检索结果-内蒙古大学图书馆

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Peng Jin Ryuichi Takanobu Wancai Zhang Xiaochun Cao Li Yuan School of Electronic and Computer Engineering Peking University Shenzhen China Peng Cheng Laboratory Shenzhen China AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School Shenzhen China Nari Technology Co. Ltd. China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University Shenzhen China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Large language models have demonstrated impressive universal capabilities across a wide range of open-ended tasks and have extended their utility to encompass multi-modal conversations. However, existing methods encounter challenges in effectively handling both image and video understanding, particularly with limited visual tokens. In this work, we introduce Chat-UniVi, a Unified Vision-language model capable of comprehending and engaging in conver-sations involving images and videos through a unified visual representation. Specifically, we employ a set of dynamic visual tokens to uniformly represent images and videos. This representation framework empowers the model to ef-ficiently utilize a limited number of visual tokens to simul-taneously capture the spatial details necessary for images and the comprehensive temporal relationship required for videos. Moreover, we leverage a multi-scale representation, enabling the model to perceive both high-level seman-tic concepts and low-level visual details. Notably, Chat-UniVi is trained on a mixed dataset containing both images and videos, allowing direct application to tasks involving both mediums without requiring any modifications. Exten-sive experimental results demonstrate that Chat- UniVi con-sistently outperforms even existing methods exclusively de-signed for either images or videos. Code is available at https://***/PKu-Yuan Group/Chat-UniVi.

关键词： Bridges Visualization computer vision Codes Large language models Computational modeling Oral communication

来源：评论

学校读者我要写书评

暂无评论

CLINICAL DETERIORATION PREDICTION IN BRAZILIAN HOSPITALS BASED ON ARTIFICIAL NEURAL NETWORKS AND TREE DECISION MODELS

arXiv

引用

arXiv 2022年

作者： Yazdanpanah, Hamed Silva, Augusto C.M. Guedes, Murilo Morales, Hugo M.P. Coelho, Leandro dos S. Moro, Fernando G. Department of Research Robô Laura PR Curitiba Brazil Department of Computer Science University of São Paulo SP São Paulo Brazil Industrial and Systems Engineering Graduate Program Pontifical Catholic University of Parana PR Curitiba Brazil Electrical Engineering Graduate Program Federal University of Parana PR Curitiba Brazil

Early recognition of clinical deterioration (CD) has vital importance in patients' survival from exacerbation or death. Electronic health records (EHRs) data have been widely employed in Early Warning Scores (EWS) to measure CD risk in hospitalized patients. Recently, EHRs data have been utilized in Machine Learning (ML) models to predict mortality and CD. The ML models have shown superior performance in CD prediction compared to EWS. Since EHRs data are structured and tabular, conventional ML models are generally applied to them, and less effort is put into evaluating the artificial neural network's performance on EHRs data. Thus, in this article, an extremely boosted neural network (XBNet) is used to predict CD, and its performance is compared to eXtreme Gradient Boosting (XGBoost) and random forest (RF) models. For this purpose, 103,105 samples from thirteen Brazilian hospitals are used to generate the models. Moreover, the principal component analysis (PCA) is employed to verify whether it can improve the adopted models' performance. The performance of ML models and Modified Early Warning Score (MEWS), an EWS candidate, are evaluated in CD prediction regarding the accuracy, precision, recall, F1-score, and geometric mean (G-mean) metrics in a 10-fold cross-validation approach. According to the experiments, the XGBoost model obtained the best results in predicting CD among Brazilian hospitals' data. © 2022, CC BY-NC-SA.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Oil Palm Fruits Dataset in Plantations for Harvest Estimation Using Digital Census and Smartphone

引用

Scientific data 2025年第1期12卷 972页

作者： Martinus Grady Naftali Gregory Hugo Muhammad Reza Azhar Priyadi Muhammad Asrol Ditdit Nugeraha Utama Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta 10480 Indonesia. Computer Science Department BINUS Online Learning Bina Nusantara University Jakarta 10480 Indonesia. Industrial Engineering Department BINUS Graduate Program - Master of Industrial Engineering Bina Nusantara University Jakarta 11480 Indonesia.

This article presents a dataset of oil palm Fresh Fruit Bunches (FFBs) images from commercial plantations in Central Kalimantan, Indonesia, focusing on five maturity stages: Unripe, Underripe, Ripe, Flower, and Abnormal. The data collection involved smartphone video recordings of unharvested trees from multiple angles under varying conditions. Video frames were extracted and expertly annotated using computer Vision Annotation Tool (CVAT), with annotations exported in Common Objects in Context (COCO) format suitable for object detection tasks. It has 10,207 images in its training set, 2,896 in the validation set, and 1,400 in the test set, which are supplemented using data augmentation to handle class imbalance and increase variation. These images have real-world complications arising from partial visibility, low contrast, occlusion, and blurriness. It forms the basis that will support the development of deep learning models for detection and classification of FFB, particularly for monitoring of harvest times, yield prediction, and optimization of resources in plantation operations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploration of Technology Home-based Learning Guidance for Parents and Students during the Covid-19 Pandemic 9

Exploration of Technology Home-based Learning Guidance for P...

引用

9th International Congress on Advanced Applied Informatics, IIAI-AAI 2020

作者： Suzanna, Suzanna Sasmoko, Sasmoko Lumban Gaol, Ford Oktavia, Tanty Matsuo, Tokuro Bina Nusantara University Binus Graduate Program-Doctor of Computer Science Computer Science Department Jakarta11480 Indonesia Advanced Institute of Industrial Technology Information System Department Tokyo140-0011 Japan

ISBN: (纸本)9781728173979

With the sudden attack of the Corona Virus Disease 2019 (COVID-19), some 300 million children in the world have been forced to study at home because of the mass closure of schools that began on March 18, 2020. This has caused many obstacles in the teaching and learning process. Every effort is made to minimize the COVID-19 pandemic while ensuring the teaching and learning process is not interrupted. If the school closures too long and the child is trapped inside the house this will have a negative impact on the physical and mental health of the children. This situation makes parents become worried and look for alternative education in addition to formal schooling for their children. Of the various types of education offers that exist homeschooling or commonly known as home-based learning provides a way out for the current situation. Now children are quarantined in their homes and they will return to school once this epidemic fades. But with this disaster, parents' views on homeschooling or home-based learning can be different from before. They may still be marked if home-based learning can be a long-term education. With the existence of COVID-19, most parents might finally realize that education without formal schooling is not a crisis but an opportunity to take their children to a better future. This research was conducted by utilizing a descriptive qualitative method and within the descriptive qualitative method, the concept of document analysis would be utilized the most. It was expected that the results of this research would explore what type of technology parents could prepare for their children to use to initiate home-based learning. © 2020 IEEE.

关键词： Viruses

来源：评论

学校读者我要写书评

暂无评论

Enhanced Pain Detection and Movement of Motion with Data Augmentation based on Deep Learning

Enhanced Pain Detection and Movement of Motion with Data Aug...

引用

International Conference on Knowledge and Smart Technology (KST)

作者： Kornprom Pikulkaew Varin Chouvatut Graduate Program in Computer Science Faculty of Science Chiang Mai University Chiang Mai Thailand Faculty of Science Chiang Mai University Chiang Mai Thailand

Pain is what anyone would experience, regardless of age or gender. Facial pain tracking technology is a successful tool since it is user-friendly with high precision. Auto pain monitoring benefits include that it will support patients and care professionals, including physicians and nurses. This paper suggests 2D facial expression and movement for pain perception with data augmentation utilizing deep learning approaches. We used approximately 50,000 UNBC sequential photos in this study. Deep learning is applied to train data and activity approach to assist patient orientation. Our method can separate pain thresholds into three levels: painless, beginning to be painful, and painful. Our work is the standard method for detecting discomfort before heading to the hospital. It is easy, cost-effective, and readily grasped by the general public and healthcare professionals.

关键词： Deep learning Pain Hospitals Tracking Tools Reliability Standards

来源：评论

学校读者我要写书评

暂无评论

Reconfigurable Intelligent Surface-Aided Joint Radar and Covert Communications: Fundamentals, Optimization, and Challenges

arXiv

引用

arXiv 2022年

作者： Du, Hongyang Kang, Jiawen Niyato, Dusit Zhang, Jiayi Kim, Dong In The School of Computer Science and Engineering The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore The School of Computer Science and Engineering Nanyang Technological University Singapore The School of Electronic and Information Engineering Beijing Jiaotong University Beijing100044 China The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of

Future wireless communication systems will evolve toward multi-functional integrated systems to improve spectrum utilization and reduce equipment sizes. A joint radar and communication (JRC) system, which can support simultaneous information transmission and target detection, has been regarded as a promising solution for emerging applications such as autonomous vehicles. In JRC, data security and privacy protection are critical issues. Thus, we first apply covert communication into JRC and propose a joint radar and covert communication (JRCC) system to achieve high spectrum utilization and secure data transmission simultaneously. In the JRCC system, an existence of sensitive data transmission is hidden from a maliciously observant warden. However, the performance of JRCC is restricted by severe signal propagation environment and hardware devices. Fortunately, reconfigurable intelligent surfaces (RISs) can change the signal propagation smartly to improve the networks performance with low cost. We first overview fundamental concepts of JRCC and RIS and then propose the RIS-aided JRCC system design. Furthermore, both covert communication and radar performance metrics are investigated and a game theory-based covert rate optimization scheme is designed to achieve secure communication. Finally, we present several promising applications and future directions of RIS-aided JRCC systems. © 2022, CC BY.

关键词： Data transfer

来源：评论

学校读者我要写书评

暂无评论

The Accuracies of ANFIS and Genetic Algorithm with Tournament Selection on Classifying Hepatitis Data 4

The Accuracies of ANFIS and Genetic Algorithm with Tournamen...

引用

4th International Conference on Computing and Applied Informatics 2019, ICCAI 2019

作者： Siahaan, W.F.A. Sitompul, O.S. Situmorang, Z. Graduate Program of Computer Science Universitas Sumatera Utara Medan Indonesia Department of Information Technology Universitas Sumatera Utara Medan Indonesia Department of Computer Science Universitas Katolik Santo Thomas Medan Indonesia

Classification is an important technique in data mining to create patterns and data modeling. Hepatitis is a disease that is dangerous to humans as this disease affects the human liver which is a vital organ. Early detection of hepatitis by diagnosing its occurrence on patients is needed to give them help, care, and treatment. Therefore, a classification technique is required to create patterns and models of data. To achieve accuracy in classifying hepatitis there would be requirements to separate relevant from irrelevant features. By only considering relevance features in classifying hepatitis, it is expected that the classification process will be faster, easier, and more accurate. In this research, the ANFIS algorithm and genetic algorithm are used in classifying the diagnosis of hepatitis based on a dataset from the UCI data mining repository. Results obtained showed that the genetic algorithm gave a slightly higher accuracy of 98.73% compared to 86.67% results obtained using ANFIS. © Published under licence by IOP Publishing Ltd.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Towards Cloud Computing and Blockchain Integrated Applications

Towards Cloud Computing and Blockchain Integrated Applicatio...

引用

IEEE International Conference on Software Architecture Workshops (ICSAW)

作者： Emanuel F. Coutinho Diogo Eliseu Paulo Antonio Welligton Abreu I. M.Bezerra Carla Graduate Program in Computer Science (PCOMP) Undergraduate Course in Computer Science

ISBN: (数字)9781728174150

ISBN: (纸本)9781728174167

Cloud Computing is a technology widely used in academia and industry, providing varied services on demand. Blockchain technology was developed initially for the creation of a crypto-currency and nowadays is being exploited for several other applications, such as health, agriculture, IoT and education. Some work initiatives are already taking place with the integration of these two technologies, either for research or for cloud service provision. This article aims to present a preliminary discussion on some aspects of integration between blockchain and cloud computing. Contributions of this paper include: (i) presentation of two integrated commercial cloud computing and blockchain environments; and (ii) some research opportunities on the use of both environments.

关键词： Cloud computing Computational modeling Peer-to-peer computing Cryptography Contracts Tools

来源：评论

学校读者我要写书评

暂无评论

E-payment for Jakarta Smart Public Transportation, Using the Point System for E-Commerce 2

E-payment for Jakarta Smart Public Transportation, Using the...

引用

2nd International Conference on computer, science, Engineering, and Technology, ICComSET 2019

作者： Anwar, Nizirwan Rasjidin, Roesfiansjah Najoan, Daniel Stephanus Rolando, Christopher Tamimmanar Warnars, Harco Leslie Hendric Spits Faculty of Computer Science Esa Unggul University Jakarta11510 Indonesia Faculty of Engineering Esa Unggul University Jakarta11510 Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program - Doctor of Computer Science Bina Nusantara University Jakarta11480 Indonesia

The ease of using transportation is one of the most critical things in the city with a significant population like Jakarta. The growth of the population in Jakarta is increased rapidly. The wage that Many transportations are causing a traffic jam in Jakarta. The government suggests that people use public transportation for their mobility. However, people choose to use their vehicles rather than public transportation. The main reason is that public transportation cannot guarantee the arriving time, whether it is on time or not. Many people move on to online transportation services. However, the massive growth of online transportation is still a contradiction as public transportation. People in Jakarta need faster mobility to go. This research is trying to make a system for public transport without any delay and hard to use it. This problem can be solved by building a new system. This system required e-wallet for payment in public transportation. This E-Wallet will search the possible route from the nearest location to the destination - only the public transport where there is a station that can use it. By using QR-Code generated by e-wallet on the mobile phone, people can scan it directly to a machine located in the station. This method will make a transaction faster than ever. Moreover, people can enjoy another feature like cashback and redeem the prize by a point system. In this era, e-commerce is dominating the market for purchasing something. This is also the attraction of the system. This system is also required excellent facilities from the government so that people can enjoy it. © Published under licence by IOP Publishing Ltd.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Smartphone Application for Badminton sports community 2

Smartphone Application for Badminton sports community

引用

2nd International Conference on computer, science, Engineering, and Technology, ICComSET 2019

作者： Anwar, Nizirwan Hendroasali, Eric Heryanto Budiyanto, Teddy Hendyan, Willy Warnars, Harco Leslie Hendric Spits Faculty of Computer Science Esa Unggul University Jakarta Indonesia Information Systems Department School of Information Systems Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program - Doctor of Computer Science Bina Nusantara University Jakarta Indonesia

Nowadays, there are so many people in Indonesia particularly young people who are interested in playing badminton, but at the end of the day, this game will make boring for young people particularly with the booming of the smartphone game. Literally, it will make the young generation too lazy for outing activity or doing sports and busy with their digital technology, particularly their smartphone. Obviously, we are interested in using the mobile application which can be used to bridge the boring of doing sports mainly badminton sport, wherewith this mobile application is not just only for field badminton or coach booking, but can extend their friendship and community in positive ways. Hopefully, with this mobile application not just only booking for Badminton fields, but beyond that, there will be a mobile application that supports the fans of the badminton sports community when can know each other from different places and make friendship and competition among the members. At the end of the day, we hope this mobile application will support young people to stay away from trouble and drug and to have a positive life with the sport, particularly badminton sport as Indonesian's favorite sport. © Published under licence by IOP Publishing Ltd.

关键词： Sports

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：