检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Statkevich, Ekaterina Bondar, Sofiya Dvinskikh, Darina Gasnikov, Alexander Lobanov, Aleksandr Moscow Institute of Physics and Technology Department of Applied Mathematics and Computer Science Institutsky lane 9 Dolgoprudny141701 Russia HSE University Myasnitskaya st. 20 Moscow101000 Russia Skolkovo Institute of Science and Technology Bolshoy Boulevard 30 p.1 Moscow121205 Russia ISP RAS Research Center for Trusted Artificial Intelligence Alexander Solzhenitsyn st. 25 Moscow109004 Russia

This paper focuses on solving a stochastic saddle point problem (SPP) under an overparameterized regime for the case, when the gradient computation is impractical. As an intermediate step, we generalize Same-sample Stochastic Extra-gradient algorithm Gorbunov, Berard, Gidel and Loizou (2022) to a biased oracle and estimate novel convergence rates. As the result of the paper we introduce an algorithm, which uses gradient approximation instead of a gradient oracle. We also conduct an analysis to find the maximum admissible level of adversarial noise and the optimal number of iterations at which our algorithm can guarantee achieving the desired accuracy. Copyright © 2024, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Exploiting Partial Observability and Optimized Simple State Representations in Deep Q-Learning

Exploiting Partial Observability and Optimized Simple State ...

引用

Frontiers of Information technology (FIT)

作者： Danyaal Mahmood Usama Arshad Raja Hashim Ali Zain Ul Abideen Muhammad Huzaifa Shah Talha Ali Khan Ali Zeeshan Ijaz Nisar Ali Abu Bakar Siddique Faculty of Computer Science & Engineering GIK Institute of Engg. Sciences & Technology Topi Pakistan Dept. of Technology & Software Engineering University of Europe for Applied Sciences Berlin Germany BCMaterials Basque Center for Materials Applications & Nanostructure Spain Faculty of Electronic Systems Engineering University of Regina Regina Canada

The advent of deep Q-learning has opened up new possibilities in training autonomous agents to perform intelligently in intricate settings. This research work examines the potential of deep Q-learning in the paradigmatic Snake game, which requires an agent to navigate a grid, ingest food items, and avoid collisions. We incorporated a partially observable game state, introducing a novel level of difficulty to the task. Our proposed approach utilizes a straightforward feed-forward neural network to estimate Q-values of potential actions, given the current state. The agent progressively learns to balance between exploration and exploitation, allowing it to navigate optimally in the game scenario. Most existing studies in deep Q-learning for the Snake game overlook the complexities posed by partial observability, focusing mainly on fully observable state representations. Furthermore, the majority of the investigations delve into the efficacy of complex neural network architectures, leaving a gap in the understanding of the performance of more simplistic feed-forward networks. Our study fills this gap by offering an in-depth exploration and analysis of deep Q-learning strategies, especially when applied to partially observable game states and simple neural networks. Simulations and results reveal that adopting simpler state representations can significantly boost the agent’s performance in the Snake game. A more detailed and intricate reward function is also observed to enhance the agent’s decision-making skills and overall proficiency in the game. These observations underscore the significance of optimizing state representations and reward functions for maximizing the performance of deep Q-learning agents in the Snake game.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Study on a Detection Method of Driving Scenes Using Driver’s Operation Data and In-Vehicle Camera Videos

Study on a Detection Method of Driving Scenes Using Driver’...

引用

On-Line Conference (ONCON), Industrial Electronics Society Annual

作者： Kohjiro Hashimoto Daichi Yanagihara Hiroshi Kuniyuki Kae Doki Yuki Funabora Shinji Doki Dept. Applied Information Engineering Suwa University of Science Chino City Japan Dept. Mechanical and Electrical Engineering Suwa University of Science Chino City Japan Dept. Electrical Engineering Aichi Institute of Technology Toyota City Japan Dept. Electrical Engineering and Computer Science Nagoya University Nagoya Japan

In this paper, a method to detect arbitrary driving scenes from actual driving behavior data is proposed. This is positioned as a necessary technology to evaluate a driver’s cognitive ability from actual driving behavior data. In order to evaluate a driver’s cognitive ability from actual driving behavior data, it is first necessary to be able to detect scenes in which cognitive ability can be evaluated. However, since there is no clear definition of the scenes in which cognitive ability can be evaluated. Therefore, this method detects arbitrary driving scenes defined by the *** method is a binary classifier generation method based on deep learning. However, a driving scene is considered to be composed of road information, appearing object information, and operation information, and each is expressed by four types of modalities: driving video, object label vector, grid feature, and operation data in this method. By adopting a deep learning model structure that incorporates the idea of stacking ensemble learning and training a binary classifier based on four types of modal information, a detector that detects the desired driving situation is generated. In this paper, the effectiveness of the proposed method through experiments is verified.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Personalized tourism recommendation algorithm integrating tag and emotional polarity analysis

Personalized tourism recommendation algorithm integrating ta...

引用

International Conference on Advanced Cloud and Big Data (CBD)

作者： Peng Yuan Qiuxia Chen Zhifeng Wang Jinfeng Yang School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan Liaoning China Institute of Applied Artificial Intelligence of the Guangdong-Hong Kong-Macao Greater Bay Area Shenzhen Polytechnic Shenzhen Guangdong China

ISBN: (纸本)9798350309720

The matrix factorization algorithm has achieved good results in the field of scenic spot recommendation, but there are still many problems. Most of the studies only refer to the user’ s score of the tourist attraction to represent the user ’s overall evaluation of the attraction, thus ignoring the correlation between the online review text information of the attraction and the attraction, which eventually leads to the low accuracy of the entire recommendation system. This paper proposes a personalized tourism recommendation algorithm that integrates scenic spot labels and sentiment polarity analysis. On the basis of constructing feature labels for various scenic spots, the sentiment polarity analysis of user comments is carried out through natural language text information processing, and implicit emotions are given to the labels contained in scenic spots. Secondly, it is introduced into the factor vector of matrix decomposition model algorithm, and finally the potential relationship between users and feature labels and scenic spots is deeply explored. Through the user ’s preference for emotional feature labels, the user ’s approximate rating value for attractions is predicted. Experiments show that compared with the user-based collaborative filtering scenic spot recommendation algorithm, the average absolute error (MAE) and root mean square error (RMSE) are reduced by 70.28 % and 65.23 % respectively. Compared with the tag-based collaborative filtering attraction recommendation algorithm, MAE and RMSE are reduced by 65.02 % and 63.93 %, respectively. Compared with the matrix factorization recommendation algorithm of scenic spot labels, MAE and RMSE are reduced by 34.02% and 29.93 % respectively. To sum up the performance of the algorithm is significantly higher than the existing attractions recommended algorithm can be more accurate to provide users with recommended options.

关键词： Correlation Collaborative filtering Natural languages Information processing Prediction algorithms Approximation algorithms Matrix decomposition

来源：评论

学校读者我要写书评

暂无评论

Low-cost Smart Glasses for People with Visual Impairments

Low-cost Smart Glasses for People with Visual Impairments

引用

Advances in Electronics, Communication, Computing and Intelligent Information Systems (ICAECIS), International Conference on

作者： Nayana B R Yogesh Raju N R Abhav S Velidi Dept. of Computer Science Engineering M S Ramaiah Univesrity of Applied Sciences Bangalore Karnataka India Dept. of Electrical and Electronics Engineering Sir M Visvesvaraya Institute of Technology Bangalore Karnataka India Dept. of Electronics and Commuincation Engineering National Institute of Technology Suratkal Karnataka India

An efficient visual aid is essential for visually impaired candidate. At the same instance it has to be simple, robust and cost effective. However, regardless of being expensive, it is challenging to incorporate high end artificial intelligence into a compact device to serve the purpose. This paper presents a prototype of low-cost smart glasses for visually impaired individuals. Also, a brief survey on the cost and features of the goggles available in the market are included. In this work a prototype is developed integrating Raspberry Pi module, camera, sensors and a goggles. The captured images are processed using object recognition models and its corresponding text is read aloud using google text to translator. Subsequently, a comparative analysis of object recognition model is explored and discussed. Essential experimental results are incorporated along with cost involved for the prototype development.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Channel Treatment for Internet Addiction with Puskesmas Application: Design Approach with Usability Heuristics

Channel Treatment for Internet Addiction with Puskesmas Appl...

引用

2021 International Conference Advancement in Data science, E-learning and Information Systems, ICADEIS 2021

作者： Lubis, Muharman Handayani, Dini Oktarina Adrian, Qadhli Jafar Gustiarani, Anastassya Madjid, Cheta Kusuma Nurhas, Irawan Telkom University Information System Department Bandung Indonesia Tailor University Innovation Technology Department Selangor Malaysia Universitas Teknokrat Indonesia Computer Engineering and Science Department Bandar Lampung Indonesia Institute of Positive Computing Hochschule Ruhr West University of Applied Science Mülheim Germany

ISBN: (纸本)9781665437097

Developed since 1968, Puskesmas is the most important healthcare facility and is at the forefront of providing basic healthcare services at the community level. Basically, its role is very important and should be one of the keys to Indonesia's success in improving the health and nutritional status of the community. Meanwhile, Internet addiction become potential threat to the community that might be more dangerous compare to drug and sex addiction in term of social consequences. This study offer the integrated solution through usability heuristics design for the purpose of redesigning current apps after the identification of business process in several Puskesmas in the Bandung. It also want to increase the quality of service in order to provide proper communication between health workers and patients. In evaluation phase, the 4 criteria was used to generate sketches in relation to contextual settings. Then, the mockups will be assessed with 12 transaction features to ensure the readiness of its financial management before the application launching. © 2021 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Movie recommendation system using clustering mining with Python 1

Movie recommendation system using clustering mining with Pyt...

引用

1st International Conference on Advances in Computational science and Engineering, ICACSE 2020

作者： Sadhasivam, Jayakumar Cera, Juan Manuel Deepa, R. Satheshkumar, K. Muthukumaran, V. Satheesh Kumar, S. Angeline Kavitha, M. Vellore Institute of Technology Vellore India Universudad de la Costa Barranquilla Colombia Telangana Hyderabad India School of Computing Kalasalingam Academy of Research and Education Tamilnadu 626128 India Department of Mathematics School of Applied Science REVA University Bengaluru64 India Department of Computer Science School of Applied Science REVA University Bengaluru64 India Voorhees College Tamilnadu Vellore India

The research we are pursuing here is about building a system which we will use and mine a movie review database using concepts of statistics like Euclidean Distance algorithm. This will help us determine similar review according to the ratings. What we plan on achieving through this approach is to analyze the reviews to suggest a suitable critic according to one's preferences and one's taste. We will do this according to the review we select and our algorithm which we use upon it. This algorithm will be the key to find those similar reviews. We are going to use Python programming to program this experiment. We have chosen to pursue this because of not the reviewers being incorrect or correct but merely different according to their preferences and their lean towards a certain genre and we know that a reviewer should also match the taste of the person who want to feel benefited of the review itself. So, we plan to make system that could help with that. © Published under licence by IOP Publishing Ltd.

关键词： High level languages

来源：评论

学校读者我要写书评

暂无评论

HMAMP: Hypervolume-Driven Multi-Objective Antimicrobial Peptides Design

arXiv

引用

arXiv 2024年

作者： Wang, Li Liu, Yiping Fu, Xiangzheng Ye, Xiucai Shi, Junfeng Yen, Gary G. Zeng, Xiangxiang The College of Computer Scienceand Electronic Engineering Hunan University Hunan Changsha China The School of Electrical and Computer Engineering Oklahoma State University StillwaterOK74078 United States The School of System Information and Engineering University of Tsukuba Ibaraki Japan Neher’s Biophysics Laboratory for Innovative Drug Discovery State Key Laboratory of Quality Research in Chinese Medicine Macau Institute for Applied Research in Medicine and Health Macau University of Science and Technology 999078 China

Antimicrobial peptides (AMPs) have exhibited unprecedented potential as biomaterials in combating multidrugresistant bacteria. Despite the increasing adoption of artificial intelligence for novel AMP design, challenges pertaining to conflicting attributes such as activity, hemolysis, and toxicity have significantly impeded the progress of researchers. This paper introduces a paradigm shift by considering multiple attributes in AMP design. Presented herein is a novel approach termed Hypervolume-driven Multi-objective Antimicrobial Peptide Design (HMAMP), which prioritizes the simultaneous optimization of multiple attributes of AMPs. By synergizing reinforcement learning and a gradient descent algorithm rooted in the hypervolume maximization concept, HMAMP effectively expands exploration space and mitigates the issue of pattern collapse. This method generates a wide array of prospective AMP candidates that strike a balance among diverse attributes. Furthermore, we pinpoint knee points along the Pareto front of these candidate AMPs. Empirical results across five benchmark models substantiate that HMAMP-designed AMPs exhibit competitive performance and heightened diversity. A detailed analysis of the helical structures and molecular dynamics simulations for ten potential candidate AMPs validates the superiority of HMAMP in the realm of multiobjective AMP design. The ability of HMAMP to systematically craft AMPs considering multiple attributes marks a pioneering milestone, establishing a universal computational framework for the multi-objective design of AMPs. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Measuring Electromagnetic Performance and Configuration of Networks in High Interference Environments

Measuring Electromagnetic Performance and Configuration of N...

引用

International Conference on Computing and Networking technology (ICCNT)

作者： A. Z. Khan Neeraj Panwar N K Rayaguru Priya M. Shelke Rakesh Kumar Giri P. Jaishankar Applied Physics Department Yeshwantrao Chavan College of Engineering Nagpur India Department of School of Computing University GEHU Dehradun India Department of EEE. Vel Tech Rangarajan Dr sagunthala R & D Institute of Science and Technology Department of InformationTechnology Vishwakarma Institute of Information Technology Pune India Department of Computer Science & Engineering Sunrise University Alwar India Department of School of Civil Engineering SASTRA Deemed to be University India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Measuring the electromagnetic overall performance and configuration of networks in high-interference environments can be challenging. In those environments, the indicators of hobby can be infected with unwanted heritage indicators, i.e., noise, leading to degraded overall performance and misguided size readings. This paper investigates the most reliable techniques for measuring networks’ electromagnetic performance and configuration in these problematic environments, utilizing introducing a unique multistage framework that combines sign-processing strategies with some community parameters. In particular, the framework includes four degrees: sign reception, sensitivity analysis, pass-correlation, and community configuration optimization-an analysis of the results of varying environmental conditions on sign reception and sensitivity change into conduct. A cross-correlation approach has evolved to decide the extent of correlation among one-of-a-kind alerts and to locate the specific configurations of the particular networks. Sooner or later, an optimization set of rules was carried out to locate the network’s optimum configuration. The final result of this research is a reliable method for measuring the electromagnetic performance and configuration of networks in high-interference environments. The proposed technique is anticipated to help researchers and engineers better understand the electromagnetic behaviors of complicated networks in actual-world scenarios.

关键词： Correlation Sensitivity analysis Atmospheric measurements Noise Electromagnetic interference Reliability engineering Particle measurements Electromagnetics Optimization Monitoring

来源：评论

学校读者我要写书评

暂无评论

Impact of spin-orbit interaction on the phase diagram and anisotropy of the in-plane critical magnetic field at the superconducting LaAlO3/SrTiO3 interface

引用

Physical Review B 2021年第17期104卷 174503-174503页

作者： P. Wójcik M. P. Nowak M. Zegrodnik AGH University of Science and Technology Faculty of Physics and Applied Computer Science Aleja Mickiewicza 30 30-059 Krakow Poland AGH University of Science and Technology Academic Centre for Materials and Nanotechnology Aleja Mickiewicza 30 30-059 Krakow Poland

The two-dimensional electron gas at the interface between LaAlO3 and SrTiO3 (LAO/STO) exhibits gate-tunable superconductivity with a characteristic domelike shape of the critical temperature (Tc) in the phase diagram. As shown recently [Phys. Rev. B 102, 085420 (2020)], such an effect can be explained as a consequence of the extended s−wave symmetry of the gap within an intersite real space pairing scenario, leading to a good agreement between the experiment and theory. In this work, we turn to a detailed analysis of the influence of spin-orbit coupling on the LAO/STO phase diagram by considering separately the atomic component as well as the interorbital hopping induced by the broken inversion symmetry at the interface. In particular, we analyze the optimal carrier concentration for which the maximal Tc is reached relative to the Lifshitz transition point. We find that the misalignment between the two can be significantly enhanced by the spin-orbit splitting of the bands, combined with the fact that superconductivity sets in when the Fermi level passes the anticrossing induced by the spin-orbital hybridization. In the presence of the external in-plane magnetic field, our calculations show fourfold anisotropy with the paramagnetic limit largely exceeded for B|| directed along the high symmetry points [01] and [01]. The obtained electron concentration dependence of Bc|| reproduces the characteristic domelike shape reported in experiments and the estimated value of Bc|| corresponds to that measured experimentally.

关键词： Multiband superconductivity Superconducting order parameter Two-dimensional electron gas Mean field theory

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：