检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Putra, Danendra Athallariq Harya Muharram, Arief Purnama Master Program of Informatics School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia

Sentiment analysis using big data from YouTube videos metadata can be conducted to analyze public opinions on various political figures who represent political parties. This is possible because YouTube has become one of the platforms for people to express themselves, including their opinions on various political figures. The resulting sentiment analysis can be useful for political executives to gain an understanding of public sentiment and develop appropriate and effective political strategies. This study aimed to build a sentiment analysis system leveraging YouTube videos metadata. The sentiment analysis system was built using Apache Kafka, Apache PySpark, and Hadoop for big data handling;TensorFlow for deep learning handling;and FastAPI for deployment on the server. The YouTube videos metadata used in this study is the video description. The sentiment analysis model was built using LSTM algorithm and produces two types of sentiments: positive and negative sentiments. The sentiment analysis results are then visualized in the form a simple web-based dashboard. © 2023, CC BY.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

ConvNeXt Model for Breast Cancer Image Classification 6

ConvNeXt Model for Breast Cancer Image Classification

引用

6th International Conference on Cybernetics and Intelligent System, ICORIS 2024

作者： Setiawan, Devin Karnyoto, Andrea Stevens Intan, Indo Pardamean, Bens Department of Electrical Engineering and Computer Science University of Kansas Lawrence United States Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Department of Informatics Engineering Universitas Dipa Makassar Makassar Indonesia Computer Science Department BINUS Graduate Program Computer Science Program Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9798331539603

Breast cancer is an occurrence of cancer that attacks breast tissue and is the most common cancer among women worldwide, affecting one in eight women. In this modern world, breast cancer image classification simplifies the process of analyzing, providing objective and accurate results. By leveraging machine learning algorithms and computer vision techniques, we developed breast cancer detection. The dataset is histopathology dataset from BreakHis and UNHAS Hospital. We chose the ConvNeXt-Tiny model then modified the classifier head as the proposed method. Before the dataset is processed by the model, we augment the images by applying random horizontal and vertical flips, adjustments to brightness, contrast, saturation, and hue using color jitter. The augmentation process simulates real-world variance and enhances the model's ability to generalize to unseen data. Our proposed model gained better performance (accuracy, F1-Score) results compared two other techniques to VGG16 and SVM. According to our experiments, the F1-Score for the ConvNeXt-Tiny model with classifier head modification is higher at 0.9516, than the gain for VGG16 at 0.9292, and the gain for the SVM at 0.83. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Multi-task Learning Graph Neural Networks for Cancer Prognosis Prediction with Genomic Data 46

Multi-task Learning Graph Neural Networks for Cancer Prognos...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Lin, Tsung-Wei Arriagada, Sofia Ormazabal Lin, Che Taiwan Taiwan International Graduate Program AIoT Ntu Taiwan Research Center for Information Technology Innovation Academia Sinica Taiwan Department of Electrical Engineering Ntu Taiwan Center for Advanced Computing and Imaging in Biomedicine Ntu Taiwan Smart Medicine and Health Informatics Program Ntu Taiwan

ISBN: (纸本)9798350371499

Providing robust prognosis predictions for cancers with limited data samples remains a challenge for precision oncology. In this study, we propose a novel approach that combines multi-task learning (MTL) and graph neural networks (GNNs) to address this issue. By representing gene-gene interactions as a graph network, our approach leverages multi-task learning to effectively capture the relationships of genes relevant to the oncogenesis and progression of breast, lung, and colon cancer. We demonstrate that our approach improves the cancer prognosis prediction for cancers with fewer samples, such as colon adenocarcinoma, by leveraging the shared gene-gene interactions across different cancer types, obtaining increases in the area under the precision-recall curve (AUPRC) of 24%. Our work contributes to the field of smart healthcare by demonstrating the potential of MTL and GNNs for enhancing cancer prognosis prediction, even with limited data samples. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Augmented Reality Application for Book Detection with Google Colaboratory and SnapML Lens Studio 8

Augmented Reality Application for Book Detection with Google...

引用

8th IEEE International Conference on Computing, engineering and Design, ICCED 2022

作者： Saputri, Galuh Suwamo, Joko Fuadi, Achmad Lutfi Heri Yunial, Agus Universitas Pamulang Program Study Informatics Engineering Faculty of Engineering Jl.Raya uspitek serpong No. 10 Tangerang Selatan Indonesia

ISBN: (纸本)9781665453899

Artificial intelligence is one of the technological breakthroughs in science, especially in the field of computers. Object detection and recognition presents a new challenge on how to make machines detect objects automatically. To detect an object, the previous system will take the classifier of an object and evaluate it at various locations and various scales in the image. Smartphones currently play an important role in everyday life, but the existence of smartphones can be one of the causes of the user's lack of interest in reading books. With this Augmented Reality-based object detector, it is hoped that users can experiment on smartphones with the Snapchat application installed to detect objects in books that are around them and the number of objects will be counted automatically, it is also expected to attract users' desire to read books. Image recognition identification is taken through the phone's camera which is recognized as a lens. Lens AR in the Lens Studio application is supported by the SnapML machine learning algorithm, this machine learning function is to display book information and the number of books detected. This research was conducted using Cloud Computing such as Google Collaboratory which uses the python programming language, the book object dataset is selected from the COCO class, the model is exported to Open Neural Network Exchange (.ONNX) and then imported into the Lens Studio application. Publish lenses in the Snapchat app. Finally, a model test was carried out to detect objects and the number of objects in books that had been made using a Smartphone. Open the Snapchat application, scan the Snapcode generated by Lens Studio, AR lenses can be used in real time. AR Book Detection has been tested by other users on Snapchat with 18,845 Lens Views, 18,737 Lens Plays and 16 Lens Shares. © 2022 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Real-Time Hand Gesture Recognition for Humanoid Robot Control Using Python CVZone 7th

Real-Time Hand Gesture Recognition for Humanoid Robot Contro...

引用

7th International Conference on Smart City Applications, SCA 2022

作者： Baihaqi, Muhammad Yeza Vincent Simatupang, Joni Welman Graduate Institute of Automation and Control College of Engineering National Taiwan University of Science and Technology Taipei Taiwan School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia Study Program of Electrical Engineering President University Bekasi Indonesia

ISBN: (纸本)9783031268519

Humanoid robot is able to mimic repetitive activities done by human. By having them, humans can focus on tasks that require extra focus, while leaving the simple one to be done by humanoid robot. To extend the functionality of the 3D-printed upper-body humanoid robot, a camera along with a machine learning algorithm is implemented. In this case, their responses can be categorized based on the gesture it sees. In this paper, the authors evaluate the performance of an upper-body humanoid robot that implements CVZone. The method of evaluation is conducted under three different distances, and each distance has three different brightness levels. It is found that the success rate is highest at the shortest distance which is 50 cm, and under medium-lighted environment. As the distance increases, the hand gesture gets harder to differentiate. At the same time, low or high brightness environment makes the image that contain hand gesture hard to interpret, thus lowering the success rate. Finally, hand gesture that involves third and little finger has the lowest success rate of 75%, while the movement that involves three fingers simultaneously has the second lowest success rate of 80.9%. Meanwhile, simple hand gesture such as clenched-fist or lifting a thumb has 100% success rate under all condition. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

Design of Waste Management System Using QR Code for Effective Management in Wastebank 1

Design of Waste Management System Using QR Code for Effectiv...

引用

1st Paris Van Java International Seminar on Computer, Science, engineering, and Technology, PVJ ISComSET 2020

作者： Widaningsih, S. Suheri, A. Informatics Engineering Program Suryakancana University Cianjur Indonesia

Waste management is one of the problems faced in almost every city in Indonesia. One way to manage waste is through the waste bank. The business process of a waste bank is similar to a bank, but it is processed in the form of inorganic waste that has been sorted. In general, data management in waste banks is still conventional but the others have used of web-based or mobile technology. But in this way there are still some weaknesses such as the the time needed to input the collected waste data because the data cannot be directly entered into the system. In addition it can occur inaccurately entered data. The proposed method is using the QR code for the waste management system. In this method, admin only need to scan the QR code label attached on the waste bin stored above the weighing device using a smartphone camera. With this system QR scanner application based on mobile can be synchronized automatically with anroid smartphone. Admin then input the weight of the waste that is weighed and will be stored in the database. In this way the data input process can be faster and with the use of QR code, more data can be stored. © Published under licence by IOP Publishing Ltd.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Identification of Software Bugs by Analyzing Natural Language-Based Requirements Using Optimized Deep Learning Features

引用

Computers, Materials & Continua 2024年第3期78卷 4379-4397页

作者： Qazi Mazhar ul Haq Fahim Arif Khursheed Aurangzeb Noor ul Ain Javed Ali Khan Saddaf Rubab Muhammad Shahid Anwar Department of Computer Science and Engineering and International Bachelor’s Program in Informatics Yuan Ze UniversityZhongliTaoyuan320315Taiwan Department of Computer Science National University of PakistanRawalpindiPunjab46000Pakistan Department of Computer Software Engineering MCSNational University of Sciences and TechnologyIslamabad44000Pakistan Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityP.O.Box 51178Riyadh11543Saudi Arabia Department of Computer Science School of PhysicsEngineering and Computer ScienceUniversity of HertfordshireHatfieldAL109ABUK Department of Computer Engineering College of Computing and InformaticsUniversity of SharjahSharjah27272United Arab Emirates Department of AI and Software Gachon UniversitySeongnam-SI13120South Korea

Software project outcomes heavily depend on natural language requirements,often causing diverse interpretations and issues like ambiguities and incomplete or faulty *** are exploring machine learning to predict software bugs,but a more precise and general approach is *** bug prediction is crucial for software evolution and user training,prompting an investigation into deep and ensemble learning ***,these studies are not generalized and efficient when extended to other ***,this paper proposed a hybrid approach combining multiple techniques to explore their effectiveness on bug identification *** methods involved feature selection,which is used to reduce the dimensionality and redundancy of features and select only the relevant ones;transfer learning is used to train and test the model on different datasets to analyze how much of the learning is passed to other datasets,and ensemble method is utilized to explore the increase in performance upon combining multiple classifiers in a *** National Aeronautics and Space Administration(NASA)and four Promise datasets are used in the study,showing an increase in the model’s performance by providing better Area Under the Receiver Operating Characteristic Curve(AUC-ROC)values when different classifiers were *** reveals that using an amalgam of techniques such as those used in this study,feature selection,transfer learning,and ensemble methods prove helpful in optimizing the software bug prediction models and providing high-performing,useful end mode.

关键词： Natural language processing software bug prediction transfer learning ensemble learning feature selection

来源：评论

学校读者我要写书评

暂无评论

Design Technology of Geographical Information System of Rice Pandanwangi Cianjur Prediction Factors Products 1

Design Technology of Geographical Information System of Rice...

引用

1st Paris Van Java International Seminar on Computer, Science, engineering, and Technology, PVJ ISComSET 2020

作者： Musrifah, Ai Adikusuma, Andri Sutono Informatics Engineering Study Program Faculty of Engineering University of Suryakancana Indonesia

Cianjur is one of the renowned rice producers, particularly with the presence of Pandanwangi rice that can be grown in the Cianjur area. Pandanwangi has become one of Cianjur City's icons, the rice supremacy created by Pandanwangi Cianjur's tenacity and distinctive scent (pandanus fragrance). The Interest of pandanwangi was very high, both within the town of Cianjur and outside the town of Cianjur, but this was inversely proportional to the desires of the groups of farmers who appeared to prefer to plant rice other than Pandanwangi, on the grounds that the planting of Pandanwangi had a long harvest and that the likelihood of crop failure was also very high. Problems with information flows that are not well integrated between farmers' groups, farmers' group organizations, and the Agriculture Department in adjusting land details, planting time, planting location, estimating total harvest and harvesting time. To solve this problem, a framework must be built that can integrate the information needed for Pandanwangi Cianjur Harvest Prediction with Pandanwangi farmers' regional analysis based on geographic information system technology, using Google Maps Service. © Published under licence by IOP Publishing Ltd.

关键词： Harvesting

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Multi Class Support Vector Machine vs Deep Convolutional Neural Network for Brain Tumor Classification

A Comparison of Multi Class Support Vector Machine vs Deep C...

引用

2023 International Seminar on Application for Technology of Information and Communication, iSemantic 2023

作者： Cahyo, Nur Ryan Dwi Sari, Christy Atika Rachmawanto, Eko Hari Jatmoko, Cahaya Al-Jawry, Rabei Raad Ali Alkhafaji, Mohamed Ayad University of Dian Nuswantoro Department of Informatics Engineering Semarang Indonesia University of Dian Nuswantoro Study Program in Informatics Engineering Semarang Indonesia Northern Technical University Department Computer Science Semarang Indonesia Northern Technical University Department of Computer Engineering Technology Mosul Iraq National University of Science and Technology Department of Computer Sciece DhiQar Iraq

ISBN: (纸本)9798350339215

Multi SVM has long been one of the popular methods in classification, while DCNN has recently gained significant attention in image processing and pattern recognition. This research evaluates the effectiveness of Multi Class Support Vector Machine (M-SVM) and Deep Convolutional Neural Network (DCNN) techniques in classifying brain tumors. A dataset of 2660 3D medical images with dimensions 227 x 227 x 3;including Glioma, Meningioma, and Pituitary tumors, has been partitioned into distinct sets for both training and testing purposes. DCNN approach achieves excellent accuracy in identifying tumor names, with a training accuracy of 97.8% and 100% success rate in 9 experiments. The Multi SVM method demonstrates relatively good accuracy, with training accuracies ranging from 70% to 90% based on different kernel functions. These findings provide valuable insights for selecting appropriate methods in brain tumor classification and encourage further exploration of hybrid Multi SVM-DCNN approaches to enhance accuracy and reliability. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Multiplayer Ludo Game Application Based on Mixed Reality Using UrhoSharp and RabbitMQ Message Broker 9

Multiplayer Ludo Game Application Based on Mixed Reality Usi...

引用

9th International Conference on Wireless and Telematics, ICWT 2023

作者： Sukoco, Agus Apriliansyah, Aghil Alfhauzhi Nurmalasari, Rin Rin Pratama, Vitradisa Prihatmanto, Ary Setijadi Juhana, Agus School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia Uin Sunan Gunung Djati Department of Electrical Engineering Bandung Indonesia Universitas Pendidikan Indonesia Multimedia Education Study Program Bandung Indonesia

ISBN: (纸本)9798350305029

This paper describes the design and implementation of the Ludo game on Microsoft Hololens to create a mixed reality-based application with Hololens technology connected to many services. The Ludo game is made for two players, with player one playing on Hololens and player two sending and receiving player one's data via the console. The Ludo game with Hololens is one of the results of the development of Hololens technology and the RabbitMQ Messaging Server. The Ludo game is made on Visual Studio software using UrhoSharp Framework and RabbitMQ Messaging Server service with the AMQP protocol. As application frameworks, Hololens and UrhoSharp function as devices for visualization and running games. At the same time, the RabbitMQ Messaging Server and AMQP protocol serve as services that connect two players from the Hololens and console by sending the data needed by the application. The test results show that Hololens is running successfully and communicating with other console players. Thus, the results obtained are the purpose of this paper, which is to create a mixed reality-based application with Hololens technology connected to many services. © 2023 IEEE.

关键词： Mixed reality

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：