检索结果-内蒙古大学图书馆

Electrical, Computer, Communications and Mechatronics engineering (ICECCME), International Conference on

作者： Souheil Fenghour Daqing Chen Kun Guo Perry Xiao School of Engineering London South Bank University London UK Data Analytics Xi’an VANXUM Electronics Technology Co. Ltd. Xi’an China

Automating lip reading has attracted a lot of research attention in the last several years and there are a wide variety of applications where automated lip reading could be implemented, including forensic closed-circuit television footage or to assist those with language impairment. An obstacle for both professional lip-readers and automated lip-reading systems is not only the situation of different-sounding words being confused because they produce identical lip movements, but also that word with similar lip movements can easily be confused because they have sequences of visemes that are similar. This paper proposes a library and corpus called Visemes2Vec for learning the embeddings of viseme sequences as a contribution and is to the best of our knowledge the first attempt at proposing library for visualising words that have similar lip movements. Visemes2Vec is analogous to Word2Vec which groups together that are semantically similar in meaning or Chars2Vec which groups together words that share common characters.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Classification and Contrast of Supervised Machine Learning Algorithms

Classification and Contrast of Supervised Machine Learning A...

引用

2023 International Conference on Artificial Intelligence and Smart Communication, AISC 2023

作者： Raman, Ramakrishnan Shamim, Rejuwan Akram, Shaik Vaseem Thakur, Lalit Pillai, Biju G. Ponnusamy, R. Symbiosis Institute of Business Management Maharashtra Pune India Maharishi University of Information Technology Department of Computer Science and Engineering with Data Science Noida India Uttaranchal University Uttaranchal Institute of Technology India Parul University Department of Civil India Biib & Dean - Faculty of Management Department of It & Business Analytics India Chennai Institute of Technology Department of Computer Science & Engineering India

ISBN: (纸本)9798350322309

Supervised Classification (SML) is the pursuit of systems that reasoning from externally given instances to generate broad hypotheses, which subsequently generate predictions for future instances. One of the jobs performed by intelligent systems most commonly is supervised classification. Based on the data set, number of occurrences and variables in this study, the most efficient classification algorithm is selected. It is comprehensively described and contrasted with various supervised learning methods. Seven distinct machine learning algorithms were taken into consideration utilizing the Waikato Environment for data Analysis (WEDA) machine learning tool. For the identification process, the data set was used with 780 instances, eight independent variables (quality), and one dependent variable (variable). According to the data, SVM was the technique with the highest degree of precision and accuracy. Accordingly, the next accurate classification algorithms after SVM were determined to be Naive Bayes and Random Forest. The study demonstrates that precision (accuracy) and model construction time are two factors, whereas kappa statistics and mean error percentage (MAE) are two other factors. Therefore, controlled predictive machine learning requires precision, accuracy, and minimal error in ML algorithms. © 2023 IEEE.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Flying Ad Hoc Coverage Area Mobility Model for Post-Disaster Area based on Two Drones

Flying Ad Hoc Coverage Area Mobility Model for Post-Disaster...

引用

International Conference on Computing, Networking and Communications (ICNC)

作者： Intan Nabina Azmi Yusnani Mohd Yussoff Norashikin M Thamrin Fadhlan Hafizhelmi Kamaru Zaman Nooritawati Md Tahir School of Electrical Engineering College of Engineering Universiti Teknologi MARA Malaysia College of Engineering Universiti Teknologi MARA Malaysia Institute for Big Data Analytics and Artificial Intelligence (IBDAAI) Universiti Teknologi MARA Malaysia

In this study, the use of two drones, the DJI Phantom 3 Standard, is investigated and explored for usage during disasters. Parameters investigated include network coverage and optimum flying pattern to ensure battery usage is feasible during the post-disaster mission. Hence, OMNeT++ simulator version 5.2.1 with Inet 3.6.2 are used during the numerical analysis in determining the most optimum flying patterns using two drones. Results showed the square flying pattern as the most effective with a good coverage area. For the packet loss percentage analysis, the square pattern shows the highest packet loss at 30m, followed by Zigzag and Circular patterns. As for the Total End-to-End Delay analysis, the square pattern is the second best. From the simulation conducted, results showed that the camera’s specification and the height of the flying drone impacted in gaining a wider coverage area.

关键词： Simulation Packet loss Throughput Ad hoc networks Delays Safety Quality assessment

来源：评论

学校读者我要写书评

暂无评论

Design and Development of an Efficient Classification Model to Suggest Videos based on Artificial Intelligence Association 9

Design and Development of an Efficient Classification Model ...

引用

9th IEEE International Conference on Smart Structures and Systems, ICSSS 2023

作者： Thenmozhi, A. Karkuzhali, S. Vijayalakshmi, G. Malathi, P. Shobana, D. Priya, J. Lakshmi Kings Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai India R.M.K. Engineering College Department of General Engineering Tamil Nadu Chennai India Prince Shri Venkateshwara Padmavathy Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai India Simats Saveetha College of Liberal Arts and Sciences Department of Data Analytics Tamil Nadu Chennai India Rajalakshmi Engineering College Department of Electrical and Electronics Engineering Tamil Nadu Chennai India Chennai Institute of Technology Department of Electronics and Communication Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350384208

An excellent strategy to increase user pleasure and stickiness is to implement a video recommendation system. This system will give users with acceptable videos to pick from. This is why academics and video-sharing websites are so interested in it. Video recommendation systems now employ merged machine learning techniques. Some research has shown that combining Support Vector Machine (SVM) with a content-based recommendation algorithm or a Deep Neural Network with a collaborative filtering method can significantly increase the accuracy of these algorithms. Advances in Deep Learning have been substantial, keeping pace with the burgeoning field of Machine Learning. Since the random sample problem with training efficiency has been resolved, the dependability of multi-layer neural networks has been more apparent, which has piqued the attention of academics in neural network research. Our article proposed AIDCL, an AI-based Deep Classification Logic method, a new way to provide video recommendations. This allows us to compare the suggested scheme's performance in areas such as function approximation and feature extraction to that of the standard deep learning model, Deep Neural Network (DNN). Our goal is to find out how well the proposed scheme works. It would appear that the suggested method, when used to provide video recommendations, will lead to improved accuracy. In this study, we provide a video recommendation engine that demonstrates the efficacy of our algorithm through experiments by integrating a screening algorithm with artificial intelligence logic. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Efficiency ordering of stochastic gradient descent 22

Efficiency ordering of stochastic gradient descent

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Jie Hu Vishwaraj Doshi Do Young Eun Department of Electrical and Computer Engineering North Carolina State University Data Science and Advanced Analytics IQVIA

ISBN: (纸本)9781713871088

We consider the stochastic gradient descent (SGD) algorithm driven by a general stochastic sequence, including i.i.d noise and random walk on an arbitrary graph, among others; and analyze it in the asymptotic sense. Specifically, we employ the notion of 'efficiency ordering', a well-analyzed tool for comparing the performance of Markov Chain Monte Carlo (MCMC) samplers, for SGD algorithms in the form of Loewner ordering of covariance matrices associated with the scaled iterate errors in the long term. Using this ordering, we show that input sequences that are more efficient for MCMC sampling also lead to smaller covariance of the errors for SGD algorithms in the limit. This also suggests that an arbitrarily weighted MSE of SGD iterates in the limit becomes smaller when driven by more efficient chains. Our finding is of particular interest in applications such as decentralized optimization and swarm learning, where SGD is implemented in a random walk fashion on the underlying communication graph for cost issues and/or data privacy. We demonstrate how certain non-Markovian processes, for which typical mixingtime based non-asymptotic bounds are intractable, can outperform their Markovian counterparts in the sense of efficiency ordering for SGD. We show the utility of our method by applying it to gradient descent with shuffling and mini-batch gradient descent, reaffirming key results from existing literature under a unified framework. Empirically, we also observe efficiency ordering for variants of SGD such as accelerated SGD and Adam, open up the possibility of extending our notion of efficiency ordering to a broader family of stochastic optimization algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

data-driven Energy Consumption Modelling for Electric Micromobility using an Open dataset

Data-driven Energy Consumption Modelling for Electric Microm...

引用

IEEE Transportation Electrification Conference and Expo (ITEC)

作者： Yue Ding Sen Yan Maqsood Hussain Shah Hongyuan Fang Ji Li Mingming Liu SFI Centre for Research Training in Machine Learning (ML-Labs) Dublin City University SFI Insight Centre for Data Analytics and the School of Electronic Engineering Dublin City University Dublin Ireland Department of Mechanical Engineering University of Birmingham

ISBN: (数字)9798350317664

ISBN: (纸本)9798350317671

The escalating challenges of traffic congestion and environmental degradation underscore the critical importance of embracing E-Mobility solutions in urban spaces. In particular, micro E-Mobility tools such as E-scooters and E-bikes, play a pivotal role in this transition, offering sustainable alternatives for urban commuters. However, the energy consumption patterns for these tools are a critical aspect that impacts their effectiveness in real-world scenarios and is essential for trip planning and boosting user confidence in using these. To this effect, recent studies have utilised physical models customised for specific mobility tools and conditions, but these models struggle with generalization and effectiveness in real-world scenarios due to a notable absence of open datasets for thorough model evaluation and verification. To fill this gap, our work presents an open dataset, collected in Dublin, Ireland, specifically designed for energy modelling research related to E-Scooters and E-Bikes. Furthermore, we provide a comprehensive analysis of energy consumption modelling based on the dataset using a set of representative machine learning algorithms and compare their performance against the contemporary mathematical models as a baseline. Our results demonstrate a notable advantage for data-driven models in comparison to the corresponding mathematical models for estimating energy consumption. Specifically, data-driven models outperform physical models in accuracy by up to 83.83% for E-Bikes and 82.16% for E-Scooters based on an in-depth analysis of the dataset under certain assumptions.

关键词： Energy consumption Analytical models Machine learning algorithms Transportation Environmental degradation Electrification Boosting

来源：评论

学校读者我要写书评

暂无评论

Predictive Insight of Global Warming-A Sustainable Control System

Predictive Insight of Global Warming-A Sustainable Control S...

引用

International Conference on Computing Communication Control and Automation (ICCUBEA)

作者： Soumit Roy Hafizullah Mahmudi Rik Das Jaya H. Dewan Sudeep D. Thepade Analytics Presales and Solution PracticeLead Jade Global Chicago USA Data Management and Analytics Kamyab ITS Kabul Afghanistan Association for Computing Machinery Ranchi India Department of Information Technology Pimpri Chinchwad College of Engineering Pune India Computer Engineering Department Pimpri Chinchwad College of Engineering Pune India

Global warming is one of the major issues for decades. Implementation of integrated solution to get sustainable control system has significant challenges. Acceptance of the key precautions and maintenance of sustainability became a bottleneck. The consequence of human social activities increases the consumption of fossil fuels as power resources which indirectly increased the concentration of greenhouse gases and water vapor, in the environment. This causes the earth's average surface temperature to increase. Water vapor is responsible for two-thirds of this issue; however, C02 is proven to be the key factor of global warming. The global temperature could have increased to 3.8 o C in case C02 concentration was doubled. The trend and association between rising temperatures and C02 emissions are shown in this work, along with an explanation of the many methods behind ideal mitigation. One of the goals of this research is to identify the issue area and integrate the climatic data. This will assist in obtaining a dependable control system capable of addressing global warming concerns. This paper outlines how data engineering and analytics may be used to regulate global warming and provides an architecture for the Green Warming Model (GWD). Therefore, the primary contribution of this study effort is environment preservation using data engineering and machine learning (ML).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development and Innovations in Wearable Sensors and Devices for Human Machine Interaction in Virtual Platform 2

Development and Innovations in Wearable Sensors and Devices ...

引用

2nd International Conference on Augmented Intelligence and Sustainable Systems, ICAISS 2023

作者： Singh, Rahul Javali, Anand Priya, S. Vardhana Naidu, B Vishnu Gautam, Gaurav Presidium Gurgaon Sec-57 Pgt Physics Department of Physics Haryana 122103 India Conduent Technology Services - Usa Data Analytics and Innovations Dept FriscoTX75035 United States Nehru Institute of Engineering and Technology Department of Computer Science and Engineering Tamilnadu Coimbatore India Mohan Babu University Department of Mechanical Engineering Andhra Pradesh Tirupati India Graphic Era Hill University Department of Physics Dehradun India

ISBN: (纸本)9798350325799

Recent advances in deep learning algorithms and wearable sensor technology have opened the door for creative methods to improve human-machine interaction (HMI) on virtual platforms. The use of wearable sensors and devices in conjunction with hybrid deep learning algorithms is presented in detail in this abstract. Real-time physiological and contextual data from users can be collected with the help of wearable sensors integrated into devices like smartwatches, augmented reality goggles, and biometric monitoring equipment. This information can then be used to improve augmented reality (AR) and virtual reality (VR) systems, enabling more effortless and intuitive user interactions. A seamless connection between the user and the virtual platform is made possible by the combination of sensor data and deep learning models, which enables the creation of complex algorithms that can decipher user intent, gestures, emotions, and physical actions. These hybrid models may efficiently learn complicated patterns from wearable sensor data by combining standard feature extraction techniques with convolutional neural networks (CNNs), recurrent neural networks (RNNs), and generative adversarial networks (GANs). Wearable sensors and hybrid deep learning techniques have numerous and significant applications in virtual platforms. They make it possible for, among other things, real-time activity recognition for individualized virtual fitness coaching, emotion recognition for adaptive and sympathetic virtual characters, and gesture recognition for intuitive control of virtual objects. In summary, combining wearable sensors and devices with hybrid deep learning algorithms has enormous potential to change how humans and machines interact on virtual platforms. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Medical Image Noise Controller (MINC): Boosting U-NET Based Networks for Superior Segmentation

Medical Image Noise Controller (MINC): Boosting U-NET Based ...

引用

Integrated Intelligence and Communication Systems (ICIICS), International Conference on

作者： Anand Swaroop Srivastava Rishi Prakash Ved Prakash Dubey Sumit Tripathi Department of Electronics and Communication Engineering Graphic Era Deemed to be University Dehradun India Department of Electronics and Communication Engineering Graphic Era Hill University Dehradun India Big Data Analytics Goa Institute of Management Poriem Sattari India

ISBN: (数字)9798331504960

ISBN: (纸本)9798331504977

Segmentation of medical images is very crucial for clinical diagnosis, yet it faces challenges due to factors like noise, complex structures, and blurred boundaries. Rician noise in MRI images makes the problem even more challenging, thus degrading the segmentation accuracy. In this study, Medical Image Noise Controller (MINC) is proposed - a novel architecture to enhance the effectiveness of the U-NET based segmentation networks. The integration of MINC with U-NET, Swin-UNET, and UNETR brings significant improvements in critical segmentation metrics like IoU, Dice coefficient, and MCC. MINC experimental results shows an improvement in IoU from 2.55% to 8.49% on all three networks when tested under noisy conditions. MINC consistently demonstrates its effectiveness in enhancing performance across diverse medical image datasets, even under noisy conditions. The results suggest that MINC is a reliable approach for improving medical image segmentation, with potential for broader application in clinical settings characterized by noisy data.

关键词： Image segmentation Noise Rician channels Robustness Noise robustness Noise measurement Medical diagnostic imaging Standards Optimization Noise level

来源：评论

学校读者我要写书评

暂无评论

Artificial Neural Network Modeling for Predicting Thermal Conductivity of EG/Water-Based CNC Nanofluid for Engine Cooling Using Different Activation Functions

引用

Frontiers in Heat and Mass Transfer 2024年第2期22卷 537-556页

作者： Munirul Hasan Mustafizur Rahman Mohammad Saiful Islam Wong Hung Chan Yasser M.Alginahi Muhammad Nomani Kabir Suraya Abu Bakar Devarajan Ramasamy Faculty of Computing Universiti Malaysia Pahang Al-Sultan AbdullahPekanPahang26600Malaysia Faculty of Mechanical and Automotive Engineering Technology Universiti Malaysia Pahang Al-Sultan AbdullahPekanPahang26600Malaysia Department of Management and Information Technology St.Francis College179 Livingston StBrooklynNY11201USA Dell Technologies Data Analyticsand AutomationBukit TengahBukit Mertajam14000Malaysia Department of Computer Science Adrian CollegeAdrianMIUSA Department of Computer Science&Engineering United International University BangladeshUnited CityMadani AvenueBaddaDhaka1212Bangladesh

A vehicle engine cooling system is of utmost importance to ensure that the engine operates in a safe temperature *** most radiators that are used to cool an engine,water serves as a cooling *** performance of a radiator in terms of heat transmission is significantly influenced by the incorporation of nanoparticles into the cooling *** and uniformity of nanoparticle distribution are the two major factors for the practical use of *** shape and size of nanoparticles also have a great impact on the performance of heat *** researchers are investigating the impact of nanoparticles on heat *** study aims to develop an artificial neural network(ANN)model for predicting the thermal conductivity of an ethylene glycol(EG)/waterbased crystalline nanocellulose(CNC)nanofluid for cooling internal combustion *** implementation of an artificial neural network considering different activation functions in the hidden layer is made to find the bestmodel for the cooling of an engine using the *** of the model with different activation functions in artificial neural networks are analyzed for different nanofluid concentrations and *** artificial neural networks,Levenberg–Marquardt is an optimization approach used with activation functions,including Tansig and Logsig functions in the training *** findings of each training,testing,and validation phase are presented to demonstrate the network that provides the highest level of *** best result was obtained with Tansig,which has a correlation of 0.99903 and an error of 3.7959×10^(–8).It has also been noticed that the Logsig function can also be a good model due to its correlation of 0.99890 and an error of 4.9218×10^(–8).Thus ourANNwith Tansig and Logsig functions demonstrates a high correlation between the actual output and the predicted output.

关键词： Artificial neural network activation function thermal conductivity nanocellulose

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：