on both immediate sensory input and environmental interactions. Simulations show that our system performs the task much faster than classic systems: up to 30% improvement in completing tasks compared with classic models, and an average improvement of 25% in allround energy efficiency. It intelligently integrates machine learning techniques with real-time data processing. With the ability to scale up or down, or to adapt itself, this system addresses the chief challenges existing methods face and could revolutionize logistics operations within any industry. © 2024 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Explainable Convolutional Neural Network for Phenotype Prediction from Genotype

Explainable Convolutional Neural Network for Phenotype Predi...

引用

2024 IEEE International Conference on E-Health Networking, Application and Services, HealthCom 2024

作者： Sam, Maxwell Annan, Richard Yang, Pei Anwar, Mohd Rhinhardt, Kristen Qingge, Letu Department of Computer Science North Carolina A&T State University GreensboroNC United States Department of Computer Science Qinghai University Xining China Department of Computational Data Science and Engineering North Carolina A&T State University GreensboroNC United States

ISBN: (纸本)9798350350548

In the realm of precision medicine, the prediction of phenotypic traits from genotype data plays a pivotal role in understanding disease susceptibility, drug response, and overall health outcomes. Machine learning models trained on genotype data offer promising avenues for phenotype prediction. However, the black-box nature of these models often hinders interpretability, raising concerns about their reliability and trustworthiness in clinical decision-making. This paper explores the application of SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) on our existing CNN model to identify important features from genotype that contribute to phenotype prediction in yeast data. Both techniques on machine learning models include improving model transparency and interpretability by providing insights into prediction mechanisms. LIME focuses on local interpretability, explaining individual predictions tailored to specific instances swiftly, while SHAP computes feature importance using Shapley values, offering a comprehensive understanding of feature contributions. Our dataset contains 4,390 samples, each with 28,220 features in genotype which are used in the training, testing and validation of our existing CNN model. In our analysis of 20 phenotypes, we identify the number of relevant important features using SHAP, LIME methods, and the intersection which not only improves the Mean Squared Error (MSE) values compared to using all the features in the genotype data, but also the model training time. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Generalising Violence Detection with a New Near-Real-World Violence dataset 3

Generalising Violence Detection with a New Near-Real-World V...

引用

3rd International Conference on Advancement in Electrical and Electronic engineering, ICAEEE 2024

作者： Haque, Mahmudul Nyeem, Hussain Ovi, Tareque Bashar Nahid, Al Molla, Md. Sabbir Hossain Tuhin, Md. Tanjim Mahmud Shahab, Fardin Alam, Ayat Subah Alam, Saadia Binte Mirpur Cantonment Dhaka1216 Bangladesh Independent University Department of Computer Science and Engineering Dhaka1229 Bangladesh Independent University Bangladesh Center for Computational & Data Sciences Dhaka1229 Bangladesh

ISBN: (纸本)9798350388282

Detecting and classifying violence is crucial for public safety and addressing societal violence. DL models have greatly improved the automation of violence detection systems by effectively capturing intricate visual patterns. However, the quality and diversity of the training data greatly impact the effectiveness of these models. Existing datasets may be biased towards specific situations, limiting their practical use. To address this limitation, we introduce the Movie Clip (MC) dataset to enhance the generalisability of Automated Violence Detection and Classification (AVDC) systems. The MC dataset encompasses a broad spectrum of near-real-world violent actions, incorporating diverse demographics, environmental circumstances, and cultural elements extracted from movies. Consequently, it accurately reflects the complexity and diversity of real-world violent scenarios. The potential of the new dataset is investigated against its existing counterparts, like Hockey Fight (HF) and AIRTLab datasets. These datasets are used to train the ConvLSTM models based on the VGG16 and VGG19 architectures. The proposed dataset significantly improves AVDC model generalisation, outperforming the generalisability of current datasets, thereby advancing violence detection and facilitating the development of more robust and efficient AVDC systems. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Fast and scalable finite-element based approach for density functional theory calculations using projector augmented wave method

引用

Physical Review B 2025年第3期111卷 035101-035101页

作者： Kartick Ramakrishnan Sambit Das Phani Motamarri Department of Computational and Data Sciences Indian Institute of Science Bengaluru India Department of Mechanical Engineering University of Michigan Ann Arbor Michigan 48109 USA

In this paper, we present a computationally efficient methodology that utilizes a local real-space formulation of the projector augmented wave (PAW) method discretized with a finite-element (FE) basis to enable accurate and large-scale electronic structure calculations. This real-space approach for DFT calculations combines the efficiency of PAW formalism involving smooth electronic fields with the ability of systematically improvable higher-order finite-element basis to achieve significant computational gains. In particular, we developed efficient strategies for solving the underlying FE discretized PAW generalized eigenproblem by employing the Chebyshev filtered subspace iteration approach to compute the desired eigenspace in each self-consistent field iteration. These strategies leverage the low-rank perturbation of the FE basis overlap matrix in conjunction with reduced order quadrature rules to invert the discretized PAW overlap matrix while also exploiting the sparsity of both the local and nonlocal parts of the discretized PAW Hamiltonian and overlap matrices. Further, we employ higher-order quadrature rules to accurately evaluate integrals in these matrices involving PAW-atomic data, allowing the use of coarser FE meshes for various electronic fields. Using the proposed approach, we benchmark the accuracy and performance of various representative examples involving periodic and nonperiodic systems with plane-wave-based PAW implementations. Furthermore, we also demonstrate a considerable computational advantage (∼5×−10×) over state-of-the-art plane-wave methods for medium to large-scale systems (∼6000−35000 electrons). Finally, we show that our approach (PAW-FE) significantly reduces the degrees of freedom to achieve the desired accuracy, thereby enabling large-scale DFT simulations (>50000 electrons) at an order of magnitude lower computational cost compared to norm-conserving pseudopotential calculations using finite-element discretization.

关键词： Hamiltonians

来源：评论

学校读者我要写书评

暂无评论

Predictive Analysis of Consumer Behavior Using Supervised Learning Techniques 2

Predictive Analysis of Consumer Behavior Using Supervised Le...

引用

2nd International Conference computational and Characterization Techniques in engineering and sciences, IC3TES 2024

作者： Rekha, K. Sashi Amutha, T. Usharani, R. Pushparani, S. Sivagami, V.M. Saveetha Institute of Medical and Technical Sciences Simats Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India Care College of Engineering Department of Artificial Intelligence & Data Science Tamil Nadu Trichy India Srm Institute of Science and Technology Faculty of Engineering and Technology Department of Computational Intelligence School of Computing Chennai India Meenakshi College of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India Sri Venkateswara College of Engineering Department of Information Technology Tamil Nadu Chennai India

ISBN: (纸本)9798350364699

The study presented here consists of an entire framework for prediction of consumers behavior through the machine training of supervised learning methods. The strategy involves the following: data collection, preprocessing, exploration, feature selection, model selection, training, evaluation, interpretation and deployment. The systematic process is tailored to clear the pathway for combining data about customer taste, sophisticated habits, and purchasing trends. Primary components include data preprocessing, training of machine learning models, feature selection, and ethical issues regarding data privacy and transparency. The outcomes of the implementation are a high accuracy in consumers clustering, efficient classification of customers' behavior, as well as unveiling a bunch of crucial predictors that affect the customers mood and behavior. As a result, the report stresses the necessity of integrated monitoring and redirection strategies to realize the potential of the created models. The idea of predictive analysis as an evolving tool that enables marketers to tailor their campaigns more closely, and improve the overall customer experience therefore also receives attention. The proposed system methodology constitutes a solid process framework for business defined to aim at using predictive analytics to gain competitive edge in the current dynamic marketplace. © 2024 IEEE.

关键词： Self-supervised learning

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：