检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wianto, Elizabeth Toba, Hapnes Malinda, Maya Chen, Chien-Hsu Bachelor Program in Visual Communication Design Universitas Kristen Maranatha Indonesia Master Program in Computer Science Universitas Kristen Maranatha Indonesia Bachelor Program in Management Universitas Kristen Maranatha Indonesia Industrial Design Department National Cheng Kung University Taiwan

Maintaining a high quality of life through physical activities (PA) to prevent health decline is crucial. However, the relationship between individuals' health status, PA preferences, and motion factors is complex. PA discussions consistently show a positive correlation with healthy aging experiences, but no explicit relation to specific types of musculoskeletal exercises. Taking advantage of the increasingly widespread existence of smartphones, especially in Indonesia, this research utilizes embedded sensors for Human Activity Recognition (HAR). Based on 25 participants' data, performing nine types of selected motion, this study has successfully identified important sensor attributes that play important roles in the right and left hands for muscle strength motions as the basis for developing machine learning models with the LSTM algorithm. © 2024, CC BY-SA.

关键词： Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Single Image Perspective Grid System on Floor Surface for 2D to 3D Transformation

Single Image Perspective Grid System on Floor Surface for 2D...

引用

International Conference on Computing, Engineering, and Design (ICCED)

作者： Darma Rusjdi Edi Abdurachman Yaya Heryadi Gede Putra Kusuma Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9781665453905

Our study discusses the application of the perspective grid concept as the basis for the process of transforming the 2D coordinates of the image into 3D coordinates in real space for estimating the location of objects in a single image scene. In several other studies in the field of robotics, AR use methods and media in the form of a chessboard box as a reference for camera calibration and location estimation. However, it does not show accurate results for the size of objects in the room. We saw the potential areas of Alberti's perspective grid, which is often used as a reference in making sketches for the arts and various engineering fields so that they are visually precise with reality. Our study uses 6 reference points in a room arrangement with a floor grid pattern as a reference for the formation of a perspective grid. Based on the triangle comparison approach to determine the x-ordinate, the average error is 0.2193. And through 3 interpolation approaches to get the most accurate results with the Lagrange and Newton methods on the 6th order with the average difference between the actual and predicted points of 1.5 cm from the y-direction distance of the camera from 2 meters to 6.80 meters.

关键词： Meters Interpolation Three-dimensional displays Robot kinematics Robot vision systems Estimation Media

来源：评论

学校读者我要写书评

暂无评论

Feasibility Study of Semi-supervised Intrusion Detection Systems for Industrial Control Systems

Feasibility Study of Semi-supervised Intrusion Detection Sys...

引用

International Conference on Applied System Innovation (ICASI)

作者： Fu-Nie Loo Tung-Shou Chen Chia-Wei Tsai Jason Lin Chun-Wei Yang Department of Computer Science and Information Engineering National Taichung University of Science and Technology Taichung City Taiwan Department of Computer Science and Engineering National Chung Hsing University Taichung City Taiwan Master Program for Digital Health Innovation China Medical University Taichung City Taiwan

ISBN: (数字)9798350394924

ISBN: (纸本)9798350394931

Industrial Control systems (ICS) automate industrial processes but also introduces cybersecurity threats. Intrusion Detection System (IDS) are crucial for detecting cyber-attacks on ICS, yet zero-day attacks are often inefficiently detecting with supervised learning. This study employs semi-supervised learning using one-class SVM, isolation forest, and Local Outlier Factor (LOF), to train IDS models. Utilizing dataset collected from a self-build virtual ICS environment, the study demonstrates the feasibility of these models in detecting common attack like Injection, ARP, and Man-in-the-Middle.

关键词： Training Support vector machines Technological innovation Supervised learning Intrusion detection Forestry Semisupervised learning

来源：评论

学校读者我要写书评

暂无评论

Leveraging regression models for rule based complex event processing

Leveraging regression models for rule based complex event pr...

引用

International Conference on Electrical Engineering, computer science and Informatics (EECSI)

作者： Shashi Shekhar Kumar Ashutosh Kumar Ritesh Chandra Sonali Agarwal Mohammad Syafrullah Krisna Adiyarta Dept.of Information Technology IIIT Allahabad Prayagraj India Program of Master of Computer Science Universitas Budi Luhur Indonesia Budi Luhur Indonesia

In recent times, IoT devices have surged enormously, which creates a lot of raw data that is dynamic in nature, and processing it in real time to find useful information is challenging. Complex event processing involves the analysis of large volumes of real-time data to identify patterns and events of interest. These events are formed based on a predefined set of rules, and since rules are created by domain experts and for dynamic data, there is a requirement for a robust model that can eliminate manual intervention for rule generation. In this paper, to help the domain experts, a regression-based model is proposed so that more accurate decision-making can be performed by finding more robust event patterns. For regression-based rule implementation, three models are compared: logistic regression, ridge regression, and support vector machine. The models are trained using an IoT temperature dataset and tested using a synthetically generated dataset with the same set of *** ridge regression performed best among all the models, with an accuracy, precision, recall, and f1 score of 99% 97% 96% 95% among all. The entire experiment was carried out with the apache flink ecosystem and pattern API.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Systematic Literature Review of Deep Learning Application in Multiclass Anomaly Detection for Chest Medical Imaging

A Systematic Literature Review of Deep Learning Application ...

引用

International Conference of computer and Informatics Engineering (IC2IE)

作者： Philips Bens Pardamean Gregorius Natanael Elwirehardja Mahmud Isnan Computer Science Department BINUS Graduate Program - Master of Compuer Science Bina Nusantara University Jakarta Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia

Medical imaging abnormality detection is challenging, but deep learning approaches have shown promise. This paper reviews the current state of the art in deep learning approaches for detecting abnormalities in chest medical imaging. To discover the trends, opportunities, and challenges associated with this field, 18 studies were selected from Google Scholar based on their titles, abstracts, and contents for extensive review to answer two research questions. The study found that the National Institutes of Health (NIH) Chest X-ray 14 dataset is the most used dataset for this task. Most research uses a single-modal approach, considering only image data as input, with X-ray being the more popular instrument. There are 8 out of 18 studies leverage the transfer learning approach, with ResN et50 being the most popular network. MobileNetV2 has demonstrated competitive results compared to more robust networks. Preprocessing techniques such as image enhancement and data augmentation are leveraged by 61.1 % of the reviewed studies and are shown to improve model performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Efficient Traffic Sign Detection and Recognition for Taiwan Road Using YOLO Model with Hybrid Dataset

The Efficient Traffic Sign Detection and Recognition for Tai...

引用

International Conference on Applied System Innovation (ICASI)

作者： Taweelap Suwattanapunkul Lung-Jen Wang International Master Program in Information Technology and Applications National Pingtung University Taiwan Department of Computer Science and Information Engineering National Pingtung University Taiwan

According to the trend of worldwide car sales have grown up, this cause may increase accidents on the road due to human error. The self-driverless car has been developed to solve this problem. One task of the self-driverless car is traffic sign detection and recognition (TSDR), which will help drivers notify the traffic sign installed on the road in advance. Taiwan roads have specific traffic signs, and no Taiwan traffic sign public dataset is available. In this paper, our proposed object detection method was experimentally performed using YOLOv5s6 and YOLOv8s models on three different datasets, as Tsinghua-Tencent 100K (TT100k), the self-created Taiwan traffic sign (TWTS), and the hybrid dataset, which combine the traffic scenes between TT100k and TWTS dataset. The output results from each dataset and each model, which is trained on the same parameter, will be compared to validate the proposed method. The experiment results’ comparison of the hybrid dataset between YOLOv5s6 and YOLOv8s models display the results of the mAP@.5 is about 65% and 76.2%, respectively, which means the performance of the YOLOv8s is higher than the YOLOv5s6 when using hybrid dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hate Speech Text Classification Using Long Short-Term Memory (LSTM)

Hate Speech Text Classification Using Long Short-Term Memory...

引用

International Conference of computer science and Information Technology

作者： Suminar Ariwibowo Abba Suganda Girsang Diana Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9798350399080

This paper aims to build hate speech text classification model by applying a combination of LSTM and FastText. The features of hate speech & non-hate speech, target hate speech, and categories of the hate speech. Dataset of those features taken from previous research by Okky Ibrohim. FastText word embeddings is used for formation of text vectors that will be used as input of the LSTM training model. The evaluation results obtained by getting the level of accuracy using confusion matrix. The accuracy value of text classification in this study is 83.52% on the classification of hate speech, 78.44% on the classification of target labels for hate speech, 82.75% on the classification of the label for category of hate speech.

关键词： Training computer science Dictionaries Hate speech Text categorization Bit error rate Information technology

来源：评论

学校读者我要写书评

暂无评论

Twitter-based Sentiment Analysis for Indonesian Drug Products using Supervised Feature Engineering

Twitter-based Sentiment Analysis for Indonesian Drug Product...

引用

International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)

作者： Kartika Purwandari Nicholaus Hendrik Jeremy Panji Arisaputra Samuel Philip Derwin Suhartono Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta Indonesia

Social media communications offer valuable feedback to firms about their products. Twitter users share their opinions about e-commerce products on social networking sites. This paper reports a study in sentiment classification for Indonesian drug products for automatically classifying Twitter data as expressing positive or negative sentiments or opinions. The study investigates the effectiveness of using a Decision Tree, Support Vector Machine, Random Forest, Na rve Bayes, and Logistic Regression, along with the term frequency-inverse document frequency used to classify 531 tweets into recommended (positive sentiment) and not recommended (negative sentiment). Among all traditional machine learning models, the highest average accuracy value is 88.6 in the RF model and the lowest average accuracy value is 80.2 when using the LR model. Judging from the average accuracy obtained, the DT and RF model used has a considerable performance

关键词： Drugs Support vector machines Seminars Analytical models Sentiment analysis Social networking (online) Blogs

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Decision Support Model on Virtual Plant Computational Model of Water Spinach (Ipomoea aquatica. Forssk) in Farming Business

Fuzzy Decision Support Model on Virtual Plant Computational ...

引用

International Conference on Information Technology, Information Systems and Electrical Engineering (ICITISEE)

作者： Ditdit Nugeraha Utama Ika Diah Agustia Rachmawati Heraldo Yusron Purwantono Computer Science Department Binus Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

Using soil as a planting medium (conventional system) raises several problems, such as the need for large agricultural land, but the available land is limited. This problem is triggered by an increase in demand for nutrients needed by the body to support daily activities, one of which can be met by consuming green vegetables, such as Water Spinach. To solve this problem, a hydroponic wick system or a wick system can use that is simple and easy to care for. Water Spinach (Ipomoea aquatica. Forssk) vegetables are easy to grow and care for. Nutrients contained in 100 grams of Water Spinach, energy: 29 kcal, protein: 3 grams, Fat: 0.3 grams, carbohydrates: 5.4 grams, calcium: 73 mg, phosphorus: 50 mg, iron: 3 mg, vitamin A: 6300IU,vitamin B1: 0.07 mg, vitamin C: 32 mg. In addition, a combination of disciplines such as mathematics, computer science, plant science, biology, and statistics can be used. This combination of knowledge is known as Plant Computational Modeling (PCM), which uses the Growth Grammar Interactive Modeling Platform (GroIMP) with the Functional Structural Plant Modeling (FSPM) method. The virtual plant model was successfully built, the results were divided into two parts, such as single plant and multi-plant. Plant computational modeling and DSM can help deal with agricultural problems. By using a plant dataset, the GroIMP-FSPM platform, and fuzzy logic, the model could help researchers in making a better decision based on BEP evaluation. The minimum numbers of plants cultivated were 650 plants in one harvest period in order to gain a desirable profit. We recommend to cultivate even more plants in one harvest period to gain even higher profits.

关键词： Proteins Phase change materials Computational modeling Plants (biology) Soil Phosphorus Mathematical models

来源：评论

学校读者我要写书评

暂无评论

Rule Extraction using Machine Learning Classifiers for Complex Event Processing

Rule Extraction using Machine Learning Classifiers for Compl...

引用

International Conference on Electrical Engineering, computer science and Informatics (EECSI)

作者： Shashi Shekhar Kumar Ashutosh Kumar Ritesh Chandra Sonali Agarwal Mohammad Syafrullah Krisna Adiyarta Dept. of Information Technology IIIT Allahabad Prayagraj India Program of Master of Computer Science Universitas Budi Luhur Indonesia Budi Luhur Indonesia

The large volume of data processing is always challenging for real-time applications. These applications need an optimal framework for handling large scale data and correlating these streams in real time to make better decision making. Complex event processing has emerged as a novel methodology for handling event streams based on atomic events or complex events to find useful patterns by predefined *** play a major role in these systems and the streams are matched with rules created through a decision tree and machine learning classifier algorithms. In this research work, we propose a complex event processing based framework for rule extraction as well as a comparative analysis of rule-based classifier algorithms for automatic extraction of rules, and since event rules are based on human expertise, sometimes they fail due to a static approach, therefore there is a need for an automatic rule extraction *** comparative analysis is performed using a case study of an air quality dataset that outperformed traditional approaches to rule extraction for stream data. Decision tree fetched most number of rules with an accuracy of 99%.The classifier’s learning rate show how efficiently the rule are fetched.

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：