检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Ni, Bo Buehler, Markus J. Massachusetts Institute of Technology 77 Massachusetts Ave. CambridgeMA02139 United States Department of Materials Science and Engineering Carnegie Mellon University 5000 Forbes Avenue PittsburghPA15213 United States Center for Computational Science and Engineering Schwarzman College of Computing Massachusetts Institute of Technology 77 Massachusetts Ave. CambridgeMA02139 United States

Proteins are dynamic molecular machines whose biological functions, spanning enzymatic catalysis, signal transduction, and structural adaptation, are intrinsically linked to their motions. Designing proteins with targeted dynamic properties, however, remains a challenge due to the complex, degenerate relationships between sequence, structure, and molecular motion. Here, we introduce VibeGen, a generative AI framework that enables end-to-end de novo protein design conditioned on normal mode vibrations. VibeGen employs an agentic dual-model architecture, comprising a protein designer that generates sequence candidates based on specified vibrational modes and a protein predictor that evaluates their dynamic accuracy. This approach synergizes diversity, accuracy, and novelty during the design process. Via full-atom molecular simulations as direct validation, we demonstrate that the designed proteins accurately reproduce the prescribed normal mode amplitudes across the backbone while adopting various stable, functionally relevant structures. Notably, generated sequences are de novo, exhibiting no significant similarity to natural proteins, thereby expanding the accessible protein space beyond evolutionary constraints. Our work integrates protein dynamics into generative protein design, and establishes a direct, bidirectional link between sequence and vibrational behavior, unlocking new pathways for engineering biomolecules with tailored dynamical and functional properties. This framework holds broad implications for the rational design of flexible enzymes, dynamic scaffolds, and biomaterials, paving the way toward dynamics-informed AI-driven protein engineering. © 2025, CC BY-NC-ND.

关键词： Signal transduction

来源：评论

学校读者我要写书评

暂无评论

Air Pollution Monitoring By Integrating Local and Global Information in Self-Adaptive Multiscale Transform Domain

引用

IEEE Transactions on Multimedia 2025年

作者： Gu, Ke Liu, Yuchen Liu, Hongyan Liu, Bo Qiao, Junfei Lin, Weisi Zhang, Wenjun Beijing University of Technology School of Information Science and Technology Engineering Research Center of Intelligent Perception and Autonomous Control of Ministry of Education Beijing Laboratory of Smart Environmental Protection Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing Artificial Intelligence Institute Beijing100124 China Massey University School of Mathematical and Computational Sciences New Zealand Nanyang Technological University College of Computing and Data Science Singapore Shanghai Jiao Tong University Institute of Image Communication and Information Processing Shanghai China

As the deadliest form of pollution, air pollution had a prolonged severe damage to the human health and life safety of nearly 99% of the world's population. Facing to the problem that billions of tons of pollutants discharged into the air per year by industrial activities, this paper proposed a novel image-based air pollution monitor (IAPM) by incorporating local and global information in the self-adaptive multiscale transform domain, so as to achieve the timely and effective leakage detection of typical air pollutants from a single image. To be specific, this paper first developed a screen-shaped module according to two significant findings in visual neuroscience, which include the high sensitivity of human eyes to horizontal and vertical stimuli and the center-surround inhibition, by designing and fusing the square module, horizontal strip module and vertical strip module parallelly for simulating the behaviour of human eyes to extract local features. Second, the learnable weights and proportional mapping were applied to incorporate the screen-shaped module and lightweight vision transformer as backbone, towards more richly exploiting and fusing local and global information just as the way a brain perceives external stimuli. Third, a new self-adaptive multiscale transform domain method was devised based on two motivations from the visual characteristics of multiscale perception and the brain characteristics of self-adaptive domain transform to modify the backbone by using the operations of pooling and pointwise convolution. Extensive experiments implemented on the datasets of carbon particulate matters and ethylene leakage confirmed the superior monitoring performance of the proposed IAPM model beyond the state-of-the-art (SOTA) peers by an accuracy gain of about 4%. Furthermore, the proposed IAPM model only required 0.089 GFLOPs and 0.15 million model parameters, remarkably outperforming SOTA competitors in computational efficiency and storage resources. © 1999-2

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Neural Networks for Fault diagnosis in Electrical Machine

Neural Networks for Fault diagnosis in Electrical Machine

引用

Intelligent Technologies (ACOIT), Asian Conference on

作者： R. Vinston Raja J. Raja Sreenivasulu Gogula Atul Katiyar T. Thilagam V. S. Bhagavan Department of Computational Intelligence Faculty of Engineering and Technology School of Computing SRM Institute of Science and Technology Kattankulathur Chennai Tamil Nadu India Department of Computer Science and Engineering School of Computing Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Computer Science and Engineering (Data Science) Vardhaman College of Engineering Hyderabad Telangana India Department of Electrical Engineering Mahatma Jyotiba Phule Rohilkhand University Bareilly Uttar Pradesh India Department of Science and Engineering S.A Engineering College Chennai Tamil Nadu India Department of Mathematics Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh India

ISBN: (数字)9798350374957

ISBN: (纸本)9798350374964

Finding electrical equipment problems quickly is essential for minimising downtime and ensuring ongoing functioning. When it comes to early defect identification, traditional methods like human inspection or sensor-based surveillance might not cut it. Another alternative to employing machine learning algorithms to analyse complex patterns in sensor data is neural networks. With an emphasis on motor drives, this article lays forth a method for identifying electrical equipment issues using neural networks. The network has been trained to identify various issues, such as imbalanced rotors, broken stator windings, and failing bearings, by examining historical data. The trial findings prove that the suggested method may effectively find issues, make things more reliable, and cut down on maintenance expenses.

关键词： Fault diagnosis Motor drives Machine learning algorithms Surveillance Neural networks Stator windings Rotors Machine learning Maintenance Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

ANALYSIS AND APPROXIMATION TO PARABOLIC OPTIMAL CONTROL PROBLEMS WITH MEASURE-VALUED CONTROLS IN TIME

arXiv

引用

arXiv 2024年

作者： Gong, Wei Liang, Dongdong The State Key Laboratory of Scientific and Engineering Computing Institute of Computational Mathematics National Center for Mathematics and Interdisciplinary Sciences Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China The Hong Kong Polytechnic University Shenzhen Research Institute Shenzhen518057 China

In this paper, we investigate an optimal control problem governed by parabolic equations with measure-valued controls over time. We establish the well-posedness of the optimal control problem and derive the first-order optimality condition using Clarke’s subgradients, revealing a sparsity structure in time for the optimal control. Consequently, these optimal control problems represent a generalization of impulse control for evolution equations. To discretize the optimal control problem, we employ the space-time finite element method. Here, the state equation is approximated using piecewise linear and continuous finite elements in space, alongside a Petrov-Galerkin method utilizing piecewise constant trial functions and piecewise linear and continuous test functions in time. The control variable is discretized using the variational discretization concept. For error estimation, we initially derive a priori error estimates and stabilities for the finite element discretizations of the state and adjoint equations. Subsequently, we establish weak-* convergence for the control under the norm M(I¯c;L2(ω)), with a convergence order of O(h 21 + τ 41 ) for the *** Codes 65M06, 68M99, 49M40 © 2024, CC BY-SA.

关键词： Optimal control systems

来源：评论

学校读者我要写书评

暂无评论

On a Robin-type non-singular coupling scheme for solving the wave scattering problems

arXiv

引用

arXiv 2023年

作者： Liu, Xiaojuan Li, Maojun Yin, Tao School of Mathematical Sciences University of Electronic Science and Technology of China Sichuan Chengdu611731 China LSEC Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China

This paper studies a non-singular coupling scheme for solving the acoustic and elastic wave scattering problems and its extension to the problems of Laplace and Lamé equations and the problem with a compactly supported inhomogeneity is also briefly discussed. Relying on the solution representation of the wave scattering problem, a Robin-type artificial boundary condition in terms of layer potentials whose kernels are non-singular, is introduced to obtain a reduced problem on a bounded domain. The wellposedness of the reduced problems and the a priori error estimates of the corresponding finite element discretization are proved. Numerical examples are presented to demonstrate the accuracy and efficiency of the proposed method. Copyright © 2023, The Authors. All rights reserved.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

IoT-Enhanced Path Planning and Obstacle Avoidance for Autonomous Mobile Robots

IoT-Enhanced Path Planning and Obstacle Avoidance for Autono...

引用

Advancement in Technology (ICONAT), International Conference for

作者： N Selvanathan Sr Ramya C Sureshkumar R. Kiruthiga J Akshya Mani Deepak Choudhry M. Sundarrajan Department of Information Technology Sona College of Technology Salem Department of Computer Science and Engineering Dr NGP Institute of Technology Coimbatore Department of Information Technology KGiSL Institute of Technology Coimbatore Department of AI&DS Bannari Amman Institute of Technology Erode Department of Computational Intelligence SRM Institute of Science and Technology Chennai Department of Computing Technologies SRM Institute of Science and Technology Chennai Department of Networking and Communications SRM Institute of Science and Technology Chennai

ISBN: (数字)9798350354171

ISBN: (纸本)9798350354188

Path planning and obstacle avoidance play a key role in how well autonomous mobile robots work and stay safe when they move through tricky areas. Traditional path-planning methods often can’t keep up when new obstacles pop up or existing ones change, which makes them less useful in the real world. To fix these problems, the proposed research work brings in a new IoT-powered path planning and obstacle avoidance system that uses the $\mathrm{D}^{*}$ Lite and Deep Reinforcement Learning (DRL) algorithms. Our approach brings together D* Lite’s quick replanning skills with DRL’s ability to learn and adapt made even better by live data from IoT sensors. We’ve put our model through its paces in different simulated environments set up to be as tricky as real-world navigation. Quantitative analysis shows it’s a big step up from older models. Adding IoT data leads to a 30% boost in how paths are planned and cut the time robots need to get through complex routes by 20%. Plus, using DRL helps robots deal with moving obstacles 25% better, which means fewer potential crashes. This is a big step forward in the field of autonomous robotics. It gives a robust answer that would not just be reactive to the given environmental inputs but also, through proactivity, prompt possible obstacles, further contributing to smoother and safer output. As we move along with the development of our methodology, we foresee broad applications in many sectors enhancing the autonomy and efficiency of robotic systems working in dynamic and unpredictable environments.

关键词： Measurement Adaptation models Navigation Statistical analysis Heuristic algorithms Robot sensing systems Path planning Mobile robots Collision avoidance Autonomous robots

来源：评论

学校读者我要写书评

暂无评论

A Voice Enabled Grammar Correction System using Transformers

A Voice Enabled Grammar Correction System using Transformers

引用

Artificial Intelligence For Internet of Things (AIIoT), International Conference on

作者： Prakhar Jain Nishtha Yashwantrao Bahirat C.Sherin Shibi Babitha Lincy R Jency Rubia J A R Arunarani Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur Chengalpattu Tamil Nadu India Computer and Communication Engineering Department Sri Eshwar College of Engineering Coimbatore Tamil Nadu India Department of ECE Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Avadi Tamil Nadu India

ISBN: (数字)9798350372120

ISBN: (纸本)9798350372137

This paper introduces a groundbreaking real-time grammar error detection and correction system (named “Error Ears”) that adapts to linguistic interactions. At the core of the proposed approach lies the utilization of the potent “T5” model, renowned for its capability to comprehend and produce human-like text. The proposed workflow meticulously covers essential stages including data pre-processing, model training, and fine-tuning. By fine-tuning the “T5” model on a diverse dataset of sentences with numerous grammatical errors, the goal is to empower it to distinguish complex contextual nuances in speech. Preliminary results indicate that “Error Ears” represents a substantial advancement over traditional correctional systems. This system excels at swiftly identifying and rectifying intricate spoken language errors, encompassing structural and contextual details. What sets it apart is its ability to provide real-time contextual suggestions, rendering it especially valuable during virtual meetings, presentations, and everyday conversations. “Error Ears” is poised to redefine spoken language communication standards by enhancing clarity and precision. Its potential utility extends across a spectrum of contexts and linguistic environments, ensuring more efficient and accurate oral communication. In the digital age, this study opens up new avenues for a better comprehension and expression of language, resulting in more effective and transparent communication.

关键词： Adaptation models Accuracy Speech recognition Oral communication Linguistics Web conferencing Transformers

来源：评论

学校读者我要写书评

暂无评论

Identification of Cyberbullying and Finding Target User's Intention on Public Forums

Identification of Cyberbullying and Finding Target User's In...

引用

International Conference on Contemporary computing and Informatics (IC3I)

作者： Lalitha Krishnasamy Kiruthika M Manjunatha Swamy C Vigneshwaran T Sharon Roji Priya C D. Vijay Anand Department of CSE School of Engineering and Technology Christ University Bengaluru India Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur Tamilnadu India Department of Information Technology Kongu Engineering College Erode India

Numerous cybercriminals are active in the online realm, carrying out cyber-crimes according to predetermined and preplanned agendas. Cyberbullying, which was formerly limited to physical limits, has now expanded online as a result of technology advancements. One type of cyberbullying is denigration or insult. The cyberbullying cases are in exponential rise in social media as per the reports of Computer Emergency Team by Sri Lanka. Insulting words are changeable in dynamic and the same terminology may have numerous meanings depending on the context. Bullying cannot be defined just because a statement comprises such a term. As a result, when classifying comments, standard keyword detecting approaches are insufficient. Other languages also may have dealt with this issue by utilizing lexical databases like WordNet, which might give synonyms as well as homonyms for words. Because no adequate lexical database mainly for the English language has been built, recognizing a word like bullying is difficult. As a result, employed rules to solve the problem. Facebook comments containing profanity were gathered, outliers were eliminated, and the remaining messages were pre-processed. Five feature extraction rules were employed to assess insult in the text. Following that, used the Support Vector Machine (SVM) technique. Using an F1-score of 85%, the findings demonstrate that when compared to existing works, SVM performs better. The focus on English language cyberbully identification, which has never been addressed earlier, distinguishes this study.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Analysis of Arabic Sentiment Analysis using Lexicon and Machine Learning based Approaches

Comprehensive Analysis of Arabic Sentiment Analysis using Le...

引用

Network, Multimedia and Information Technology (NMITCON) International Conference on

作者： M. Maheswari Ammar Hameed Shnain Ayesha Siddiqua H C Nagaraj N. Shilpa Department of Computational Intelligence School of Computing SRM Institue of Science and Technology Kattankulathur India Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Department of ECE Nitte Meenakshi Institute of Technology Bengaluru India Department of ECE School of Engineering SR University Warangal India

ISBN: (数字)9798350372892

ISBN: (纸本)9798350372908

Arabic sentiment analysis (ASA) is a vital field in Natural Language Processing (NLP) that utilizes Machine Learning (ML) techniques to understand the complex emotional tones that are present in Arabic text. This survey discovers the use of ML in Arabic sentiment analysis, which aims to implement various methodologies for sentiment classification. The goal is to develop a robust model capable of translating nuanced sentiments expressed in different dialects and intricate linguistic structures. The methodology involves creating a labeled dataset, using preprocessing techniques, and utilizing machine learning algorithms such as linear classifiers and deep learning models. By extracting features, training the model, and evaluating its performance, the methodology improves the accuracy of sentiment evaluations. The results of this study highlight the effectiveness of machine learning models in accurately categorizing sentiments in Arabic text, as demonstrated by performance metrics such as precision, recall, and accuracy.

关键词： Surveys Training Support vector machines Measurement Sentiment analysis Accuracy Social networking (online) Reviews Feature extraction Standards

来源：评论

学校读者我要写书评

暂无评论

Identifying Transient candidates in the Dark Energy Survey using Convolutional Neural Networks

arXiv

引用

arXiv 2022年

作者： Ayyar, Venkitesh Knop, Robert Awbrey, Autumn Andersen, Alexis Nugent, Peter Lawrence Berkeley National Laboratory 1 Cyclotron Rd BerkeleyCA94720 United States Hariri Institute for Computing and Computational Science and Engineering Boston University BostonMA02215 United States Department of Astronomy University of California Berkeley BerkeleyCA94720 United States

The ability to discover new transient candidates via image differencing without direct human in-tervention is an important task in observational astronomy. For these kind of image classification problems, machine Learning techniques such as Convolutional Neural Networks (CNNs) have shown remarkable success. In this work, we present the results of an automated transient candidate identification on images with CNNs for an extant dataset from the Dark Energy Survey Supernova program (DES-SN), whose main focus was on using Type Ia supernovae for cosmology. By performing an ar-chitecture search of CNNs, we identify networks that efficiently select non-artifacts (e.g. supernovae, variable stars, AGN, etc.) from artifacts (image defects, mis-subtractions, etc.), achieving the efficiency of previous work performed with random Forests, without the need to expend any effort in feature identification. The CNNs also help us identify a subset of mislabeled images. Performing a relabeling of the images in this subset, the resulting classification with CNNs is significantly better than previous results, lowering the false positive rate by 27% at a fixed missed detection rate of 0.05. © 2022, CC BY.

关键词： Convolution

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：