检索结果-内蒙古大学图书馆

2023 International Conference on computer science, Information Technology and Engineering, ICCoSITE 2023

作者： Hasani, Muhammad Fikri Heryadi, Yaya Arifin, Yulyani Lukas Suparta, Wayan Bina Nusantara University BINUS Graduate Program Computer Science School of Computer Science Computer Science Department Jakarta11480 Indonesia Bina Nusantara University BINUS Graduate Program Computer Science Computer Science Department Jakarta11480 Indonesia Jakarta12930 Indonesia Institut Teknologi Nasional Yogyakarta Faculty of Industrial Technology Department of Electrical Engineering Yogyakarta55281 Indonesia

ISBN: (纸本)9798350320954

Task oriented chatbots are a sub-topic related to chatbots, where chatbots will perform certain tasks with specific goals. One part of creating a task-oriented chatbot is doing intent classification. Intent classification is a task of text classification. As in general text classification, the required dataset requires a label to carry out the classification process. To speed up and help the utterance analysis process, there is already a method, namely clustering, and Density-based clustering is a part of clustering that can determine cluster patterns based on arbitrary data, with DBScan as one of its algorithms. This research used 10000 client utterance data of awhatsapp based e-commerce conversation. SentenceBert also used as a state of art sentence embedding. This research yield silhouette score of 0.327 as the best result from eps of 0.1 and MinPts of 95. However, based on the cluster result, sentences labelled as noise can be further clustered. Text Preprocessing, text augmentation and sentence embedding techniques can be explored to increase the cluster performance. © 2023 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

ML-Based Fault Detection Strategies for Power Electronics 9

ML-Based Fault Detection Strategies for Power Electronics

引用

9th IEEE India International Conference on Power Electronics, IICPE 2023

作者： Jain, Aarushi Lathwal, Rani Data Science Jagannath University New Delhi India Amity University Department of Computer Science & Engineering Noida India

ISBN: (纸本)9798350307252

Power electronics plays a pivotal role in modern energy systems, contributing to improved efficiency, reduced emissions, and enhanced control in various applications such as renewable energy integration, electric vehicles, and smart grids. This vital domain within electrical engineering, has undergone a remarkable transformation through the integration of Machine Learning, as the power electronics industry has witnessed significant advancements in optimizing operations, improving reliability, and enabling sustainable energy solutions. This research paper presents various strategies of Machine learning used in power electronics. It focuses on using Machine Learning based models to examine and train various voltage and current record units obtained by simulated malfunctioning transmission line model created with Matlab /Simulink. This yielded a dataset consisting of 12,001 fault data samples. Machine Learning models SVM, KNN and Decision Tree were trained on the same data and were employed to detect the faults. Next, the model was chosen for its strong fault detection capabilities and potential, which were evaluated based on accuracy, precision, and the F1- score. Effective fault detection techniques play a crucial role in optimizing power system control, reducing energy wastage, and ensuring top-notch performance. © 2023 IEEE.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

Knowledge Graphs Can be Learned with Just Intersection Features 41

Knowledge Graphs Can be Learned with Just Intersection Featu...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Le, Duy Zhong, Shaochen Liu, Zirui Xu, Shuai Chaudhary, Vipin Zhou, Kaixiong Xu, Zhaozhuo Department of Computer and Data Sciences Case Western Reserve University United States Department of Computer Science Rice University United States Department of Electrical and Computer Engineering North Carolina State University United States Department of Computer Science Stevens Institute of Technology United States

Knowledge Graphs (KGs) are potent frameworks for knowledge representation and reasoning. Nevertheless, KGs are inherently incomplete, leaving numerous uncharted relationships and facts awaiting discovery. Deep learning methodologies have proven effective in enhancing KG completion by framing it as a link prediction task, where the goal is to discern the validity of a triple comprising a head, relation, and tail. The significance of structural information in assessing the validity of a triple within a KG is well-established. However, quantifying this structural information poses a challenge. We need to pinpoint the metric that encapsulates the structural information of a triple and smoothly incorporate this metric into the link prediction learning process. In this study, we recognize the critical importance of the intersection among the k-hop neighborhoods of the head, relation, and tail when determining the validity of a triple. To address this, we introduce a novel randomized algorithm designed to efficiently generate intersection features for candidate triples. Our experimental results demonstrate that a straightforward fully-connected network leveraging these intersection features can surpass the performance of established KG embedding models and even outperform graph neural network baselines. Additionally, we highlight the substantial training time efficiency gains achieved by our network trained on intersection features. Copyright 2024 by the author(s)

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Knowledge‐based deep learning system for classifying Alzheimer's disease for multi‐task learning

引用

CAAI Transactions on Intelligence Technology 2024年第4期9卷 805-820页

作者： Amol Dattatray Dhaygude Gaurav Kumar Ameta Ihtiram Raza Khan Pavitar Parkash Singh Renato R.Maaliw III Natrayan Lakshmaiya Mohammad Shabaz Muhammad Attique Khan Hany S.Hussein Hammam Alshazly Department of Data Science University of WashingtonSeattleWashingtonUSA Department of Computer Science&Engineering Parul Institute of TechnologyParul UniversityVadodaraGujaratIndia Department of Computer Science Jamia HamdardDelhiIndia Department of Management Lovely Professional UniversityPhagwaraIndia 5 College of Engineering Southern Luzon State UniversityLucbanQuezonPhilippines Department of Mechanical Engineering Saveetha School of EngineeringSIMATSChennaiTamil NaduIndia Model Institute of Engineering and Technology JammuJ&KIndia Department of Computer Science HITEC UniversityTaxilaPakistan Department of Computer Science and Mathematics Lebanese American UniversityBeirutLebanon Electrical Engineering Department College of EngineeringKing Khalid UniversityAbhaSaudi Arabia Electrical Engineering Department Aswan UniversityAswanEgypt Faculty of Computers and Information South Valley UniversityQenaEgypt

Deep learning has recently become a viable approach for classifying Alzheimer's disease(AD)in medical ***,existing models struggle to efficiently extract features from medical images and may squander additional information resources for illness *** address these issues,a deep three‐dimensional convolutional neural network incorporating multi‐task learning and attention mechanisms is *** upgraded primary C3D network is utilised to create rougher low‐level feature *** introduces a new convolution block that focuses on the structural aspects of the magnetORCID:ic resonance imaging image and another block that extracts attention weights unique to certain pixel positions in the feature map and multiplies them with the feature map ***,several fully connected layers are used to achieve multi‐task learning,generating three outputs,including the primary classification *** other two outputs employ backpropagation during training to improve the primary classification *** findings show that the authors’proposed method outperforms current approaches for classifying AD,achieving enhanced classification accuracy and other in-dicators on the Alzheimer's disease Neuroimaging Initiative *** authors demonstrate promise for future disease classification studies.

关键词： classification deep learning

来源：评论

学校读者我要写书评

暂无评论

Building a portable parallel asynchronous PDE solver using Kokkos 31

Building a portable parallel asynchronous PDE solver using K...

引用

31st IEEE International Conference on High Performance Computing, data, and Analytics Workshops, HiPCW 2024

作者： Bhat, Ranjan Aditya, Konduri Department of Computer Science and Engineering Manipal Institute of Technology Manipal Academy of Higher Education Manipal India Department of Computational and Data Sciences Indian Institute of Science Bengaluru India

ISBN: (纸本)9798331509118

In this study, we outline the design and implementation of a portable massively parallel asynchronous solver for time-dependent partial differential equations (PDEs). The solver is implemented using Kokkos library for portability across different node architectures and is coupled with the communication-avoiding algorithm that relaxes the communication across nodes, thus improving the scalability. Asynchrony-tolerant finite difference schemes for spatial derivatives along with the low storage Runge-Kutta scheme for time integration are used to achieve high-order accuracy. The efficacy of the implementation is demonstrated using a mini-app that solves the three-dimensional diffusion problem. © 2024 IEEE

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Monkeypox Disease Classification from Skin Lesion Images using Deep Convolution Neural Network 3

Monkeypox Disease Classification from Skin Lesion Images usi...

引用

3rd International Conference on Intelligent Systems, Advanced Computing, and Communication, ISACC 2025

作者： Thangaraj, Rajasekaran Vadivel, Balasubramaniam Kumar, S. Manoj Sadesh, S. Karunakaran, P. Prakash, P. Nandha Engineering College Department of Computer Science and Engineering Erode India Sri Ramakrishna Institute of Technology Department of Computer Science and Engineering Coimbatore India KPR Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore India Velalar College of Engineering and Technology Department of Artificial Intelligence and Data Science Erode India Nandha Engineering College Department of Artificial Intelligence and Data Science Erode India Velalar College of Engineering and Technology Department of Information Technology Erode India

ISBN: (纸本)9798331523893

Recently monkeypox outbreak has raised concerns due to its increasing number of cases and diverse dermatological symptoms in 2024, which can complicate early diagnosis due to similarities with other viral infections such as measles and chickenpox. To enhance diagnostic accuracy, transfer learning models and artificial intelligence (AI) have been explored as effective tools. Pre-trained models such as VGG16, VGG19, ResNet50V2, and MobileNetV2 have been employed for monkeypox detection, each with distinct trade-offs in terms of computational efficiency and diagnostic precision. MobileNetV2 offers superior efficiency, but this comes at the cost of reduced accuracy. VGG models provide higher accuracy but require much more computational *** these models, DenseNet121 stands out by achieving 99% accuracy while requiring 37% less computational power, making it the model optimized choice for efficient and accurate monkeypox classification. © 2025 IEEE.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Successful Integration of IoT and Blockchain Technologies Using Several Machine Learning Algorithms 5

Successful Integration of IoT and Blockchain Technologies Us...

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Calarany, C. Indumathy, M. Senthilraja, P. Suganya, D. Gopi Vardhan, V. Rahul, Yelisetty Shanmukh Tagore Government Arts and Science College Department of Computer Science Puducherry India Rajiv Gandhi College of Engineering & Technology Department of Information Technology Kirumampakkam India K.S.Rangasamy College of Technology Department of Computer Science Tamil Nadu India Rajiv Gandhi College of Engineering & Technology Department of Computer Science Kirumampakkam India Data Science and Business Systems Srm Institute of Science and Technology Kattankulathur India

ISBN: (纸本)9798350383522

Internet of Things (IoT) produces massive amounts of data that need to be processed and saved securely. The strong features of Blockchain makes it as a best candidate for storing the data received from IoT sensors. However, there is a need of concern to take care of the challenges associated with both IoT and blockchain paradigms. Firstly, the enormous amount of data should be effortlessly handled by Blockchain network, without adding much complexity. Secondly, the heterogeneous nature of data that are received from various IoT Sensors should be stored within the blockchain. In this paper, a conceptual framework based on Multimodal Machine Learning (MML) algorithm is proposed as an interface between the IoT sensors and Blockchain networks. The MML algorithm is used to understand the different modalities of the data and provides a way to manage the heterogeneity in that data. The MML algorithms provides an intelligent data processing that allows for real-time data storage in the blockchain networks. The conceptual frame assumes that audio, video, and text are the three types of data as received from IoT. These inputs are processed in simplistic Recurrent neural network RNN that acts as MML and then passed to Blockchain networks for secure storage. Simulation of the above said conceptual framework is performed assuming all other relevant requirements of IoT, MML and Blockchain are taken into account with default parameters and values. The results obtained provide a promising note for future scope in this direction. © 2024 IEEE.

关键词： IoT MML RNN

来源：评论

学校读者我要写书评

暂无评论

SAMPLING MULTIMODAL DISTRIBUTIONS WITH THE VANILLA SCORE: BENEFITS OF data-BASED INITIALIZATION 12

SAMPLING MULTIMODAL DISTRIBUTIONS WITH THE VANILLA SCORE: BE...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Koehler, Frederic Vuong, Thuy-Duong Department of Statistics Data Science Institute University of Chicago ChicagoIL60637 United States Department of Computer Science Stanford University StanfordCA94305 United States

There is a long history, as well as a recent explosion of interest, in statistical and generative modeling approaches based on score functions - derivatives of the log-likelihood of a distribution. In seminal works, Hyvärinen proposed vanilla score matching as a way to learn distributions from data by computing an estimate of the score function of the underlying ground truth, and established connections between this method and established techniques like Contrastive Divergence and Pseudolikelihood estimation. It is by now well-known that vanilla score matching has significant difficulties learning multimodal distributions. Although there are various ways to overcome this difficulty, the following question has remained unanswered - is there a natural way to sample multimodal distributions using just the vanilla score? Inspired by a long line of related experimental works, we prove that the Langevin diffusion with early stopping, initialized at the empirical distribution, and run on a score function estimated from data successfully generates natural multimodal distributions (mixtures of log-concave distributions). © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dual Attention and Question Categorization-Based Visual Question Answering

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第1期4卷 81-91页

作者： Mishra, Aakansha Anand, Ashish Guha, Prithwijit Department of Computer Science & Engineering Guwahati781039 India Department of Electronics and Electrical Engineering Guwahati781039 India Mehta Family School of Data Science and Artificial Intelligence Indian Institute of Technology Guwahati Guwahati781039 India

Visual question answering (VQA) aims at predicting an answer to a natural language question associated with an image. This work focuses on two important issues pertaining to VQA, which is a complex multimodal AI task: First, the task of answer prediction in a large output answer space, and second, to obtain enriched representation through cross-modality interactions. This work aims to address these two issues by proposing a dual attention (DA) and question categorization (QC)-based visual question answering model (DAQC-VQA). DAQC-VQA has three main network modules: First, a novel dual attention mechanism that helps toward the objective of obtaining an enriched cross-domain representation of the two modalities;second, a question classifier subsystem for identifying input (natural language) question category. The second module of question categorizer helps in reducing the answer search space;and third, a subsystem for predicting answer depending on the question category. All component networks of DAQC-VQA are trained in an end-to-end manner with a joint loss function. The performance of DAQC-VQA is evaluated on two widely used VQA datasets, viz., TDIUC and VQA2.0. Experimental results demonstrate competitive performance of DAQC-VQA against the recent state-of-the-art VQA models. An ablation analysis indicates that the enriched representation obtained using the proposed dual-attention mechanism helps improve performance. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Emergency Vehicle Detection Using Deep ConvNet2D and computer Vision 2

Emergency Vehicle Detection Using Deep ConvNet2D and Compute...

引用

2nd International Conference on Emerging Trends in Information Technology and Engineering, ic-ETITE 2024

作者： Poongavanam, Elumalaivasan Prathik, A. Munirathinam, T. Kayalvizhi, V. Rajesh, R. Mahavishnu, C. Srm Institute of Science and Technology Department of Data Science and Business Systems Chennai Kattankulathur India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai India Sona College of Technology Department of Information Technology Salem India School of Computer Science and Engineering and Information Science Presidency University Bangalore India School of Computer Science and Engineering Vellore Institute of Technology Chennai India Shreenivasa Engineering College Department of Computer Science and Engineering Dharmapuri India

ISBN: (纸本)9798350328202

A surveillance system detects emergency vehicles stuck in traffic. This system helps manage traffic because the number of vehicles on the road has been increasing daily for years, causing congestion. This project implements Deep ConvNet2D (Convolutional Network 2D) and computer Vision emergency vehicle recognition. We propose a CNN-based real-time image processing model for emergency vehicle detection. The signal control unit can be set to terminate the round robin sequence when an emergency vehicle is detected. A CNN trained on Indian ambulance images solves the problem. Tensor Flow, a Python library, was used for training. Our method detects and classifies emergency cars well. Existing systems use ANN algorithm, which is inaccurate and inefficient. The system uses Deep ConvNet2D Algorithm. The proposed real-time system is accurate. The proposed system loads and executes faster than the existing system. The system is efficient, scalable, and enhanced for complex use cases. © 2024 IEEE.

关键词： Real time systems

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：