检索结果-内蒙古大学图书馆

Identification of Features in ANN's Black Box using Dimensional Reduction and Correlation Analysis: A Case Study of Cardiovascular Disease Dataset

Identification of Features in ANN's Black Box using Dimensio...

引用

International Conference on Advanced Mechatronics, Intelligent Manufacture, and Industrial Automation (ICAMIMIA)

作者： Boby Siswanto Yaya Heryadi Wayan Suparta Antoni Wibowo Haryono Soeparno Lukas Computer Science Department BINUS Graduate Program-Doctor of Computer Science Bina Nusantara University Jakarta Indonesia Cognitive Engineering Research Group (CERG) Atma Jaya University Jakarta Indonesia

ISBN: (纸本)9781665499705

Artificial Neural Network (ANN) is a machine learning algorithm that can perform classification. ANN has limitations; namely, it has a black box working principle, which is unsure which feature is the most influential. This study is to identify the most influential features inside the ANN's black box using a classification model by applying Principal Component Analysis (PCA) dimension reduction combined with Pearson correlation analysis. The result of the proposed model can identify the name of the main features of the data inside the ANN's black box. This study uses two public Kaggle cardiovascular datasets. The first dataset consists of 13 features, and the second dataset consists of 12 features. The result is height and gender are the most influential features in the first dataset with the correlation value of 0.734; sex and smoking are the most influential features in the second dataset with the correlation value of 0.728. Black box model result with 2 PCA's features against a model with height and gender features in the first dataset resulting from the same accuracy on the test dataset of the classification prediction results with the value of 49.90%, while on the second dataset 58.30%.

关键词： Dimensionality reduction Analytical models Correlation Mechatronics Machine learning algorithms Artificial neural networks Predictive models

来源：评论

学校读者我要写书评

暂无评论

Communicaton On Mobile Phone For The Deaf Using Image Recognition

Communicaton On Mobile Phone For The Deaf Using Image Recogn...

引用

International Conference on Information Management and Technology (ICIMTech)

作者： Benfano Soewito Alexander Khrisna Satyadhana Raymond Sarah Maria BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia School of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9781728170718

ISBN: (纸本)9781728170725

Sign language is an absolute thing that is mastered by some people, especially people who have hearing or deaf problems. Problems will occur if they want to communicate via mobile devices. They have to use an application that translate sign language to text and vice versa. The research in this field still open because each language will have different sign language. In the other hand the image that was captured by the mobile devices depend on the environment such as brightness and the background. The sign language captured with static background has high accuracy compared with dynamic background that has colorful background. Most of research do not include the dynamic background. Therefore in this study introduced an application used image recognition that can translate sign language with dynamic background into a text so that it can be used to communicate among people who have hearing problems and also between deaf and normal people. The experimental showed that accuracy of our system is 87%.

关键词： Assistive technology Gesture recognition Auditory system Artificial neural networks Neurons computer science Mobile handsets

来源：评论

学校读者我要写书评

暂无评论

Mobile application for the futsal sports community in Jakarta

Mobile application for the futsal sports community in Jakart...

引用

Artificial Intelligence and Smart Systems (ICAIS), International Conference on

作者： Farel Darari Deksano Dimas Raka Erfiandhi Anggy Cahya Prasetya Aditya Satria Nagara Patmuryanto Harco Leslie Hendric Spits Warnars School Of Information Systems Bina Nusantara University Jakarta Indonesia BINUS Graduate Program—Doctor of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9781728195377

ISBN: (纸本)9781728195384

The rapid development of technology makes many changes that occur in the community in carrying out daily activities, one of which is the use of online-based applications to support community activities in Jakarta. This study aims to build applications to support community activities in the field of futsal sport, namely ordering Android-based sports arenas. This ordering application consists of Home, Schedule, sparring, profile, info, and ordering. This application makes it easier for people to find information about the sports arena and make it easier to order sports fields anytime, anywhere, so they can increase profits for the sports arena business. This mobile application was applied with android studio and using MySQL for the database. Hopefully, creating this mobile application will reduce the number the crime rate committed by youth and expand their friendship not only around their house or school but for future development it is possible to run a competition that can be held at the provincial level, or at the national level and possibly even at the South East Nation country (ASEAN) level which involving several ASEAN countries.

关键词： computer science Schedules Databases Mobile applications Artificial intelligence Sports Business

来源：评论

学校读者我要写书评

暂无评论

Digitizing Farmers' Land Data Collection Systems in Indonesia with the Use of Tani Millenial Apps

Digitizing Farmers' Land Data Collection Systems in Indonesi...

引用

International Conference on Cybernetics and Intelligent System (ICORIS)

作者： Mohammad Prasanto Bimantio Dian Pratama Putra Teddy Suparyanto Amallia Ferhat Nanda Satya Nugraha Alam Ahmad Hidayat Bens Pardamean Department of Food and Agricultural Technology Institute of Agriculture STIPER Yogyakarta Indonesia Department of Agrotechnology Institute of Agriculture STIPER Yogyakarta Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Department of Agricultural Socio-Economics Institute of Agriculture STIPER Yogyakarta Indonesia Department of Forestry Institute of Agriculture STIPER Yogyakarta Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9781665453967

In this era of digital world information, farmers face challenges about information management of huge data and the complexity of processes in precision farming. The data collection carried out so far can cause several difficulties, especially if the data is needed by the government or academics to support decision-making. Agricultural data collection applications only cover 12% of the market share of Android-based agriculture-based applications. In this study, Tani Milenial application is present as an alternative to support agricultural data collection activities in Indonesia. This application encourages farmers to be active and contribute independently to their role as subjects of agricultural development and is accustomed to digitally recording their agricultural activities. In this developed application system, the community, especially farmers and farmer groups, will find it easier to get information about agricultural potential data around where they carry out agricultural activities and can access this information online. Tani Milenial works as a guide to help farmers and transform agriculture but still have some gaps which should be checked and removed. The data collected can be used by various parties for research and decision-making. The app can be further improved to develop new features related to education, market information, and goods.

关键词： Decision making Education Government Transforms Data collection Agriculture Recording

来源：评论

学校读者我要写书评

暂无评论

Detepet Mobile Application for Pet Tracking

Detepet Mobile Application for Pet Tracking

引用

Emerging Smart Computing and Informatics (ESCI), Conference on

作者： Brian Wijaya Aqraldo Jessen Yuliet Sentoman Deven Markos Harco Leslie Hendric Spits Warnars School of Information System Bina Nusantara University Jakarta Indonesia BINUS Graduate Program – Doctor of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9781728185194

ISBN: (纸本)9781728185200

We have often heard of cases of loss of animals in the world, the owners of these animals are very troubled in looking for lost animals, so often when the pet is lost, the owner leaves it or makes the news of the competition for who can find it. We strive to help these pet owners easily detect the presence of pets they have through a mobile application that we make, namely Detepet that can track all the pets you have, so you are not afraid of losing your pet. In this case, the user should register their pet and the tool GPS necklace will be attached to the pet and the pet will be under monitoring of the systems.

关键词： Heart rate Animals Tools Mobile applications Registers Informatics Monitoring

来源：评论

学校读者我要写书评

暂无评论

Measure the Level of Success in Using Google Drive with the Kuder Richardson (KR) Reliability Method

Measure the Level of Success in Using Google Drive with the ...

引用

2019 International Congress on Applied Information Technology, AIT 2019

作者： Nugroho, Andi Warnars, Harco Leslie Hendric Spits Heriyadi, Yaya Tanutama, Lukas Mercu Buana University and Binus Graduate Program - Doctor of Computer Science Computer Science Department Jakarta Indonesia Binus Graduate Program - Doctor of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9781728158624

The Google Sheets is a cloud technology part of Google Drive. Google Drive is a cloud operating system owned by Google's search engine. National Elementary School (SDN) to make a report book or Basic Education Databook (Dapodik) still use Microsoft Excel, which has the effect of delaying the delivery of report results to parents. This happens because to fill in the DAPODIK score must be filled by teachers who teach subjects in class. This study aims to provide knowledge to teachers in collaborating to fill DAPODIK and measure how reliable the delivery of material received by each teacher. Using the method of reliability Kuder Richardson KR-20 and KR-21 produces a value before the training on reliability values KR-20 = 0.6328, and KR-21 = 0.6000, after the training, the reliability values KR-20 = 0.5788 and KR-21 = 0.6231. From these results, it is known that the value after training for KR-21 has increased and according to the conventional correlation coefficient. In future research can be re-developed by making application system recommendations in determining teachers in schools to become instructors in accordance with the capabilities possessed based on the reliability testing results of the KR-20 and KR-21. © 2019 IEEE.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Realtime Vehicle Counting Method Using Haar Cascade Classifier Model

Realtime Vehicle Counting Method Using Haar Cascade Classifi...

引用

International Conference on Advanced Mechatronics, Intelligent Manufacture, and Industrial Automation (ICAMIMIA)

作者： Prasetyo Mimboro Yaya Heryadi Lukas Wayan Suparta Antoni Wibowo Doctor of Computer Science Graduate Program Faculty of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program Bina Nusantara University Jakarta Indonesia Cognitive Engineering Research Group (CERG) Atma Jaya University Jakarta Indonesia Computer Science Department Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9781665499705

The proliferation of digital camera technology has provided many digital images for object detection and counting in public places. This paper presents an experiment on the realtime vehicle counting method to be implemented in a single board computer. The proposed design's objective is to detect and count vehicles entering and exiting at entrances using haar cascade classifier algorithms and other automatic open and close door systems controlled by a single board computer (SBC). The proposed system was tested using raspberry pi 4 model B with a 4GB RAM platform. The empiric results using 3-minute video as input with a total of 113 passing vehicles the proposed method achieve of 91.2 % of average accuracy.

关键词： Mechatronics Automation Computational modeling Digital images Random access memory Object detection Logic gates

来源：评论

学校读者我要写书评

暂无评论

Pyramid Scene Parsing Net Model for Automated Paddy Field Map using SPOT 6 Satellite Images

Pyramid Scene Parsing Net Model for Automated Paddy Field Ma...

引用

IEEE Asia-Pacific Conference on Geoscience, Electronics and Remote Sensing Technology (AGERS)

作者： Yaya Heryadi Edy Irwansyah Eka Miranda Haryono Soeparno Herlawati Kiyota Hashimoto Computer Science Department BINUS Graduate Program-Doctor of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Information Systems Department School of Information Systems Bina Nusantara University Jakarta Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Faculty of Technology and Environment Prince of Songkla University Phuket Thailand

Food sustainability is still one of the main priorities for many countries as it contributes to the economy and stability of the nation. For government in many countries whose peoples consumes rice as its staple food, food self-sufficiency initiatives highly depend on accurate prediction of paddy field map. Mapping paddy field task is a challenging problem which cannot be handled manually especially when the paddy fields are spread out in very wide geographical areas such as those in Indonesia. Fortunately, wide availability of satellite imagery and the advent of deep learning technology in the past ten years have made it possible to improve efficiency of most parts of those manual works involving image semantic segmentation tasks. However, satellite image-based semantic segmentation is a challenging task. High object complexity, cloud partial occlusion, larger image size than a computer memory can stored can hinder accuracy of the image segmentation results. This paper presents a method for paddy field map generating using semantic image segmentation approach in which Pyramid Scene Parsing Net model is used for segmenting satellite imagery. The generated paddy map can be used as a basis for decision-making, especially in the agricultural sector. Analysis of local land use/land cover dynamics. The results of his experiments using SPOT 6 satellite imagery from the Pahung region of Central Kalimantan achieved average training accuracy, best training accuracy and test accuracy of 0.85, 0.86 and 0.89 respectively. These results indicated that the semantic segmentation model is suitable for addressing the same task in different crops.

关键词： Training Productivity Deep learning Satellites Semantic segmentation Crops Predictive models

来源：评论

学校读者我要写书评

暂无评论

Jakarta Smart City Mobile Application for Problem Reporting

Jakarta Smart City Mobile Application for Problem Reporting

引用

Artificial Intelligence and Smart Systems (ICAIS), International Conference on

作者： Dejan Rivaldo Bongestu Yappiter Harco Leslie Hendric Spits Warnars School of Information Systems Bina Nusantara University Jakarta Indonesia Binus Graduate Program Doctor of Computer Science Bina Nusantara Univerisity Jakarta Indonesia

ISBN: (数字)9781728195377

ISBN: (纸本)9781728195384

This paper discusses the possibility of a better smart city implementation with the Jakarta Information App. Our App will be a one-stop go platform where people could access new information regarding the city live and instantaneously, the information contained is not just from an average news report, but people from social media or communities can also contribute in giving up to date news 24/7. In order to create this app, some processes are done to dive deeper into Jakarta's core infrastructure, the way of living, and the society behind the city. Jakarta Information App's goals are to connect the people everywhere at any time or place; it is not just an average social media app, its main objective is to be some hub for the city, it is an a2-way connected dots, the city with the people and also the reverse. The proposed system has been modeled with a use case diagram to design the business process and using the class diagram to model the database model diagram. The user interface has been designed as a means of communication between the user and the system.

关键词： Smart cities Social networking (online) Databases User interfaces Mobile applications Artificial intelligence Business

来源：评论

学校读者我要写书评

暂无评论

Improved LSTM hyperparameters alongside sentiment walk-forward validation for time series prediction

引用

Journal of Open Innovation: Technology, Market, and Complexity 2025年第1期11卷

作者： Wahyuddin, Eko Putra Caraka, Rezzy Eko Kurniawan, Robert Caesarendra, Wahyu Gio, Prana Ugiana Pardamean, Bens Department of Statistical Computing Politeknik Statistika STIS Jakarta 13330 Indonesia Statistics Indonesia (BPS) Jl. Dr Sutomo 6-8 Jakarta Indonesia School of Economics and Business Telkom University Bandung 40257 Indonesia Research Center for Data and Information Sciences Research Organization for Electronics and Informatics National Research and Innovation Agency (BRIN) Bandung 40135 Indonesia Faculty of Integrated Technologies Universiti Brunei Darussalam Gadong BE1410 Brunei Darussalam Department of Mathematics Universitas Sumatera Utara Medan 20155 Indonesia Bioinformatics and Data Science Research Centre Bina Nusantara University DKI Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program Master of Computer Science Program Bina Nusantara University DKI Jakarta 11480 Indonesia

This study aims to address the common issue of biased estimation errors in time series modeling by analyzing the error in locating ideal hyperparameters and defining appropriate validation methods. Specifically, it focuses on predicting the stock price of Bank Rakyat Indonesia using a combination of historical stock prices, technical indicators, exchange rates, and news sentiment data, while determining the optimal variables for deep learning models. Employing a deep learning-based Long-Short Term Memory (LSTM) model, the study optimizes hyperparameters alongside walk-forward validation for time series prediction. It explores different combinations of variables and adapts the sliding window approach to the context of the data. The results highlight the importance of optimizing hyperparameters and utilizing walk-forward validation for accurate time series prediction. The model incorporating historical stock prices and sentiment scores outperforms others, achieving an RMSE of 96.61 and MAE of 86.97. Incorporating sentiment scores reduces RMSE by 39.55 % compared to models using only historical stock prices, while adding technical indicators does not yield improvement. This study contributes to the field by addressing the issue of biased estimation errors in time series modeling, offering insights into the optimization of hyperparameters and validation methods for accurate predictions. It also underscores the significance of incorporating sentiment analysis alongside historical stock prices for improved forecasting accuracy. © 2024 The Authors

关键词： LSTM Sentiment analysis Stock price prediction Time series modeling Validation methods

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：