检索结果-内蒙古大学图书馆

international conference on advanced Communication Technology (ICACT)

作者： Ali Hussain Sikandar Ali Umm E Farwa Md Ariful Islam Mozumder Hee-Cheol Kim Dept. of Digital Anti-Aging Healthcare Inje University Gimhae Republic of Korea College of AI Convergence Institute of Digital Anti-Aging Healthcare u-AHRC Inje University Gimhae Korea

ISBN: (数字)9791188428137

ISBN: (纸本)9798331507602

Foundation models are a revolutionary technology in the field of artificial intelligence that could usher in an era of transformation in every field with its vision and language understating capabilities while maintaining remarkable performance. Here, we extensively review state-of-the-art foundation models in various fields such as LLMs, GPT, BERT, CLIP, etc. We also demonstrate some famous areas where foundation models are gaining much popularity, such as general foundation models, foundation models in the medical domain, education, law and finance, mathematics, autonomous driving, etc. These foundation models are trained on large-scale data by leveraging the capabilities of self-supervised learning approaches that ensure outperforming accuracy for relevant downstream tasks. They are successful due to pioneering architectural innovations, especially synergistically interleaving transformers and convolutional neural networks. These models have exhibited adaptability and resilience in various data patterns and conditions through sophisticated training paradigms such as self-supervised and supervised learning methods. While they hold transformative potential, they also have many challenges. The scale and quality of training data are still important predictors of model performance, and the need for interpretable and explainable AI systems becomes critically important. We highlight important research opportunities, high-performing computationally efficient and scalable architectures, and approaches to enable multimodal learning capacities. This review sheds light on the current state of foundation models and proposes a roadmap for their successful transitions.

关键词： Training Technological innovation Foundation models Reviews Computational modeling Training data Self-supervised learning computer architecture Data models Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Big Data for Enhancing Cybersecurity in Enterprise Environments Proactive Threat Detection and Prevention

Big Data for Enhancing Cybersecurity in Enterprise Environme...

引用

3rd IEEE international conference on Automation and Computation, AUTOCOM 2025

作者： Chityala, Upender Reddy Shnain, Ammar H. Govindaraj, Manoj Johri, Prashant Kuppuraj, T. Devi, N.Lavanya Equinox It Solutions Llc United States College of Technical Engineering The Islamic University Department Of Computers Techniques Engineering Najaf Iraq Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Management Studies Chennai India School of Computing Science and Engineering Galgotias University Greater Noida India Karpagam Academy of Higher Education Department of Computer Applications Coimbatore India Psna College of Engineering and Technology Department of Ece India

ISBN: (纸本)9798331542375

This research explores the integration of big data technologies and machine learning to enhance cybersecurity in enterprise environments focusing on proactive threat detection and prevention. Traditional security systems often struggle to keep up with the growing complexity and volume of cyber threats, necessitating a more advanced, data-driven approach. The proposed methodology leverages real-time data processing, predictive modeling, and anomaly detection to improve threat detection accuracy, reduce response times, and enhance system scalability. By collecting and analyzing data from various network sources, including logs from security devices and endpoint protection software, the system detects potential threats more efficiently than conventional methods. Machine learning algorithms such as supervised and unsupervised learning, along with big data platforms like Apache Spark, enable real-time analysis of large volumes of data, ensuring timely identification of both known and unknown cyber threats. The results demonstrate significant improvements in detection accuracy, system scalability, and incident resolution time, with the proposed methodology outperforming traditional security systems in key performance metrics. This research highlights the potential of big data-driven cybersecurity solutions in addressing modern challenges and offers a framework for organizations to implement more effective, scalable, and proactive security measures to safeguard their digital assets. © 2025 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Predictive Accuracy in Used Car Pricing Models: A Comparative Analysis of Regression Techniques 6th

Enhancing Predictive Accuracy in Used Car Pricing Models: A ...

引用

6th international conference on advanced Informatics for Computing research, ICAICR 2023

作者： Chaubey, Ved Prakash Sareen, Devang Harshita, Chanda Sharma, Shamneesh Rana, Rattan Pal Singh Batra, Isha upGrad Campus upGrad Education Private Limited Bangalore India School of Computer Science Engineering and Technology Lovely Professional University Punjab Phagwara India Maharishi Markandeshwar Deemed To Be University Haryana Ambala Mullana India

ISBN: (纸本)9783031840586

The most important aspect aimed to develop a prediction model that could calculate a used car’s fair value based on a variety of factors, including the make, model year, fuel type, price, and miles. This study incorporated a lot of data science and machine learning approaches in the process of developing the model, which has a lot of promise and is available to manufacturers and other players in the used automobile market. The information used in this analysis came from a database of used car advertisements. To provide the best prediction accuracy, several regression techniques were evaluated, including decision tree regression, random forest regression, support vector regression, polynomial regression, and linear regression. To gain a deeper understanding of the data set, the research included substantial preprocessing and data visualization prior to the modeling step. To make it possible to evaluate the performance of each regression model, the data set was divided and modified to satisfy their specifications. The regression models were evaluated using the R-squared statistic. The final model presented in this study contains a wider range of used automobile attributes and provides better prediction accuracy when compared to previous investigations. This research promotes the used car industry and aids in the making of more informed judgments by providing a better model for pricing used cars. The benefits of sound data analysis and a range of regression techniques are used to increase the accuracy of such predictive models. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Enhancing Industrial Automation Through IIoT-Enabled Cloud Computing and LSTM for Scalable and Real-Time Data Analytics

Enhancing Industrial Automation Through IIoT-Enabled Cloud C...

引用

Automation and Computation (AUTOCOM), international conference on

作者： S. Shanmugapriya Rajendra Prasad Mohhammed H. Al-Farouni R. Velmurugan K. Ranjith Singh Selvin Pradeep Kumar S Department of Electrical and Electronics Engineering SRM Institute of Science and Technology Chengalpattu India School of Agriculture Uttaranchal University Dehradun India Department of Computer Techniques Engineering College of technical engineering The Islamic University Najaf Iraq Karpagam Academy of Higher Education Coimbatore India Department of Computer Science Karpagam Academy of Higher Education Coimbatore India Electronics and Communication Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai India

ISBN: (数字)9798331542375

ISBN: (纸本)9798331542382

In this thesis, we investigate the combined application of the Industrial Internet of Things (IIoT), cloud computing and Long Short-Term Memory (LSTM) networks to facilitate advanced industrial automation through the industrial analytics enabled by scalable and real time data processing. IIoT is an industrial approach to generating very large amounts of data from connected industrial devices that can be parsed through cloud computing to yield immediate insights into production processes, equipment health, and operational efficiency. Since this is a time series data, we employ LSTM (A type of recurrent neural network) in this architecture which is able to handle time series data well and is a good fit for predictive maintenance and anomaly detection problems in industrial setting. The proposed system involves three main components: Second, the IoT collection of data from IIoT devices, storage of data in the cloud, and processing of data are stored in the cloud; and finally, real time analysis of data using LSTM models. The LSTM models train on historical datasets containing sensor readings and machine logs, to make accurate equipment failure and process optimization predictions. For large scale data processing we use cloud computing platforms like AWS or Azure to manage where these big databases are located. Evaluation of the system performance is presented in the study with regard to prediction accuracy, latency and a comparison of LSTM with other ML techniques. We can see that that there's strong potential for these technologies to have a powerful impact on industrial automation, downtime, and operational efficiency. Yet, there are still data security and system scalability issues to explore. This research shows that IIoT implants and cloud computing, in conjunction with LSTM, can be designed to transform existing production processes.

关键词： Cloud computing Automation Data analysis Computational modeling Time series analysis Predictive models Real-time systems Long short term memory Industrial Internet of Things Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

3D simulation of Brain Tumor from 3D MRI Using Geometric Convolutional Neural Network and Point Clouds 2nd

3D Simulation of Brain Tumor from 3D MRI Using Geometric C...

引用

2nd international conference on Intelligent Systems and Data Science, ISDS 2024

作者： Phan, Anh-Cang Nguyen, Khac-Tuong Truong, Minh-Phuong Nguyen, Thi-Hong-Yen Nguyen, Ngoc-Hoang-Quyen Vinh Long University of Technology Education Vinh Long Viet Nam

ISBN: (纸本)9789819796151

Brain tumor is a disorder caused by the growth of abnormal brain cells. Brain tumor is a major risk for the patient’s survival rate and quality of life since it can cause severe impairment of organ function and even death. In the study, the research team presented an approach by utilizing methods to the modeling of brain tumor by replacing 3D with 2D convolutions based on tumor segmentation on 2D images using the Geometric convolutional neural network (gCNN) and Point Cloud. This method not only enables to conduct an accurate reconstruction and location, but also aids in monitoring changes in tumor size and growth rate over time. A result of the study indicates that the implement of gCNN and Point Cloud significantly improves the accuracy and efficiency in brain tumor segmentation and monitoring, thus supporting medical practitioners in the diagnosis and treatment planning process. This approach holds immeasurable promise in the medical field, aiming to enhance the quality of care and treatment for patients with brain tumors. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Extended Single-Particle Model Based on Physics-Informed Neural Network for SOC State Estimation of Lithium-Ion Batteries 8th

An Extended Single-Particle Model Based on Physics-Informed ...

引用

8th international conference on Life System modeling and simulation, LSMS 2024 and 8th international conference on Intelligent Computing for Sustainable Energy and Environment, ICSEE 2024

作者： Tian, Aina He, Luyao Dong, Kailang Ding, Tao Gao, Yang Jiang, Jiuchun Yang, Xiaoguang Hubei Key Laboratory for High-Efficiency Utilization of Solar Energy and Operation Control of Energy Storage System Hubei University of Technology Wuhan430068 China School of Electric Power South China University of Technology Guangzhou510640 China Beijing Institute of Technology Shenzhen Automobile Research Institute Shenzhen China

ISBN: (纸本)9789819602315

Because of its great accuracy, the electrochemical model is frequently utilized in the algorithm design process for lithium-ion batteries. Sadly, the electrochemical model requires a lot of time to solve since it is made up of many nonlinear partial differential equations. In order to solve an extended single particle model (ESPM) fast, a neural network based on physical information (PINN) is examined in this paper. The PINN-ESPM structure can not only estimate the state of charge, but also quickly and accurately estimate the lithium-ion concentration and potential under various application currents, which has stronger adaptability and scalability. In the process of neural network learning, different from the traditional neural network that needs to be trained by labeled data, the loss function is designed only based on the physical constraints brought by equations, boundary conditions and initial values, which makes it an unsupervised learning method. Finally, by comparing the PINN-ESPM proposed in this paper with the data obtained by the P2D model under various current conditions and the experiment battery voltage, the maximum relative error is maintained at 4%. The error of SOC based on the model is less than 4%. While under the same computing resources, PINN-ESPM is 500 times faster than the traditional numerical method. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Nonlinear equations

来源：评论

学校读者我要写书评

暂无评论

Utilizing Deep Learning and Natural Language Processing to Elucidate Neural Activity in Human Listeners

Utilizing Deep Learning and Natural Language Processing to E...

引用

Mobile Computing and Sustainable Informatics (ICMCSI), international conference on

作者： Yousef Methkal Abd Algani R Saravanakumar Department of Mathematics The Arab Academic College of Education in Israel Haifa Israel Department of ECE Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai India

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

Identifying the neural substrates of human auditory system has been a classic pursuit that fell into the list of grand challenges in neuroscience. Deep learning and natural language processing towards the end of the last decade have given a fruitful way to decipher and interpret neurons concerned with audio perception. This paper describes how these technologies may be used to enhance understanding of neural activity in human listeners. This will begin by defining the general auditory perception and the neural architecture supporting it before proceeding to review the insights learned from applying deep learning and natural language processing to demystify neural signals. Activity that occurs in the human brain is very important in the development of neuroscience, cognitive science and artificial intelligence. Here the effort has been made to try to figure out how CNN, RNN, and NLP could be integrated for the purpose of building a model to study the neural responses evoked by auditory stimuli. Selecting CNN s for feature extraction and RNN s for modeling of the temporal sequence consequently applying advanced elaboration of natural language processing we are aimed to reveal the intricate neural patterns for language and sound processing. As a training and testing dataset we have used Human Connectome Project with 1200 neural images total. It attained a 91.2 % accuracy while applying in the Python platform using Keras and tensorflow. Implications and relevance: The results of this work may have significance for further neuroscientific research, the creation of the systems of brain-computer interfaces, and thinking about the problems connected with privacy and consent. The paper demonstrates how deep learning and the NLP application alter the ways in which we look at auditory processing by the brain and future work in neuroscience and more.

关键词： Deep learning Training Privacy Neuroscience Reviews Neural activity Neurons Natural language processing Substrates Testing

来源：评论

学校读者我要写书评

暂无评论

Collision-Aware Autonomous Vehicle Motion Planning using Spiking Convolutional Neural Networks and Parrot Optimization Algorithm

Collision-Aware Autonomous Vehicle Motion Planning using Spi...

引用

international conference on ent Computing and Control Systems (ICICCS)

作者： Dhivakar Poosapadi Arigela Sri Harsha Sudheer Kumar Battula V. Choudri Annie T A S. Gayathri Priya Quest Global Services North America Ct USA Department of Mechanical Koneru Lakshmaiah Education Foundation Andhra Pradesh India Department of Mechanical Lakireddy Balireddy College of Engineering Andhra Pradesh India Department of Mathematics S.A. Engineering College Chennai Tamil Nadu India Department of Information Technology St Joseph's College of Engineering Chennai Tamil Nadu India Department of Electronics and Communication Engineering R.M.D. Engineering College Chennai Tamil Nadu India

ISBN: (数字)9798331512088

ISBN: (纸本)9798331512095

The primary input for motion planning, which permits safe autonomous driving on public roads, is an accurate trajectory prediction of nearby road users. advanced urban traffic conditions which are constantly evolving provide tremendous difficulties for autonomous vehicles specifically in the task of predicting the motion of surrounding vehicles and safely moving through it. This research seeks to address these challenges by presenting a new framework that combines a lightweight spiking convolutional neural network (LS-CNN) for real-time prediction of trajectories with an efficient collision avoidance technique based on the generated trajectory. The procedure includes learning from real-time information about traffic to estimate the direction of other vehicles around, and the parrot optimizer chooses the best routes of movement with low collision probability according to the results of LS-CNN perception. computer simulations of the proposed motion planner in MATLAB software and in-the loop simulations show a significantly increased rate of collision avoidance and an efficiency of the paths generated by the proposed planner compared to conventional methods. The findings of the study emphasize that the integrated system improves both the trajectory prediction efficiency and the level of navigating safety. The model obtained above 95% of the trajectory prediction accuracy and also offered the path with the collision risk less than 0.005%. This work helps to provide an optimal performance for autonomous driving cars by implementing a highly adaptive traffic scenario prediction method to enhance the future enhancement of the autonomous vehicle navigation systems.

关键词： Adaptation models Accuracy Computational modeling Roads Predictive models Prediction algorithms Real-time systems Trajectory Planning Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Leveraging Python Interpreters for Concurrency in SeQUeNCe

Leveraging Python Interpreters for Concurrency in SeQUeNCe

引用

22nd international conference on Scientific Computing and Bioinformatics, CSC 2024, and 25th international conference on Computational Biology, BIOCOMP 2024, held as part of the World Congress in computer Science, computer Engineering and Applied Computing, CSCE 2024

作者： Martin, Brett M. Hodson, Douglas D. Grimaila, Michael R. Department of Electrical and Computer Engineering U.S. Air Force Institute of Technology WPAFB DaytonOH45433 United States Department of Systems Engineering U.S. Air Force Institute of Technology WPAFB DaytonOH45433 United States

ISBN: (纸本)9783031859014

With the advent of the Navy research Laboratory’s announcement of the establishment of the Washington D.C. Metropolitan Quantum research Consortium (DC-QNet), there has been much interest in the modeling and simulation of the quantum communication network testbed. To that end, we explore in this research the basic functionality of the Simulator of QUantum Network Communication (SeQUeNCe), the developmental Python/C API Interpreters module, and their viability as technologies to be used for high-performance simulation of quantum networks. In this paper, we outline the integration of sub-interpreters with a parallel SeQUeNCe experiment to demonstrate true multi-threading concurrency in quantum network simulations. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Quantum communication

来源：评论

学校读者我要写书评

暂无评论

Conditional Generative modeling for Amorphous Multi-Element Materials

arXiv

引用

arXiv 2025年

作者： Li, Honglin Liu, Chuhao Guo, Yongfeng Luo, Xiaoshan Chen, Yijie Liu, Guangsheng Li, Yu Wang, Ruoyu Wang, Zhenyu Wu, Jianzhuo Ma, Cheng Xie, Zhuohang Lv, Jian Ding, Yufei Zhang, Huabin Luo, Jian Zhong, Zhicheng Li, Mufan Wang, Yanchao Li, Wan-Lu Key Laboratory of Material Simulation Methods and Software Ministry of Education College of Physics Jilin University Changchun China Aiiso Yufeng Li Family Department of Chemical and Nano Engineering University of California La Jolla San DiegoCA United States Institute of Molecular Engineering Plus College of Chemistry Fuzhou University Fuzhou China College of Chemistry and Molecular Engineering Peking University Beijing China School of Physics Nankai University Tianjin China Institute of Modern Physics Fudan University Shanghai China Program in Materials Science and Engineering University of California La Jolla San DiegoCA United States School of Artificial Intelligence and Data Science University of Science and Technology of China Hefei230026 China Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou215123 China International Center of Future Science Jilin University Changchun China Department of Computer Science and Engineering University of California La Jolla San DiegoCA United States Center for Renewable Energy and Storage Technologies Physical Science and Engineering Division King Abdullah University of Science and Technology Thuwal Saudi Arabia Suzhou Lab Suzhou215123 China

Amorphous multi-element materials offer unprecedented tunability in composition and properties, yet their rational design remains challenging due to the lack of predictive structure-property relationships and the vast configurational space. Traditional modeling struggles to capture the intricate short-range order that dictates their stability and functionality. We here introduce ApolloX, a pioneering predictive framework for amorphous multi-element materials, establishing a new paradigm by integrating physics-informed generative modeling with particle swarm optimization, using chemical short-range order as an explicit constraint. By systematically navigating the disordered energy landscape, ApolloX enables the targeted design of thermodynamically stable amorphous configurations. It accurately predicts atomic-scale arrangements, including composition-driven metal clustering and amorphization trends, which are well-validated by experiments, while also guiding synthesis by leveraging sluggish diffusion to control elemental distribution and disorder. The resulting structural evolution, governed by composition, directly impacts catalytic performance, leading to improved activity and stability with increasing amorphization. This predictive-experimental synergy transforms the discovery of amorphous materials, unlocking new frontiers in catalysis, energy storage, and functional disordered systems. Copyright © 2025, The Authors. All rights reserved.

关键词： Amorphization

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：