检索结果-内蒙古大学图书馆

Development of "Peter's First-Aid Adventure" Virtual Reality-Based Serious Game in First-Aid Education: Usability Analysis of Virtual Reality Interaction Tools 9th

Development of "Peter's First-Aid Adventure" Virtual Reality...

引用

9th International Conference on computer Science and Computational Intelligence, ICCSCI 2024

作者： Rainer, Alexander Setiono, Angeline Leonardrich, Kevin Ramdhan, Dimas Game Application & Technology Program Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia

Incidents that threaten lives can occur unexpectedly, highlighting the importance of immediate first aid. Studies show that Virtual Reality (VR)-based Serious Games (SG) are excellent alternatives for learning, especially for physical training, as they provide immersive and realistic scenarios where users can learn and practice their skills in a safe environment. Therefore, this research proposes the design of a VR-based SG for learning first aid procedures. A total of 31 participants tested the game's usability using both VR controllers and hand tracking, playing the game with both tools in random order, and then completing the XR-GUQ and Interaction Categories questionnaire. The results indicate that controllers offer higher usability than hand tracking. However, the game can still effectively utilize both interaction tools, given their satisfactory usability ratings. © 2024 The Authors.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

Extracting Aspect Sentiment from Users' Book Reviews for Recommendation

Extracting Aspect Sentiment from Users' Book Reviews for Rec...

引用

2024 International Conference on Computational Linguistics and Natural Language Processing, CLNLP 2024

作者： Cui, Yachao Zhou, Peng Li, Kang Seng, Bingfeng Cao, Han Shaanxi Normal University School of Computer Science Xi'an China Qinghai University Department of Computer Technology and Application Xining China

ISBN: (纸本)9798350392098

When shopping for books on e-commerce platforms, other users' evaluations of books contain a large number of users' intuitive feelings, from which useful information can be mined to provide buyers with ideas for shopping. In terms of recommendation algorithms, although the existing research work can use various methods to model fine-grained user preferences to improve the recommendation effect. However, we believe there are still shortcomings. First, existing methods are overly dependent on the accuracy of external sentiment analysis tools and are not necessarily applicable to the recommendation domain. Second, the features extracted from reviews are still potential features when incorporated into recommendation algorithms, and they cannot be fully utilized to characterize user embeddings. For this reason, this paper proposes a new user comment extraction scheme for personalized recommendation. We first use text summarization techniques in the field of NLP to preprocess and refine the comment text to reduce data noise and obtain high-quality text information. Subsequently, in order to more accurately characterize user embeddings and item features, we use advanced aspect-based sentiment analysis techniques to extract fine-grained aspectual items and corresponding sentiment polarity from the review text. Finally, experimental validation on a real book dataset is conducted to demonstrate the effectiveness of our model. © 2024 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Location Prediction from Social Media Contents using Location Aware Attention LSTM Network

引用

Journal of Harbin Institute of technology(New Series) 2024年第5期31卷 68-77页

作者： Madhur Arora Sanjay Agrawal Ravindra Patel Department of Computer Application University Institute of TechnologyRajiv Gandhi Proudyogiki VishwavidyalayaBhopal(M.P.)462033India Department of Computer Application National Institute of Technical Teachers Training and ResearchBhopal(M.P.)462002India

Location prediction in social media,a growing research field,employs machine learning to identify users' locations from their online *** technology,useful in targeted advertising and urban planning,relies on natural language processing to analyze social media content and understand the temporal dynamics and structures of social networks.A key application is predicting a Twitter user's location from their tweets,which can be challenging due to the short and unstructured nature of tweet *** address this challenge,the research introduces a novel machine learning model called the location-aware attention LSTM(LAA-LSTM).This hybrid model combines a Long Short-Term Memory(LSTM) network with an attention *** LSTM is trained on a dataset of tweets,and the attention network focuses on extracting features related to latitude and longitude,which are crucial for pinpointing the location of a user's *** result analysis shows approx.10% improvement in accuracy over other existing machine learning approaches.

关键词： Twitter social media location machine learning attention network

来源：评论

学校读者我要写书评

暂无评论

Stochastic Gradient Descent on Modern Hardware for Business Environment 7

Stochastic Gradient Descent on Modern Hardware for Business ...

引用

7th International Conference on Intelligent Computing and Control Systems, ICICCS 2023

作者： Saravanan, V. Ranjana, P. Hindustan Institute of Technology & Science Department of Computer Application Chennai603103 India

ISBN: (纸本)9798350397253

Cost is the primary justification for outsourcing an organization's IT hardware acquisition. By avoiding the need to hire more staff members and reducing the number of hours your present workers are required to work, outsourcing the purchase of hardware may help the business save money. Additionally, you won't need to continually purchase brand-new IT hardware or software. Additionally, outsourcing can boost production and enable you to provide your consumers with a better and more effective good or service. An iterative technique for maximizing an objective function with sufficient smoothness qualities is stochastic gradient descent or SGD for short. Given that it substitutes an estimate for the real gradient, it may be thought of as a stochastic approximation of gradient descent optimization. This lightens the computational load, especially in high-dimensional optimization problems, leading to quicker iterations at the cost of a reduced convergence rate. We suggest a Stochastic Gradient Descent model for use in a commercial setting where large corporations must purchase the necessary hardware with their software. Our approach assists in determining the necessary hardware requirements based on the demands of the customers. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Designing a User-Friendly and Responsive AI based Image Generation Website and Performing Diversity Assessment of the Generated Images 4

Designing a User-Friendly and Responsive AI based Image Gene...

引用

4th International Conference on Electronics and Sustainable Communication Systems, ICESC 2023

作者： Kanakia, Harshil T. Nair, Suraj Prakkash Sardar Patel Institute of Technology Master of Computer Application Department Mumbai India

ISBN: (纸本)9798350300093

This research paper presents a website that leverages the power of the Image GPT engine for image generation. The website allows users to input a textual prompt and generate a corresponding image using Image GPT's natural language processing and machine learning capabilities. The paper details the architecture of the website, the Image GPT API integration, and the algorithms used for image generation. Additionally, we present the results and evaluate its quality and discuss potential applications of this technology in various industries such as advertising, art and design. We also discuss how the performance of image generation can be potentially improved. Overall, the website demonstrates the potential of combining natural language processing and machine learning for image generation and opens up new avenues for future research in this field. © 2023 IEEE.

关键词： Engines

来源：评论

学校读者我要写书评

暂无评论

Blockchain Enabled Autonomous Vehicle Based Vehicular IoT System

Blockchain Enabled Autonomous Vehicle Based Vehicular IoT Sy...

引用

2023 IEEE International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, ICIITCEE 2023

作者： Hemani Singh, Daya Shankar Dwivedi, Rajendra Kumar Madan Mohan Malaviya University of Technology Department of Information Technology and Computer Application Gorakhpur India

ISBN: (纸本)9781665462631

Blockchain technology is gaining its popularity in many areas with huge success which ultimately attracts all researchers to study this technology. And the result of that shows more and more research to be conducted. Which makes blockchain technology relevant in the field of transportation systems. It is expected that in near future their integration will achieve greater heights, as compared to other technology blockchain is still new and many more unknown things still need to be found out. The aim of this study is to find out how blockchain benefits in Autonomous vehicles. We have compared the blockchain integrated autonomous vehicle systems to get the picture of the present environment and the challenge of the future for this integration. AV's or we say intelligent transportation is the future. We are going to study the potential application of the blockchain which will help in improving this particular section of industry. Finally their limitations and challenges associated with this integration. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Illumination-Free Clustering Using Improved Slime Mould Algorithm for Acute Lymphoblastic Leukemia Image Segmentation

引用

Journal of Bionic Engineering 2023年第6期20卷 2916-2934页

作者： Krishna Gopal Dhal Swarnajit Ray Sudip Barik Arunita Das Department of Computer Science and Application Midnapore College(Autonomous)Paschim MedinipurMidnaporeWest BengalIndia Department of Computer Science and Engineering Maulana Abul Kalam Azad University of TechnologyKolkataWest BengalIndia Department of Computer Science and Engineering Kalyani Government Engineering CollegeKalyaniWest BengalIndia

Partitional clustering techniques such as K-Means(KM),Fuzzy C-Means(FCM),and Rough K-Means(RKM)are very simple and effective techniques for image ***,because their initial cluster centers are randomly determined,it is often seen that certain clusters converge to local *** addition to that,pathology image segmentation is also problematic due to uneven lighting,stain,and camera settings during the microscopic image capturing ***,this study proposes an Improved Slime Mould Algorithm(ISMA)based on opposition based learning and differential evolution’s mutation strategy to perform illumination-free White Blood Cell(WBC)*** ISMA helps to overcome the local optima trapping problem of the partitional clustering techniques to some *** paper also performs a depth analysis by considering only color components of many well-known color spaces for clustering to find the effect of illumination over color pathology image *** and visual results encourage the utilization of illumination-free or color component-based clustering approaches for image ***-KM and“ab”color channels of CIELab color space provide best results with above-99%accuracy for only nucleus ***,for entire WBC segmentation,ISMA-KM and the“CbCr”color component of YCbCr color space provide the best results with an accuracy of above 99%.Furthermore,ISMA-KM and ISMA-RKM have the lowest and highest execution times,*** the other hand,ISMA provides competitive outcomes over CEC2019 benchmark test functions compared to recent well-established and efficient Nature-Inspired Optimization Algorithms(NIOAs).

关键词： Pathology image Image segmentation Clustering Color space White blood cell Optimization Swarm intelligence Fuzzy clustering Rough clustering

来源：评论

学校读者我要写书评

暂无评论

Food Genie, Recipe Search Algorithm Using Web Scraping 3

Food Genie, Recipe Search Algorithm Using Web Scraping

引用

3rd IEEE Asian Conference on Innovation in technology, ASIANCON 2023

作者： Suwalka, Nikhil Shanbhag, Nishit Salmani, Sakina Raundale, Pooja Sardar Patel Institute of Technology Master of Computer Application Department Mumbai India

ISBN: (纸本)9798350302288

Coping up with our busy lifestyle and unhealthy eating habits, we are compelled to eat diet foods containing specific ingredients and recipes. It's not easy to ask the chef to make a range of recipes that contain the required ingredients. There are several recipe websites containing a wide range of recipes to choose from. This allows the chef to make new meals containing the specified calories and other nutritional values. The challenge is to find a list of all recipes containing the required ingredients along with the maximum calories allowed without having any data in-hand. This paper presents a method to get a list of all recipes along with its details like methods, ingredients, nutritional information which contains all or some of the mentioned ingredients. The method will allow users to search for recipes easily without worrying about the ingredients. Web scraping using Scrapy and Neo4j graph database is used to implement the algorithm. Web scraping takes the contents of a web page and saves them in a Neo4j graph database using the Python scrapy package. This database will be used to do more study on the food genie application in order to improve search results. Chefs may use the online app to prepare a variety of recipes using particular components to maintain a healthy lifestyle. © 2023 IEEE.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Forest Fire Likelihood And Risk Modeling: A Machine Learning Approach 4

Forest Fire Likelihood And Risk Modeling: A Machine Learning...

引用

4th International Conference on Electronics and Sustainable Communication Systems, ICESC 2023

作者： Save, Payal M. Thakur, Pallavi Sardar Patel Institute of Technology Master of Computer Application Department Mumbai India

ISBN: (纸本)9798350300093

Forest fires significantly threaten natural environments and human life, necessitating accurate forest fire prediction and risk modeling. The aim of the paper is to investigate the forest fires in the forested areas of Assam, India. The threats to the biodiversity of Assam are multi-faceted and include habitat loss or destruction and fragmentation, unlawful wildlife trade, human-wildlife conflict, climate change, pollution, invasive species, and forest fires. Forest fires, in particular, pose a significant threat, leading to habitat destruction, depletion of vegetation cover, and eviction of flora and fauna. The distinctive ecosystems of Assam consisting of tropical rainforests, grasslands, and riverine habitats, are especially vulnerable including sanctuaries, national parks, and reserves. To address the challenges posed by forest fires, the integration of novel machine learning techniques offers promising solutions. Machine learning algorithms can leverage historical fire data, weather patterns, and other relevant variables to develop predictive models for forest fire likelihood. The paper aims to predict the probability or likelihood and risk level of forest fires in the Nameri National Park And Forest Reserve region of Assam using novel machine learning approaches. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Research on identity authentication and labeling technology based on MR neural network

Research on identity authentication and labeling technology ...

引用

2022 International Conference on Artificial Intelligence, Virtual Reality, and Visualization, AIVRV 2022

作者： Yang, Hao Tang, Chuanqian Department of Computer Technology and Application Qinghai University Qinghai Xining810016 China

ISBN: (纸本)9781510662988

Aiming at the problems of poor convenience, poor scalability, and low authentication rate in traditional authentication technology using physical contact authentication methods such as magnetic cards and passwords, this paper explores the accuracy and convenience of the practical application of MR neural network in personal identity authentication. In the MR wearable device, the neural network person identity authentication method is studied flexibly and quickly to detect and identify the person. The 3D information of the face is collected and preprocessed by the depth camera, and the MR identity authentication data set is established. The neural network Resnet model is used for face detection and face feature vector extraction, and the Euclidean method is used to compare the feature vectors and label the characters. The neural network authentication algorithm is mapped to the MR wearable device, and the deep face information in the scene is identified, matched, and labeled by using the unique spatial mapping of MR technology and the camera of the MR wearable device. It solves the problems of low flexibility, poor reliability of face information, and weak recognition stability in traditional identity authentication methods, enabling MR technology to provide a more intelligent identification and labeling method for person identity authentication. © 2023 SPIE. All rights reserved.

关键词： Face recognition

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：