检索结果-内蒙古大学图书馆

2024 CHI Conference on Human Factors in Computing Sytems, CHI EA 2024

作者： Atabey, Ayça Wang, Ge Johnston, Samantha-Kaye Lin, Grace C. Wilson, Cara Urquhart, Lachlan D Zhao, Jun School of Law Centre for Data Culture & Society University of Edinburgh United Kingdom Department of Computer Science University of Oxford United Kingdom Scheller Teacher Education Program - the Education Arcade The Massachusetts Institute of Technology United States Centre for Research in Digital Education University of Edinburgh United Kingdom Edinburgh Law School University of Edinburgh United Kingdom

ISBN: (纸本)9798400703317

AI-powered solutions are increasingly woven into the fabric of children's digital worlds. They're found in interactive toys, home automation systems, everyday apps, and various online services that young users engage with. As we look ahead, it's almost certain that the prevalence of AI in tools and platforms designed for kids will grow, given AI's ability to offer rich, tailored, and dynamic experiences. However, the nuances of how these AI-centric platforms cater to children and how they can be optimized to meet the unique needs of younger users remain largely underexplored. Building on the momentum from our inaugural CCAI workshop at CHI 2023, our aspirations for this year's workshop include: (1) deepening the discourse on the essence of AI that prioritizes children, (2) focusing on actionable ethical strategies to operationalise child-centered AI design principles into practice, and (3) cultivating an ever-growing collective of professionals passionate about the future of child-focused AI innovations. © 2024 Owner/Author.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

Bayesian Parameter Estimation for Partially Observed McKean-Vlasov Diffusions Using Multilevel Markov chain Monte Carlo

arXiv

引用

arXiv 2025年

作者： Jasra, Ajay Wu, Amin School of Data Science The Chinese University of Hong Kong Shenzhen Shenzhen China Statistics Program Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia

In this article we consider Bayesian estimation of static parameters for a class of partially observed McKean-Vlasov diffusion processes with discrete-time observations over a fixed time interval. This problem features several obstacles to its solution, which include that the posterior density is numerically intractable in continuous-time, even if the transition probabilities are available and even when one uses a time-discretization, the posterior still cannot be used by adopting well-known computational methods such as Markov chain Monte Carlo (MCMC). In this paper we provide a solution to this problem by using new MCMC algorithms which can solve the aforementioned issues. This MCMC algorithm is extended to use multilevel Monte Carlo (MLMC) methods. We prove convergence bounds on our parameter estimators and show that the MLMC-based MCMC algorithm reduces the computational cost to achieve a mean square error versus ordinary MCMC by an order of magnitude. We numerically illustrate our results on two models. Copyright © 2025, The Authors. All rights reserved.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

Analysis Implementation of Chatbots to Increase Knowledge of Stunting Prevention in Indonesian Society with Bibliometric 9

Analysis Implementation of Chatbots to Increase Knowledge of...

引用

9th International Conference on Information Management and technology, ICIMTech 2024

作者： Sutedja, Indrajani Handayani, Lutfi Maryuni Hendry Faisal, Mohammad Reza School of Information Sytems Bina Nusantara University Information Systems Department Jakarta11480 Indonesia Midwifery Study Program Binawan University Faculty of Nursing and Midwifery Jakarta13630 Indonesia Satya Wacana Christian University Faculty of Information Technology Salatiga50711 Indonesia FMIPA Lambung Mangkurat University Department of Computer Science Banjarmasin70123 Indonesia

ISBN: (纸本)9798350390025

The healthcare industry uses AI, because it is more efficient. In Indonesia, the accuracy of measurements and transmission of children's growth and development is often wrong. Many small hospitals usually don't have length measuring equipment, so the results are inaccurate. This research aims to determine the effectiveness of the stunting prevention program in Indonesia using an information system. The methodology used is a qualitative method, to conduct subjective research and analysis. The results of the research are to improve the website/mobile application information system which can display a child's growth and development history and simple educational information related to nutrition. Digital recording methods can speed up the process of updating data with a central database in real time. The value of this research is to reach the public to utilize technology and obtain personalized and interactive information directly to individuals. The theoretical implications of this research focus on information dissemination and understanding how chatbots influence knowledge acquisition and behavior change in the context of stunting prevention can contribute to advancing these theories in the field of public health. Managerial implications can provide cost effectiveness as Chatbots offer potentially cost-effective solutions and data-driven insights where managers can leverage chatbot analytics. © 2024 IEEE.

关键词： Artificial Intelligent Indonesian information System Stunting stunting stunting chatbot and bibliometric stunting prevention VOS Viewer

来源：评论

学校读者我要写书评

暂无评论

Churn Prediction in Financial Risk Management using Deep Learning Techniques 2

Churn Prediction in Financial Risk Management using Deep Lea...

引用

2nd IEEE International Conference on Advanced Technologies in Intelligent Control, Environment, Computing and Communication Engineering, ICATIECE 2022

作者： Kumar, V Sunil Sowmyashree, S. Pareek, Piyush Kumar Khanna, Ashish Costa De Albuquerque, Victor Hugo Gupta, Deepak Nitte Meenakshi Institute of Technology Department of Artificial Intelligence & Machine Learning Bengaluru India Computer Science & Engineering East West Institute of Technology Bengaluru India Graduate Program in Telecommunication Engineering Federal Institute of Education Science and Technology of Cearά Fortaleza Brazil Maharaja Agrasen Institute of Technology GGSIPU CSE Dept India Federal University of Cearά Department of Teleinformatics Engineering Brazil

ISBN: (纸本)9781665493963

It is essential to develop an efficient Client Relationship Model in order to make use of the estimations about customer turnover (CRM). Finding and breaking down the facts surrounding the business information understanding is necessary for client produce prediction, which should be made possible effectively by altering the strategies used for business insight. The tools that are provided by company insight allow for the historical, current, and prospective perspectives of business activity to be anticipated and dissected. It is possible to deal with it in an efficient way by providing the information mining approaches that choose the data from the created informative index that is the most helpful. Fundamental leadership should be possible to achieve in a fruitful way if one has this information. The actions that consumers have taken in the recent past are going to be analyzed, and an accurate forecast is going to be formed about those customers who are likely going to get unhappy in the near future based on the results of that prediction. The problem is that deciding on a certain period to investigate the client's activities and also establishing on a specific day and age for each of the clients won't be appropriate6. This is due to the fact that the problem is caused by the fact that deciding on a certain period to investigate the client's activities will take too long. The challenge lies just in this aspect. How to decide on a certain amount of time to spend researching the activities of the customer. For instance, when planning a model, 100 customers are used, 70 of those customers are considered 'active,' which indicates that they are still conducting business with the organisation, and the remaining 30 customers are considered 'agitate,' which indicates that they have severed their ties with the organisation. The primary purpose of the work that has been suggested is to carry out exploratory research and management as a multicriteria basic leadership issue, a

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Merging UAV-Derived Metrics with Crop Physiology to Estimate Sunflower Yield

Merging UAV-Derived Metrics with Crop Physiology to Estimate...

引用

Frontiers of Information technology (FIT)

作者： Usama Athar Muhammad Ali Zuhair Zafar Haris Khurshid Karsten Berns Muhammad Moazam Fraz School of Electrical Engineering and Computer Science National University of Sciences and Technology (NUST) Islamabad Pakistan Oilseeds Research Program National Agricultural Research Center (NARC) Islamabad Pakistan Department of Computer Science Rheinland-Pfälzische Technische Universität Kaiserslautern Germany

ISBN: (数字)9798331510503

ISBN: (纸本)9798331510510

Accurate and timely estimation of sunflower yield is crucial for agricultural researchers, farmers, and breeders. Use of Unmanned Aerial Vehicles (UAVs) with multi-spectral sensors has been adopted to meet the need for precise sunflower seed yield predictions. This study proposes a combined approach that integrates 12 remotely sensed vegetation indices (VIs) with 3 key physiological traits - fresh weight, dry weight, and moisture factor - to capture the complex dynamics affecting sunflower crop. Predictive performance of VIs alone and in combination with physiological traits is evaluated using Root Mean Squared Error (RMSE). Our results show that incorporating these two sets of features, along with their temporal, spectral, and statistical characteristics, leads to consistent improvements in sunflower seed yield estimation that can reduce the root mean squared error to as low as 0.4075 ( $\text{kg} / \text{plot}$ ).

关键词： Vegetation mapping Moisture Autonomous aerial vehicles Physiology Seeds (agriculture) Sensors Yield estimation Reliability Vehicle dynamics Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Air Quality Prediction Based on Air Pollution Emissions in the City Environment Using XGBoost with SMOTE 4

Air Quality Prediction Based on Air Pollution Emissions in t...

引用

4th IEEE International Conference of computer science and Information technology, ICOSNIKOM 2022

作者： Nababan, Adli A Sutarman Zarlis, Muhammad Nababan, Erna B Universitas Sumatera Utara Faculty of Computer Science and Information Technology Department of Computer Science Medan Indonesia Universitas Sumatera Utara Faculty of Mathematics and Natural Sciences Department of Mathematics Medan Indonesia Binus Graduate Program-Master of Information Systems Management Bina Nusantara University Department of Information Systems Management Jakarta Indonesia

ISBN: (纸本)9798350399073

Air pollution makes it worse in populated regions. Indonesia's major cities are also impacted by air pollution. Due to rising traffic, material consumption by vehicles, industrial growth, land burning, and garbage collection, air quality has altered significantly. Accurate measurement and classification of air quality are required. Results of accurate classification aid in forming governmental regulations. To reach the criteria for livable air quality, we intend to manage controls. Some of the characteristics of air pollution include particulate (PM10) or PM25, sulfides (in the form of SO2), carbon monoxide (CO), ozone (O3), and nitrites (NO2). Using the XGBoost algorithm and synthetic minority oversampling (SMOTE) methods based on the Air Pollution Standard Index (ISPU) category, this study seeks to uncover factors that affect air quality. XGBoost, an ensemble machine learning approach built on a decision tree and applying a gradient reinforcement framework, is the classification algorithm in use. Air quality categorization has been tested and shown to work with the XGBoost algorithm. The dataset used in this study is air quality in 2021 which was collected by the Jakarta Environmental Ministry The proposed classification model will be evaluated using the Repeated k-fold cross-validation method for objective results. The results of the study prove that SMOTE and XGBoost have better performance than using only the XGBoost method in predicting air quality, where the overall accuracy value of SMOTE with XGBoost is 99.60%, The overall precision value is 99.60%, the overall recall value is 99.60% and the overall f1-score is 99.60% and the overall ROC AUC value is 99.96%. The overall SMOTE method with the proposed XGBoost has given better performance in air pollution prediction. © 2022 IEEE.

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

Prediction of Forest Fire Using Machine Learning Algorithms: The Search for the Better Algorithm 6

Prediction of Forest Fire Using Machine Learning Algorithms:...

引用

6th IEEE International Conference on Innovative Technologies in Intelligent System and Industrial Application, CITISIA 2021

作者： Rakshit, Pranati Sarkar, Srestha Khan, Sambit Saha, Pritam Bhattacharyya, Sonali Dey, Nilarpan Islam, Sardar M.N. Pal, Souvik JIS College of Engineering Computer Science of Engineerng Kalyani India Victoria University ISILC and Decision Sciences and Modeling Program Australia Global Institute of Management and Technology Computer Science of Engineerng Krishnanagar India

ISBN: (纸本)9781665417846

Forest fire has several devastating effects on the natural vegetation and the forest lives. The forest fire plays an important role in everyone's lives and also in our environment. Forest fire is an integral part of many ecosystems such as grassland, temperate forest etc. The ability to predict the area where the forest fire may occur will help in optimizing the situation. The paper presented the prediction of forest fire risk with the help of a machine learning algorithm by using meteorological data. From the existing literature and Limitations, we can show that Different studies have shown the amount of burnt area due to the forest fire, and many have proposed different models to predict forest fire. But there is no such literature which predicts the depth of risk for this forest fire specifically. For that reason, the objective of this work is to predict the risk of forest fire by identifying the particular area as highly prone, moderately prone, low prone and no fire prone area. As a Present Research, in this paper we have worked with different classification models to check which models work best to predict forest fire with greater accuracy. The results we have obtained with the help of various classifiers in machine learning are much better and reliable than the results obtained by traditional computing methods. Thus, this paper indicates a deeper investigation in the field of predicting forest fire risk through machine learning. As a contribution, in this paper we have used SVM, KNN, Decision Tree, Naive Bayes classifier for prediction purposes. The main objective of this paper is to predict the possibility of forest fire with its intensity in specific atmospheric conditions in a given location. We have made comparison of the performance analysis of the different machine learning classifiers. At the end of the abstract, we got the highest AUC value of 0.99 and classification accuracy of 0.98 using Decision Tree to predict the same. © 2021 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

GPU-Accelerated Vecchia Approximations of Gaussian Processes for Geospatial Data using Batched Matrix Computations

GPU-Accelerated Vecchia Approximations of Gaussian Processes...

引用

ISC High Performance 2024 Research Paper Proceedings (39th International Conference)

作者： Qilong Pan Sameh Abdulah Marc G. Genton David E. Keyes Hatem Ltaief Ying Sun Division of Computer Electrical and Mathematical Sciences and Engineering (CEMSE) Statistics Program Extreme Computing Research Center King Abdullah University of Science and Technology Thuwal Jeddah Saudi Arabia

Gaussian processes (GPs) are commonly used for geospatial analysis, but they suffer from high computational complexity when dealing with massive data. For instance, the log-likelihood function required in estimating the statistical model parameters for geospatial data is a computationally intensive procedure that involves computing the inverse of a covariance matrix with size $n$ × n, where $n$ represents the number of geographical locations in the simplest case. As a result, in the literature, studies have shifted towards approximation methods to handle larger values of $n$ effectively while maintaining high accuracy. These methods encompass a range of techniques, including low-rank and sparse approximations. Among these techniques, Vecchia approximation is one of the most promising methods to speed up evaluating the log-likelihood function. This study presents a parallel implementation of the Vecchia approximation technique, utilizing batched matrix computations on contemporary GPUs. The proposed implementation relies on batched linear algebra routines to efficiently execute individual conditional distributions in the Vecchia algorithm. We rely on the KBLAS linear algebra library to perform batched linear algebra operations, reducing the time to solution compared to the state-of-the-art parallel implementation of the likelihood estimation operation in the ExaGeoStat software by up to 700X, 833X, 1380X on 32GB GV100, 80GB A100, and 80GB H100 GPUs, respectively, with the largest matrix dimension that can fully fit into the GPU memory in the dense Maximum Likelihood Estimation (MLE) case. We also successfully manage larger problem sizes on a single NVIDIA GPU, accommodating up to 1 million locations with 80GB A100 and H100 GPUs while maintaining the necessary application accuracy. We further assess the accuracy performance of the implemented algorithm, identifying the optimal settings for the Vecchia approximation algorithm to preserve accuracy on two real geos

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Wavy Channel Gate-All-Around FETs for Next-Generation CMOS Applications

A Novel Wavy Channel Gate-All-Around FETs for Next-Generatio...

引用

IEEE Conference on Nanotechnology

作者： Ranita Halder Uttam Kumar Das Md. Hasan Raza Ansari Nazek El-Atab Smart Advanced Memory Devices and Applications (SAMA) Labs Electrical and Computer Engineering Program Computer Electrical and Mathematical Science and Engineering Division (CEMSE) King Abdullah University of Science and Technology (KAUST) Thuwal Saudi Arabia

The work presents a novel wavy channel nanosheet field effect transistor (WCNSFET) and its circuit-level performance. In this work, a single nanosheet is transformed into a wave-like structure to enhance the physical device area, thus showing an improvement in device performance. The device and circuit level performances are analyzed using 3D TCAD simulation tools. Furthermore, the wavy channel nanosheet FETs are analyzed with different number of waves in a single sheet and compared with flat sheet-based transistors for different channel materials (Ge and GaAs). The results reveal the improvement in drive current, low propagation delay, a smooth voltage transfer characteristic, high noise margin, and low energy. The results achieved with this novel device make the device a promising candidate for next-generation low power CMOS applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Acoustic Scene Classification Using Perceptually Weighted Log Mel Spectrogram and Buttom-up Broadcast Neural Network

Acoustic Scene Classification Using Perceptually Weighted Lo...

引用

IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW)

作者： Riyad Ali Ahmad Abuirbaiha Chang-Hsing Lee Cheng Chang Lien Ph.D. Program in Engineering Science Chung Hua University Hsinchu Taiwan Bachelor Program in Industrial Artificial Intelligence Ming Chi University of Technology New Taipei City Taiwan Department of Computer Science and Information Engineering Chung Hua University Hsinchu Taiwan

ISBN: (数字)9798350386844

ISBN: (纸本)9798350386851

The study explores various 2D feature representations including spectrogram, MFCC spectrogram, log Mel-spectrogram, and the perceptual weighted log Mel-spectrogram (PW-LMSP) for acoustic scene classification (ASC). These 2D feature representations were classified using a bottom-up broadcast neural network (BBNN). The experimental results have shown that PW-LMSP outperforms other 2D representations. Further, the proposed method (PW-LMSP with BBNN) achieves accuracies of 91.2% and 91.6% respectively on the DCASE2018 and DCASE2019 development datasets, outperforming all the submissions in DCASE2018 and DCASE2019, as well as state-of-the-art approaches.

关键词： Scene classification Accuracy Neural networks LoRa Feature extraction Acoustics Mel frequency cepstral coefficient

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：