检索结果-内蒙古大学图书馆

Computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Hazem Alnajjar Nadia Al-Rousan Syed Sahal Nazli Alhady Syed Hassan Junita Mohamad-Saleh Department of Computer Science College of Information Technology University of Petra Amman Jordan Department of computer engineering College of Engineering AlBalqa Applied University Salt Jordan Department of Computer Engineering Faculty of Electrical Engineering and Information Systems German Jordanian University Amman Jordan Colleage of Engineering and Architecture School of Electrical & Electronic Engineering Engineering Branch Campus Universiti Sains Malaysia Malaysia

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

Nowadays, the grid computing environment faces many difficulties executing new jobs, especially jobs requiring large resource requirements and long execution times. This motivates researchers and scholars to find cheap and fast methods to improve the efficiency of grid environments. One of the cheap and fast methods is to implement job scheduling algorithms based on cheap and fast techniques. This paper proposes a new job ranking backfilling algorithm based on the job's weight and back propagation neural network. To define the weight of the job, first, the proposed model will use a clustering algorithm to cluster the job's dataset into groups, and then the groups will be ranked using an experimental ranking equation. A discrete event simulator is used to validate the proposed algorithm's capability and robustness. The average results revealed that the new algorithm outperforms previous algorithms. The improvement of the studied metrics is between 1.19 and 6.30, respectively. The results proved that the proposed model is efficient and can be used with low overhead in a real environment.

关键词： Backpropagation Measurement Scheduling algorithms Computational modeling Neural networks Clustering algorithms Grid computing Mathematical models Robustness Faces

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Fine-Tuning For Low-resource Englishbased Creole with Pre-Trained LLMs

Two-Stage Fine-Tuning For Low-resource Englishbased Creole w...

引用

computer science and Data engineering (CSDE), IEEE Asia-Pacific Conference on

作者： Shu Hui Amanda Tan Eint Sandi Aung Hayato YAMANA Department of Computer Science and Communications Engineering Waseda University Tokyo Japan Department of Computer Science and Communications Engineering Waseda University Tokyo Japan Faculty of Science and Engineering Waseda University Tokyo Japan

Sentiment analysis adopts natural language processing (NLP) techniques to determine the emotional tone of the text. Sentiment analysis research has predominantly been conducted on commonly spoken languages, such as English and Mandarin Chinese. However, less widely spoken languages, such as Englishbased Creoles, have received limited attention due to the need for large-scale labeled datasets. English-based Creoles are derived from English, resulting in many similarities with English. However, English-based Creoles differ from English in some aspects, making the Creole unintelligible to other English speakers. In sentiment analysis research conducted on Singapore English-based Creole (Singlish), most existing research does not leverage the capabilities of large-language models, such as pretrained BERT. To our knowledge, only Gotera et al.'s work relates to a large-language model; however, their contribution is creating a new pre-trained model for Singlish. However, creating a new pre-trained model is computationally expensive, and pre-training a less widely spoken language will result in ineffective because of the small dataset. Hence, we propose a new two-stage fine-tuning framework for pre-trained models, targeting a low-resource English-based Creole, Singlish. Our proposed framework initially clusters the dataset into two based on each data point's percentage of English words. Then, two-stage fine-tuning is performed by transferring the pre-trained BERT model onto the clustered dataset with the higher English percentage in the first stage. The model is further transferred onto the clustered dataset with the lower English percentage in the second stage. Our proposed framework outperforms the traditional fine-tuning framework, achieving a weighted F1 score of 0.8344 for sentiment analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

COVID-19 assessment using HMM cough recognition system

引用

International Journal of Information Technology (Singapore) 2023年第1期15卷 193-201页

作者： Hamidi, Mohamed Zealouk, Ouissam Satori, Hassan Laaidi, Naouar Salek, Amine Advanced Systems Engineering Laboratory ENSA-UIT Kenitra Morocco Multimedia and Arts Department FLLA UIT Kenitra Morocco LISAC Department of Mathematics and Computer Science FSDM USMBA Fez Morocco Faculty of Medicine and Pharmacy UMP Oujda Morocco

This paper is a part of our contributions to research on the ongoing COVID-19 pandemic around the world. This research aims to use Hidden Markov Model (HMM) based automatic speech recognition system to analyze the cough signal and determine whether the signal belongs to a sick or healthy speaker. We built a configurable model by using HMMs, Gaussian Mixture Models (GMMs), Mel frequency spectral coefficients (MFCCs) and a cough corpus collected from healthy and sick voluntary speakers. Our proposed method is able to classify dry cough with sensitivity from 85.86% to 91.57%, differentiate the dry cough, and cough COVID-19 symptom with specificity from 5 to 10%. The obtained results are very encouraging to enrich our corpus with more data and increase the performance of our diagnostic system. © 2022, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： ASR system COVID-19 Diagnostic GMM HMMs

来源：评论

学校读者我要写书评

暂无评论

An IoT Machine Learning Model-Based Real-Time Diagnostic and Monitoring System 4th

An IoT Machine Learning Model-Based Real-Time Diagnostic and...

引用

4th International Conference on Machine Intelligence and Signal Processing, MISP 2022

作者： Awotunde, Joseph Bamidele Misra, Sanjay Ajagbe, Sunday Adeola Ayo, Femi Emmanuel Gurjar, Ramchandra Department of Computer Science Faculty of Information and Communication Sciences University of Ilorin Ilorin240003 Nigeria Department of Computer Science and Communication Ostfold University College Halden Norway Department of Computer Engineering Ladoke Akintola University of Technology Ogbomosho Nigeria Department of Mathematical Sciences Olabisi Onabanjo University Ago-Iwoye Ogun State Nigeria Shri Govindram Seksaria Institute of Technology and Science Indore India

ISBN: (纸本)9789819900848

Internet of things (IoT) and machine learning (ML) have recently changed the paradigm in the area of applications in health-care systems with significant results. The ML-based models enabled with IoT-based systems have greatly expedited the medical diagnosis, real-time monitoring, and treatment in the health-care system, thus reducing the burden of health-care processes and the cost of taking care of patients by caregivers and physicians. Therefore, in this paper, a framework is proposed based on an ML model-enabled IoT-based system for real-time diagnosis of various diseases using data collected from wearable devices and sensors attached within the body of patients. The captured data are stored using an integrated cloud database for further preprocessing and processes using ML-based models. ML model was used to select the most relevant features from the cloud database and thus use the preprocessed data for the diagnosis of various diseases. The findings from the study show that the XGBoost performs reliably better when compared with other existing ML-based models with an accuracy of 95.7%, recall of 95.9%, precision of 96.0%, F1-score of 94.8%, and Receiver Operating Characteristic Curve (ROC) of 94.3%. The results proposed a framework to show that the system can be widely used to diagnose various diseases and can be used in remote areas for better monitoring of patients. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Towards experimental insight into magnetic flux distribution within the air gap of permanent magnet synchronous drive

Towards experimental insight into magnetic flux distribution...

引用

International Conference on Methods and Models in Automation and Robotics (MMAR)

作者： Hubert Milanowski Adam Krzysztof Piłat Faculty of Electrical Engineering Automatics Computer Science and Biomedical Engineering Department of Automatic Control and Robotics AGH University of Krakow Krakow Poland

ISBN: (数字)9798350362343

ISBN: (纸本)9798350362350

This report explores the experimental identification of magnetic flux density within the motor air gap, focusing on the development of a robot-based approach to automate the scanning procedure. Emphasis is placed on analyzing the distribution of magnetic flux within the motor’s spatial air gap, as well as the amplification of harmonics resulting from changes in air gap orientation. Drawing upon experimental findings, a model is proposed to illustrate the three-dimensional distribution of magnetic flux within the gap.

关键词： Solid modeling Magnetic flux density Automation Atmospheric modeling Air gaps Rotors Drives

来源：评论

学校读者我要写书评

暂无评论

Optimised Mission Planning for Heterogeneous Uncrewed Vehicle Teams

引用

IEEE Access 2024年 1-1页

作者： Hajkarim, Sina M.H. Sujit, P.B. Menon, Prathyush P. Department of Engineering Faculty of Environment Science and Economy University of Exeter Exeter United Kingdom Department of Electrical Engineering and Computer Science Indian Institute of Science Education and Research Bhopal Bhopal Bypass Road Bhopal Madhya Pradesh India

In this paper, we present a new mission planning optimisation method for coverage missions involving Uncrewed Aerial Systems (UAS) and Ground Vehicles (GV) to minimize the mission planning time and the UAS and GV route length. Optimal planning of paths for the UAS and GV using the Mixed Integer Linear Program (MILP), often struggles with computational inefficiency and limited scalability in scenarios with a growing number of waypoints and vehicles. To overcome the MILP computational issues, we present a reinforcement learning technique based on rollout policy optimisation called as Multi-Agent Rollout Policy Optimisation (MARPO). Through simulations, we showcase MARPO’s ability to match the precision of conventional MILP formulation in small instances and excel in scalability and computational efficiency in larger cases. Additionally, MARPO is compared with a heuristic method, Multi-Agent Greedy Path-Finding Algorithm (MAGPA), and the superior performance of MARPO in terms of total path length and computational efficiency is demonstrated. Several simulations are presented to showcase the advantages of MARPO. In simulations with 1 UAS and 1 UGV, MARPO achieved path lengths up to 1.56% longer than MILP’s optimum for 9 to 25 waypoints, while significantly reducing computation time by up to 99.88%. In larger scenarios of 36 and 49 waypoints, where MILP was infeasible, MARPO provided convincing solutions with greatly enhanced computational efficiency, demonstrating its robust scalability and effectiveness. Authors

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Neural Network Controlled Grid Synchronization of Single-Phase Inverter Using SOGI-PLL for Efficient Solar Power Integration

Neural Network Controlled Grid Synchronization of Single-Pha...

引用

International Conference on System Modeling & Advancement in Research Trends (SMART)

作者： Vinayak Mishra Narendra Pal Singh Umesh Kumar Singh Akshit Jain Doshi Saumya Rakesh Kumar Electrical Engineering Department Faculty of Engineering Teerthanker Mahaveer University Moradabad Uttar Pradesh India Department of Computer Science and Engineering Invertis University Bareilly Uttar Pradesh India

ISBN: (数字)9798350380583

ISBN: (纸本)9798350380590

This paper presents a comprehensive Artificial Neural Network (ANN)-based control scheme for single-phase grid-connected inverters, emphasizing efficient and accurate synchronization. Using Echo State Networks (ESN) within the ANN framework, this method generates a precise modulating wave for Pulse Width Modulation (PWM) control. Combined with a Second order generalised algorithms (SOGI) Phase-Locked Loop (PLL) system, the approach effectively aligns the inverter's output with grid phase and frequency, achieving low Total Harmonic Distortion (THD). Simulations in MATLAB/Simulink verify the superior performance of this method over traditional Proportional Integral (PI) and PR control systems in terms of steady-state and transient performance.

关键词： Total harmonic distortion Renewable energy sources Artificial neural networks Pulse width modulation Inverters Steady-state Smart grids Synchronization Phase locked loops Transient analysis

来源：评论

学校读者我要写书评

暂无评论

Signet Ring Cell Detection from Histological Images Using Deep Learning

引用

computers, Materials & Continua 2022年第9期72卷 5985-5997页

作者： Muhammad Faheem Saleem Syed Muhammad Adnan Shah Tahira Nazir Awais Mehmood Marriam Nawaz Muhammad Attique Khan Seifedine Kadry Arnab Majumdar Orawit Thinnukool Department of Computer Science UETTaxila47050Pakistan Department of Computer Science HITEC University TaxilaTaxilaPakistan Faculty of Applied Computing and Technology Noroff University CollegeKristiansandNorway Department of Civil Engineering Imperial College LondonLondon SW72AZUK College of Arts Mediaand TechnologyChiang Mai UniversityChiang Mai 50200Thailand

Signet Ring Cell(SRC)Carcinoma is among the dangerous types of cancers,and has a major contribution towards the death ratio caused by cancerous *** and diagnosis of SRC carcinoma at earlier stages is a challenging,laborious,and costly *** detection of SRCs in a patient’s body through medical imaging by incorporating computing technologies is a hot topic of *** the presented framework,we propose a novel approach that performs the identification and segmentation of SRCs in the histological images by using a deep learning(DL)technique named Mask Region-based Convolutional Neural Network(Mask-RCNN).In the first step,the input image is fed to Resnet-101 for feature *** extracted feature maps are conveyed to Region Proposal Network(RPN)for the generation of the region of interest(RoI)proposals as well as they are directly conveyed to ***,RoIAlign combines the feature maps with RoI proposals and generates segmentation masks by using a fully connected(FC)network and performs classification along with Bounding Box(bb)generation by using FC *** annotations are developed from ground truth(GT)images to perform experimentation on our developed *** introduced approach achieves accurate SRC detection with the precision and recall values of 0.901 and 0.897 respectively which can be utilized in clinical *** aim to release the employed database soon to assist the improvement in the SRC recognition research area.

关键词： Mask RCNN deep learning SRC segmentation

来源：评论

学校读者我要写书评

暂无评论

REdiSplats: Ray Tracing for Editable Gaussian Splatting

arXiv

引用

arXiv 2025年

作者： Byrski, Krzysztof Wilczyński, Grzegorz Smolak-Dyżewska, Weronika Borycki, Piotr Baran, Dawid Tadeja, Slawomir Spurek, Przemyslaw Faculty of Mathematics and Computer Science Jagiellonian University Poland Department of Engineering University of Cambridge Cambridge United Kingdom

Gaussian Splatting (GS) has become one of the most important neural rendering algorithms. GS represents 3D scenes using Gaussian components with trainable color and opacity. This representation achieves high-quality renderings with fast inference. Regrettably, it is challenging to integrate such a solution with varying light conditions, including shadows and light reflections, manual adjustments, and a physical engine. Recently, a few approaches have appeared that incorporate ray-tracing or mesh primitives into GS to address some of these caveats. However, no such solution can simultaneously solve all the existing limitations of the classical GS. Consequently, we introduce REdiSplats, which employs ray tracing and a mesh-based representation of flat 3D Gaussians. In practice, we model the scene using flat Gaussian distributions parameterized by the mesh. We can leverage fast ray tracing and control Gaussian modification by adjusting the mesh vertices. Moreover, REdiSplats allows modeling of light conditions, manual adjustments, and physical simulation. Furthermore, we can render our models using 3D tools such as Blender or Nvdiffrast, which opens the possibility of integrating them with all existing 3D graphics techniques dedicated to mesh representations. The code is available at https: //***/KByrski/REdiSplats. © 2025, CC BY.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Ameliorating Semantic Search Through Advanced AI Techniques 3

Ameliorating Semantic Search Through Advanced AI Techniques

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Ravikumar, V. Dhabliya, Dharmesh Mathur, Mala Das, Sidhant Kumar, Ritesh Rao, Srikrishna B Prince Shri Venkateshwara Padmavathy Engineering College Department of Computer Science and Engineering Chennai127 India Vishwakarma Institute of Information Technology Department of Information Technology Maharashtra Pune India Vivekananda Global University Department of Civil Engineering Jaipur India Chitkara University Institute of Engineering and Technology Chitkara University Centre of Interdisciplinary Research in Business and Technology Punjab India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Faculty of Engineering and Technology Department of Mechanical Engineering Karnataka Ramnagar562112 India

ISBN: (纸本)9798350319125

Recent synthetic intelligence (AI) advances have enabled some thrilling semantic search applications. In particular, the development of advanced AI strategies, which include natural language processing (NLP) and deep learning, has enabled the creation of search engines like Google and Yahoo that leverage semantic data to enhance the accuracy of the quest outcomes. No longer simplest does this enable customers to find applicable statistics speedy. However, it additionally facilitates ameliorating any semantic mistakes resulting from typos, incorrect syntax, or wrong interpretations of the question. In this paper, we present a survey of new advances in semantic seek powered by AI and techniques for query expansion, generating question-precise training statistics, and semi-supervised gaining knowledge. We additionally talk about the results for the future of semantic search and gift some case research on the successful implementation of semantic seek with AI structures. Our assessment concludes with a dialogue of the open challenges and potential research avenues. © 2023 IEEE.

关键词： development discussion implementation implications leverage

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：