检索结果-内蒙古大学图书馆

12th International Electrical engineering Congress, iEECON 2024

作者： Rakprayoon, Panjawee Ounsiri, Akechai Chongyoa, Ratchanon Bangkok University Faculty Of Engineering Dept. Ai Engineering And Data Science Pathum Thani Thailand Dna Robotics And Automation System Company Limited Pathum Thani Thailand Bangkok University Faculty Of Engineering Dept. Computer And Robotics Engineering Pathum Thani Thailand

ISBN: (纸本)9798350383591

For an AI tic-tac-toe manipulator application, a real-time vision-based approach is proposed. The technique employs the RealSense camera to capture color and depth images. Combining object detection and image processing techniques to identify X's and O's positions on the game board. However, we recognize that errors can occur during object movement when using only 2D images. To solve this problem, a calibration method between RealSense and the manipulator based on the point-to-plane ICP algorithm is presented. This method provides the 3D object position in the robot coordinate, resulting in increasing the accuracy from 86.25% to 97.25%. Our experiment shows that this technique is highly effective and can accurately identify position objects. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Deep Learning Model for Crop Yield Prediction 2

An Adaptive Deep Learning Model for Crop Yield Prediction

引用

2nd International Conference on computer, Communication and Control, IC4 2024

作者： Gadupudi, Ashwin Rani, Rudra Yamini Jayaram, B. Sharma, Nipun Deshmukh, Jotiram Krishna Reddy, Pundru Chandra Shaker California State University Computer Science Fresno United States Vnr Vignana Jyothi Institute of Engineering and Technology Information Technology Hyderabad India Rmk Engineering College Computer Science and Business System Tamil Nadu Kavaraipettai India Presidency University Electronics and Communication Engineering Karnataka Bangalore India Bharati Vidyapeeth College of Engineering Instrumentation Engineering Navi Mumbai India Sr University School of Computer Science and Artificial Intelligence Telangana Warangal506371 India

ISBN: (纸本)9798350387933

Agriculture is the study and practice of raising plants and animals for human consumption. Approximately 60.45% of India's land is devoted to farming, making it the country's second largest economic sector. Agriculture and the related agro-industrial sector are crucial to India's economy. Soil components (such as nitrogen-phosphorus &potassium), crop rotation, soil-moisture, air and soil-temperatures, rainfall, and other environmental factors all play important roles in successful farming. One piece of current evidence in this area is a technique that utilizes machine-learning (ML) strategies like Random-Forest (RF), Decision-Tree (DT), and ANN to pick the best crop. In this study, we employ deep learning approaches to improve the suggested model, and together with crop prediction, we obtain clear information regarding the quantities of soil attributes requisite, along with their individual costs. It's more precise than the current model. By analyzing the data provided, it aids farmers in making informed business decisions. Predicting a proper yield requires thinking about the land's climate and soil. The goal is to introduce a Python-based system that makes use of strategic thinking to anticipate the most productive harvest under specific conditions while keeping costs to a minimum. While LSTM &RNN are employed as deep-learning((DL)-strategies in this work, SVM is used as the ML-strategy. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Indoor Place Recognition Using Multi-modal Range Information 7

A Comparative Study of Indoor Place Recognition Using Multi-...

引用

7th International Conference on computer Science and Artificial Intelligence, CSAI 2023

作者： Yang, Chenrushi Mei, Ruidong Cheng, Hui School of System Science and Engineering Sun Yat-sen University Guangdong Guangzhou China School of Computer Science and Engineering Sun Yat-sen University Guangdong Guangzhou China

ISBN: (纸本)9798400708688

This paper presents a discussion on the challenges encountered in localizing mobile robots in large-scale indoor environments, particularly the issues of kidnapping and localization failure, which are prevalent in factories and malls. Visual place recognition (VPR) methods are often used to alleviate these issues;however, in large-scale indoor settings, obtaining ground truth through precise 3D reconstruction using cameras can be time-consuming and challenging due to their limited field of view and varying illumination conditions. LiDAR is more suitable for large-scale mapping due to its wider field of view and its robustness to environmental changes and sensor drifts;however, the cost of LiDAR systems can be prohibitive for indoor applications. RGB-D cameras are lighter and less expensive, making them more suitable for a wide range of applications on multi-robot platforms. Therefore, it is important to investigate the use of RGB-D camera data for place recognition, especially in indoor contexts where only LiDAR maps can be used for place recognition. This paper presents a rigorous comparative study based on existing techniques to identify the key factors in addressing indoor place recognition challenges. © 2023 ACM.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

LOPO: An Out-of-order Layer Pulling Orchestration Strategy for Fast Microservice Startup 42

LOPO: An Out-of-order Layer Pulling Orchestration Strategy f...

引用

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Gu, Lin Huang, Junhao Huang, Shaoxing Zeng, Deze Li, Bo Jin, Hai Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Wuhan China China University of Geosciences School of Computer Science Wuhan China Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong

ISBN: (纸本)9798350334142

Container based microservices have been widely applied to promote the cloud elasticity. The mainstream Docker containers are structured in layers, which are organized in stack with bottom-up dependency. To start a microservice, the required layers are pulled from a remote registry and stored on its host server, following the layer dependency order. This incurs long microservice startup time and hinders the performance efficiency. In this paper, we discover that, for the first time, the layer pulling order can be adjusted to accelerate the microservice startup. Specifically, we address the problem on microservice layer pulling orchestration for startup time minimization and prove it as NP-hard. We propose a Longest-chain based Out-of-order layer Pulling Orchestration (LOPO) strategy with low computational complexity and guaranteed approximation ratio. Through extensive real-world trace driven experiments, we verify the efficiency of our LOPO and demonstrate that it reduces the microservice startup time by 22.71% on average in comparison with state-of-the-art solutions. © 2023 IEEE.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Multi-Speaker Diarization using Long-Short Term Memory Network 3

Multi-Speaker Diarization using Long-Short Term Memory Netwo...

引用

3rd IEEE International Conference on Artificial Intelligence, ICAI 2023

作者： Aafaq, Nayyer Qamar, Usama Khan, Sohaib Ali Khan, Zeashan Hameed Department of Avionics Engineering College of Aeronautical Engineering National University of Sciences and Technology NUST Islamabad Pakistan N.E.D UET Department of Computer & Information System Engineering Karachi Pakistan

ISBN: (纸本)9798350322125

The task of multi-speaker diarization involves de-tection of number of speakers and segregate the audio seg-ments corresponding to each speaker. Despite the tremendous advancements in deep learning, the problem of multi-speaker diarization is still far from achieving acceptable performance. In this work, we address the problem by first getting the timestamps employing voice activity detection and sliding window techniques. We further extract the Mel-Spectrograms / Mel-frequency Cepstral Coefficients (MFCC). We then train a Long Short-Term Memory (LSTM) network to get the audio embed dings named d-vectors. Subsequently, we employ K-Means and Spectral clustering techniques to segment all the speakers in the given audio file. We evaluate the proposed framework on publically available VoxConverse dataset and report results comparing with similar benchmarks in the existing literature. The proposed model performs better / at par with exisiting techniques despite simpler framework. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

AI-Assisted Markerless Activity Tracking system for Supporting Aging and Wellness

AI-Assisted Markerless Activity Tracking System for Supporti...

引用

2023 IEEE Microwaves, Antennas, and Propagation Conference, MAPCON 2023

作者： Abedi, Hajar Ansariyan, Ahmad Morita, Plinio P Wong, Alexander Boger, Jennifer Shaker, George University of Waterloo Electrical and Computer Engineering Waterloo Canada University of Waterloo School of Public Health Sciences Waterloo Canada University of Waterloo System Design Engineering Waterloo Canada

ISBN: (纸本)9798350328264

This paper presents a mm-Wave radar-based system to create a novel method of tracking seniors and monitoring them using ambient wireless signals. Radar sensors, coupled with deep learning models, facilitate the identification of various physical activities without requiring physical contact or the use of wearable devices. The system employs range-Doppler maps derived from a real-life in-home activities dataset for training deep learning networks. The gated recurrent units (GRU) model is chosen for real-time implementation due to its optimal trade-off between speed and accuracy. The system achieves an overall accuracy of 93% for trained subjects, with 86% accuracy for classifying the in-home physical activities of a new subject. Additionally, the system captures the frequency of washroom use, sedentary, duration of sleep, active and out-of-home periods, the level of activity performed by the subject over a period of time, current activity state, and gait parameters. © 2023 IEEE.

关键词： activity recognition aging mm-wave radar personalized care sequential deep learning

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of RouteSegmentation Algorithm in Identifying Perimeter Area Around Travel Route 16

Performance Analysis of RouteSegmentation Algorithm in Ident...

引用

16th International Conference on Information Technology and Electrical engineering, ICITEE 2024

作者： Bachmid, Muhammad Avied Anshari Haq, Muhammad Yasir Mumtaz, Muhammad Rafly Pinandito, Aryo Universitas Brawijaya Faculty of Computer Science Media Game and Mobile Laboratory Department of Informatics Engineering Malang Indonesia Universitas Brawijaya Faculty of Computer Science Malang Indonesia Universitas Brawijaya Faculty of Computer Science Media Game and Mobile Laboratory Department of Information System Malang Indonesia

ISBN: (纸本)9798350375817

Prior study has developed the RouteSegmentation algorithm to identify the perimeter area surrounding a route. In this study, a comparative experiment was carried out to investigate the performance of the RouteSegmentation algorithm implementation in contrast to the RouteBoxer algorithm. Both algorithms play a crucial role in geographical information systems (GIS), particularly in enhancing navigational tools by identifying points of interest along specified routes. Through systematic experimentation using various perimeter distance values and types of route, the trade-offs between processing efficiency and the granularity of the area identified by these algorithms were evaluated. The results demonstrate that RouteSegmentation maintained relatively consistent performance across different perimeter distance values and statistically significantly faster processing time than RouteBoxer. Furthermore, while the RouteBoxer algorithm benefits from larger perimeter distance values by reducing processing time, it compromises the coverage results of the algorithm and potentially undermines its usefulness in practical scenarios. This study not only provides insights into the optimal use of perimeter distance values for each algorithm but also guides users in selecting the appropriate algorithm based on their specific application needs, balancing detailed geographical analysis and runtime efficiency. © 2024 IEEE.

关键词： Transportation routes

来源：评论

学校读者我要写书评

暂无评论

Analyzing Employee Retention Factors using Machine Learning 4

Analyzing Employee Retention Factors using Machine Learning

引用

4th International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies, ICAECT 2024

作者： Rahman, Moshiur Islam, Md Rashedul Bala, Partho Sattar, Abdus Daffodil International University Department of Management Information System Daffodil Smart City Dhaka Bangladesh Daffodil Institute of Information and Technology Department of Computer Science and Engineering Dhanmondi Dhaka Bangladesh Bangabandhu Sheikh Mujibur Rahman Science and Technology University Department of Computer Science and Engineering Dhaka8100 Bangladesh Daffodil International University Department of Computer Science and Engineering Daffodil Smart City Dhaka Bangladesh

ISBN: (纸本)9798350343670

This research proposal aims to employ machine learning techniques to analyze employee retention factors in Software Companies, recognizing its crucial role in organizational success and the potential costs of high turnover rates. Through Watson Analytics' advanced analytics capabilities, the study seeks to identify key factors contributing to employee attrition and retention, culminating in the development of a predictive model using machine learning algorithms. The outcomes are expected to include actionable recommendations to improve retention strategies, insights into the relative importance of different factors, and the creation of a data- driven, proactive talent management approach for Software Companies. By empowering organizations to retain top talent and fostering a positive work environment, this research envisions a transformative impact on long-term success and performance. © 2024 IEEE.

关键词： Artificial Intelligence Data Science Deep Learning Machine Learning Monitoring Smartphone Sensors

来源：评论

学校读者我要写书评

暂无评论

Hybrid Dipper Throated and Grey Wolf Optimization for Feature Selection Applied to Life Benchmark Datasets

引用

computers, Materials & Continua 2023年第2期74卷 4531-4545页

作者： Doaa Sami Khafaga El-Sayed M.El-kenawy Faten Khalid Karim Mostafa Abotaleb Abdelhameed Ibrahim Abdelaziz A.Abdelhamid D.L.Elsheweikh Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura35712Egypt Department of System Programming South Ural State UniversityChelyabinsk454080Russia Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Department of Computer Science Faculty of Computer and Information SciencesAin Shams UniversityCairo11566Egypt Department of Computer Science College of Computing and Information TechnologyShaqra University11961Saudi Arabia Department of Computer Science Faculty of Specific EducationMansoura UniversityEgypt

Selecting the most relevant subset of features from a dataset is a vital step in data mining and machine *** feature in a dataset has 2n possible subsets,making it challenging to select the optimum collection of features using typical *** a result,a new metaheuristicsbased feature selection method based on the dipper-throated and grey-wolf optimization(DTO-GW)algorithms has been developed in this *** can result when the selection of features is subject to metaheuristics,which can lead to a wide range of ***,we adopted hybrid optimization in our method of optimizing,which allowed us to better balance exploration and harvesting chores more *** propose utilizing the binary DTO-GW search approach we previously devised for selecting the optimal subset of *** the proposed method,the number of features selected is minimized,while classification accuracy is *** test the proposed method’s performance against eleven other state-of-theart approaches,eight datasets from the UCI repository were used,such as binary grey wolf search(bGWO),binary hybrid grey wolf,and particle swarm optimization(bGWO-PSO),bPSO,binary stochastic fractal search(bSFS),binary whale optimization algorithm(bWOA),binary modified grey wolf optimization(bMGWO),binary multiverse optimization(bMVO),binary bowerbird optimization(bSBO),binary hysteresis optimization(bHy),and binary hysteresis optimization(bHWO).The suggested method is superior 4532 CMC,2023,vol.74,no.2 and successful in handling the problem of feature selection,according to the results of the experiments.

关键词： Metaheuristics dipper throated optimization grey wolf optimization binary optimizer feature selection

来源：评论

学校读者我要写书评

暂无评论

Learning to see speckle in the weak laser field through multimode fiber

引用

Optoelectronics Letters 2025年

作者： JI Yunqi SONG Binbin LI Xueqing LI Yonghui The Engineering Research Center of Learning-Based Intelligent System (Ministry of Education)， the Key Laboratory of Computer Vision and Systems (Ministry of Education)， and the School of Computer Science and Engineering， Tianjin University of Technology

Multimode fibers (MMFs) have great potential for endoscopic imaging due to the high number of modes and a small core diameter. Deep learning based on neural networks has received increasing attention in the field of scattering image reconstruction. However， most studies focus on designing complex network architectures to improve reconstruction， but these network models struggle to reconstruct images in a weak laser field. In the paper， a lightweight generative adversarial network model combined with a histogram specification algorithm is designed to reconstruct speckles in the weak laser field through MMF. Experimental results show that the reconstruction results of our algorithm have better metrics. Moreover， the model demonstrates excellent cross-domain generalization ability with regards to the Fashion-MNIST dataset. It is worth mentioning that we found that the speckles after inactivation still retain the ability to be reconstructed， which enhances the robustness of the model

关键词：

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：