检索结果-内蒙古大学图书馆

40th International Conference on Machine Learning, ICML 2023

作者： Bihani, Vaibhav Manchanda, Sahil Sastry, Srikanth Ranu, Sayan Anoop Krishnan, N.M. Department of Civil Engineering Indian Institute of Technology Delhi India Department of Computer Science and Engineering Indian Institute of Technology Delhi India Yardi School of AI Indian Institute of Technology Delhi India Theoretical Sciences Unit School of Advanced Materials Jawaharlal Nehru Centre for Advanced Scientific Research Bengaluru India

Optimization of atomic structures presents a challenging problem, due to their highly rough and non-convex energy landscape, with wide applications in the fields of drug design, materials discovery, and mechanics. Here, we present a graph reinforcement learning approach, STRIDERNET, that learns a policy to displace the atoms towards low energy configurations. We evaluate the performance of STRIDERNET on three complex atomic systems, namely, binary Lennard-Jones particles, calcium silicate hydrates gel, and disordered silicon. We show that STRIDERNET outperforms all classical optimization algorithms and enables the discovery of a lower energy minimum. In addition, STRIDERNET exhibits a higher rate of reaching minima with energies, as confirmed by the average over multiple realizations. Finally, we show that STRIDERNET exhibits inductivity to unseen system sizes that are an order of magnitude different from the training system. All the codes and datasets are available at https://***/M3RG-IITD/StriderNET. © 2023 Proceedings of Machine Learning Research. All rights reserved.

关键词： Silicates

来源：评论

学校读者我要写书评

暂无评论

Graph Convolution Network with Temporal Features for Autism Disorder Classification

Graph Convolution Network with Temporal Features for Autism ...

引用

2024 International Conference on computer, Electronics, Electrical engineering and their Applications, IC2E3 2024

作者： Badoni, Akhil Kaushal, Gaurav Tiwari, Alok Kumar Tripathi, Pawan ABV-Indian Institute of Information Technology and Management Gwalior Department of Information Technology Gwalior India ABV-Indian Institute of Information Technology and Management Department of Electrical and Electronics Engineering Gwalior India Case Western Researve University Department of Material science and Engineering United States

ISBN: (纸本)9798350388534

Autism Spectrum Disorder (ASD) is a significant developmental brain disorder. Recently, several advanced deep learning techniques leveraging functional magnetic resonance imaging (FMRI) data have emerged for ASD classification. Notably, graph neural networks, extending deep neural network models to graph-structured data, have demonstrated considerable benefits. Various GNN models have been proposed in the past, including the latest Heterogeneous Graph Convolution Attention Network (HCAN), which combines the phenotype features of patients and generates a graph. While some studies make use of temporal features in FMRI data, few integrate these features with phenotype data. This study presents a novel approach by adapting the state-of-the-art HCAN architecture to incorporate temporal features. By merging these two methodologies, the research seeks to propel the field towards improved accuracy and reliability in ASD detection. © 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

Developing an ML Model for Detecting the Cyber Attacks in Electric Vehicles 1

Developing an ML Model for Detecting the Cyber Attacks in El...

引用

1st IEEE International Conference on Cognitive Robotics and Intelligent Systems, ICC - ROBINS 2024

作者： Roopesh Albert, Bertia Manuel, Alan Shine Hemram, Saimon Karunya Institute of Technology and Sciences Department of Computer Science and Engineering Karunya Nagar Coimbatore641114 India

ISBN: (纸本)9798350372748

This study shows that electric cars (EVs) are a viable replacement for conventional combustion-engine vehicles, providing lower carbon emissions and more environmentally friendly modes of transportation. Depite the hype, the challenges like cybersecurity flaws and possible cyberattacks are also emerging in EVs. In addition to jeopardizing user privacy and vehicle safety, a number of issues seriously jeopardize the integrity and security of electric cars (EVs). This research offers a unique machine learning (ML)-based detection and prevention system designed to identify cyber threats in electric vehicles (EVs) in response to these problems. The suggested solution examines Controller Area Network (CAN) traffic data using cutting-edge ML algorithms to find unusual patterns suggestive of cyber threats. The solution improves the cybersecurity resilience of electric vehicles (EVs) by including proactive preventive measures and real-time threat detection capabilities. This ensures vehicle safety and guards against new and existing cyber-attacks. Through thorough evaluation and validation procedures, the efficacy of the suggested system is proven, underscoring its strong performance in identifying and averting cyberattacks in electric vehicles. This research helps to create safer and more secure mobility solutions for electric vehicles by implementing proactive cybersecurity measures and integrating cutting-edge ML technology. © 2024 IEEE.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

A novel recursive privacy-preserving information retrieval approach for private retrieval

引用

International Journal of Intelligent Information and Database Systems 2022年第3期15卷 269-274页

作者： Bhat, Radhakrishna Kumar, K.M. Mahesh Sunitha, N.R. Department of Computer Science and Engineering Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal576104 India Department of Information Science and Engineering Nitte Meenakshi Institute of Technology Karnataka Bangalore560064 India Department of Computer Science and Engineering Siddaganga Institute of Technology Karnataka Tumkur572102 India

The major drawback of existing information retrieval schemes in preserving user privacy is that they either exhibit computationally bounded privacy with intractability assumptions or perfect privacy with high bandwidth utilisation. Today, the essential requirement is to have a bandwidth efficient perfect privacy preserving information retrieval scheme in order to provide effective and guaranteed service to the information retrieving user. Therefore, in this paper, we have constructed a new single database perfect privacy preserving private block retrieval scheme called ‘pepperPBR’ using quadratic residuosity as the underlying primitive where private block retrieval (PBR) is a natural extension to private information retrieval (PIR). In this paper, user generates O(6k) bit query and server generates O(2ku + o(n)) bit response where n is the database size, o(n) is the non-trivial server communication cost, u is the number of database blocks, k is the security parameter. Copyright © 2022 Inderscience Enterprises Ltd.

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Diagnosis Using Elephant Herding Optimization and Sparse Autoencoder Through Gene Expression Analysis 15th

Breast Cancer Diagnosis Using Elephant Herding Optimization ...

引用

15th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2023 and 14th World Congress on Nature and Biologically Inspired Computing, NaBIC 2023

作者： Bharanidharan, N. Chakravarthy, S. R. Sannasi Kumar, V. Vinoth Kavya, B. Meghana, G. Rajaguru, Harikumar School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India Department of Electronics and Communication Engineering Bannari Amman Institute of Technology Sathyamangalam India Department of Computer Science and Engineering Dayananda Sagar University Bangalore India Department of Computer Science and Engineering PES University RR Campus Bangalore India

ISBN: (纸本)9783031810794

Gene expression analysis is an efficient modality to detect breast cancer. But analysis of the gene expression data is a complicated task due to the involvement of large number of numerical data for each subject. This research work focuses on the development of computerized diagnosis systems for analyzing the gene expression data and classifying the subjects as either normal or breast adenocarcinoma. Sparse autoencoder is used for dimensionality reduction and Elephant Herding Optimization is used for transforming the features. Four different supervised classifiers namely support vector machine, random forest classifier, decision trees, and naive bayes classifier are examined for classification task. Among them, random forest provides the superior balanced accuracy of 86% while it was further enhanced to 92% with the help of sparse autoencoders and elephant herding optimization algorithm. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Transcription

来源：评论

学校读者我要写书评

暂无评论

FlowARP - Using Augmented Reality for Visualizing Control Flows in Programs 2023

FlowARP - Using Augmented Reality for Visualizing Control Fl...

引用

2nd ACM Conference on Global Computing Education, CompEd 2023

作者： Venigalla, Akhila Sri Manasa Chimalakonda, Sridhar Lab Dept. of Computer Science & Engineering Indian Institute of Technology Tirupati Andhra Pradesh Tirupati India

ISBN: (纸本)9798400700484

There is a rise in the use of visual cues such as augmented reality and virtual reality to teach programming concepts and algorithms to novice programmers. These visualizations increase motivation among novice programmers, and also contribute to better conceptual understanding. For effective implementation of an algorithm or program, it is important to understand its flow of execution. The flow of an algorithm is commonly represented pictorially as a control flow graph (CFG) or as an abstract syntax tree (AST). However, existing representations are static in nature. Adding a dynamic aspect to the CFG to represent the flow of a program or an algorithm might ease the conceptual understanding. Integrating this dynamic CFG with augmented reality might also increase motivation among students in viewing and understanding various algorithms and programs. Hence, we present FlowARP, an augmented reality based visualization tool, to demonstrate the flow of programs. As a first step, we have designed FlowARP to support C/C++ programs and evaluated the usefulness of FlowARP through a user study with 44 undergraduate students, based on an amalgamated approach that assess usefulness and user perception. The results indicated that users were able to solve code-snippet based questions in lesser time, using FlowARP. However, we also observed that users take some amount of time to get accustomed to FlowARP. © 2023 ACM.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Effective Vehicle Detection Using Improved Faster Recursive Convolutional Neural Network Model

引用

SN computer science 2023年第2期4卷 105页

作者： Mahendra, G. Roopashree, H.R. Department of Computer Science & Engineering GSSS Institute of Engineering & Technology for Women Affiliated to VTU Karnataka Belagavi India

In recent decades, vehicle recognition plays an essential and effective role in the intelligent transportation system and traffic safety. Currently, the deep learning approaches made an effective impact in the fast vehicle detection application. In the real-time traffic monitoring video sequences, it is difficult to recognize the smaller vehicle targets and multi-scale vehicle targets in the complex scenes. A new fully automated vehicle detection model is implemented in this manuscript to address the above-mentioned issue. After obtaining the videos from KITTI dataset, the mask is created for specific classes like car, pedestrian, and cyclist. Additionally, the data augmentation is accomplished using the techniques like zoom-out, zoom-in, shift, shear, flipping, and rotation. The data augmentation enhances the performance of the deep learning models by creating different and new examples for training the dataset. The deep learning models perform accurately, if the dataset is rich and sufficient. After data augmentation, an improved faster Recursive Convolutional Neural Network (R-CNN) model is developed for vehicle detection. The improved faster R-CNN model first extracts discriminative feature values from the images utilizing U-Net and Visual Geometry Group (VGG) 19 pre-trained methods. Then, it creates the region proposal to improve the detection performance and narrow the search space. On the KITTI dataset, the improved faster R-CNN model achieved 90.59% of average precision and 0.45 s of processing time, which are better compared to the existing models. © 2022, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Autonomous driving computer vision Data augmentation Deep learning Faster R-CNN model Surveillance video Vehicle detection

来源：评论

学校读者我要写书评

暂无评论

Modeling of variability-aware memristive neural networks

Modeling of variability-aware memristive neural networks

引用

2023 Device Research Conference, DRC 2023

作者： Sasikumar, Renjith Ganapathi, K. Lakshmi Misra, Durgamadhab Padmanabhan, Revathy Indian Institute of Technology Palakkad Department of Electrical Engineering India National Institute of Technology Department of Physics Kurukshetra India New Jersey Institute of Technology Department of Electrical and Computer Engineering United States

ISBN: (纸本)9798350323108

In recent years, memristive neuromorphic systems have gained much attention. In this work, we developed a physics-based framework to model transport in valence change memory (VCM) memristors, implemented in Verilog-A. This has enabled us to scale up and simulate the performance of these devices in a crossbar array/neural network for pattern classification, for instance. The system's performance is analyzed based on classification accuracy in different conditions. We anticipate that this will provide useful insights into the design of these systems by analyzing their performance, based on our model. © 2023 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Classification of imbalanced datasets utilizing the synthetic minority oversampling method in conjunction with several machine learning techniques

引用

Iran Journal of computer science 2024年第1期8卷 51-68页

作者： Datta, Shrayasi Ghosh, Chinmoy Choudhury, J. Pal Department of Information Technology Jalpaiguri Government Engineering College West Bengal Jalpaiguri 735102 India Department of Computer Science & amp Engineering Jalpaiguri Government Engineering College West Bengal Jalpaiguri 735102 India Department of Computer Science & amp Engineering Narula Institute of Technology West Bengal Agarpara 700109 India

Pharmacological datasets like Yeast and Escherichia coli (E. coli) have a massive impact on the healthcare industry for the production of human drugs. Yeast is well recognized as a significant constituent in the production of pharmaceuticals for human use, owing to its cellular structure that bears resemblance to that of human cells. E. coli is widely regarded as the preferred expression host within the biotechnology industry for the efficient and cost-effective production of proteins on a large scale. This preference is particularly evident in the context of non-glycosylated proteins, which are of significant interest for their therapeutic applications. This study aims to determine the efficacy of machine learning (ML) methods in classifying pharmacological datasets like Yeast and E. coli. As Yeast and E. coli both are imbalanced datasets by nature, to handle the imbalanced classification problem, the synthetic minority oversampling technique (SMOTE) is used in this study. The application of the combined feature subset selection (CFSS) approach has been also employed to find out the overall classification performance, but classification with CFFS has not been very promising. According to the findings, classification on SMOTE-oversampled data gives better results and from several performance and evaluation metrics, random forest achieves the best overall prediction performance for both Yeast and E. coli datasets with an accuracy of 87% and 97%, precision of 87% and 97%, recall of 87% and 98%, and f1 score of 85% and 98%, respectively. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Classification E. coli Feature selection SMOTE Yeast

来源：评论

学校读者我要写书评

暂无评论

Dynamic Data Placement Strategy with Network Security Issues in Distributed Cloud Environment for Medical Issues: An Overview

引用

Recent Advances in computer science and Communications 2024年第6期17卷 25-38页

作者： Pradhan, Devasis Behera, Majusha Gheisari, Mehdi Department of Electronics and Communication Engineering Acharya Institute of Technology Karnataka Bangalore560107 India School of Electronics Engineering Campus 12 KIIT deemed to be University Odisha Bhubaneswar India Department of Cognitive Computing Institute of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India

The rapid integration of distributed cloud systems in the healthcare industry has profoundly impacted the management of valuable medical data. While this advancement has significantly improved data handling, protecting sensitive healthcare information in such a complex environment remains daunting. This comprehensive study explores the crucial intersection between dynamic data placement strategies and network security concerns in distributed cloud environments, particularly healthcare. After establishing the significance and context of this research, the survey delves into the growing need to safeguard medical data within the everevolving landscape of cloud-based healthcare systems. It lays out fundamental concepts, such as dynamic data placement and network security, highlighting their unique implications in the medical domain. Ultimately, this survey sheds light on the most effective approaches for balancing dynamic data placement and network security in the healthcare sector. This research delves into examining many tactics, evaluating their effectiveness in handling delicate medical information, and presenting tangible use cases. A key focus of this investigation is the fusion of data organization and network safety within the healthcare industry. It investigates the adaptability of dynamic data positioning techniques in fortifying network security and safeguarding against potential threats unique to the healthcare sector. Case studies of the successful implementation of these strategies in healthcare establishments are also included. © 2024, Bentham science Publishers. All rights reserved.

关键词： Electronic health record

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：