检索结果-内蒙古大学图书馆

Designing database lecture model in informatics engineering study program

Journal of Physics: Conference Series 2020年第1期1516卷

作者： C E Supriana Informatics Engineering Study Program Faculty of Engineering Pasundan University Bandung Indonesia

Database lectures in the informatics engineering study program teach the life cycle of database system development, both in terms of concepts, utilization, administration to database application systems to be studied, practiced and understood by students. Database teaching in the informatics engineering department of a private university with very diverse student participants, the ability to master computer and information technology and skills requires teaching material, lecturing strategies, lecturer quality, and facilities must also be able to adjust toward challenges, concept development, and database technology. This database design research model used Hevner's information systems research framework, starting with reference research, database lecture analysis, rigor and research relevance. This research covered the steps of constructing artifacts in the form of constructs, models, methods, instantiation, and evaluation of artifacts. The use of the framework intended to support business strategies and processes in study programs and ensure the relevance of research. The benefits of this research will produce a database lecture model that can be used as a reference and lecture development in the informatics engineering study program. Reference to produce graduates with understanding and skills in database design, the use of Database Management System (DBMS), the ability in administration and professional capability in the database field. This research will be relevant to the study program environment as well as scientific benefits in research and database teaching.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Cyber Security: Deephoax Detection

Deep Learning for Cyber Security: Deephoax Detection

引用

Advanced Innovations in Smart Cities (ICAISC), International Conference on

作者： SY. Yuliani Yakub Rivo Juicer Wowor David Agustriawan Irmawati Dinar Ajeng Kristiyanti P.M. Winarno Rosilah Hassan Roshayu Mohamad Randy Zahran Razzaq Department of Informatics Universitas Multimedia Nusantara Tangerang Indonesia Information System Study Program Universitas Multimedia Nusantara Tangerang Indonesia Center for Cyber Security (CYBER) Universiti Kebangsaan Malaysia Selangor Malaysia College of Computer Science and Engineering University of Jeddah Jeddah Saudi Arabia Department of Informatics UIN Sultan Maulana Hasanuddin Banten Indonesia

ISBN: (数字)9798331506995

ISBN: (纸本)9798331507008

The increasing prevalence of deep hoaxes, such as fake news and phishing schemes, poses a significant threat to cybersecurity, undermining trust and spreading misinformation. In Indonesia, surveys indicate that more than 60% of people exposed to hoax news believe that it is true, emphasizing the urgent need for robust detection methods. Traditional cybersecurity approaches often struggle to keep pace with the growing scale and sophistication of these attacks. To address this challenge, this research investigates the use of deep learning techniques, specifically focusing on text-based hoax detection in the Indonesian language. The study fine-tunes IndoBERT, a pretrained deep learning model optimized for Indonesian text, to enhance the accuracy and scalability of hoax detection. The IndoBERT model was trained on a balanced dataset of 29,552 articles, comprising both hoax and real news content, collected from the Mafindo API and Kaggle's Indonesia News Dataset. The model was fine-tuned using supervised learning and evaluated using several key metrics, including accuracy, F1-score, precision, and recall. The results demonstrate that IndoBERT outperforms existing state-of-the-art approaches, achieving an accuracy of 98.51%, an F1-score of 98.44%, and a precision of 98.23% on the test set. These results highlight the effectiveness of IndoBERT for hoax detection, which offers a scalable solution to improve cybersecurity defenses against deceptive content. This research contributes to the integration of advanced deep learning models into cybersecurity systems, addressing the evolving landscape of cyber threats.

关键词： Deep learning Measurement Training Surveys Adaptation models Technological innovation Accuracy Computer security Fake news Videos

来源：评论

学校读者我要写书评

暂无评论

Connectivity of single neurons classifies cell subtypes in mouse brains

引用

Nature Methods 2025年第4期22卷 861-873页

作者： Liu, Lijuan Yun, Zhixi Manubens-Gil, Linus Chen, Hanbo Xiong, Feng Dong, Hongwei Zeng, Hongkui Hawrylycz, Michael Ascoli, Giorgio A. Peng, Hanchuan New Cornerstone Science Laboratory SEU-ALLEN Joint Center Institute for Brain and Intelligence Southeast University Nanjing China School of Biological Science & Medical Engineering Southeast University Nanjing China Tencent AI Lab Bellevue WA United States UCLA Brain Research and Artificial Intelligence Nexus Department of Neurobiology David Geffen School of Medicine University of California Los Angeles Los Angeles CA United States Allen Institute for Brain Science Seattle WA United States Center for Neural Informatics Bioengineering Department and Neuroscience Program Krasnow Institute for Advanced Study George Mason University Fairfax VA United States Shanghai Academy of Natural Sciences Fudan University Shanghai China

Classification of single neurons at a brain-wide scale is a way to characterize the structural and functional organization of brains. Here we acquired and standardized a large morphology database of 20,158 mouse neurons and generated a potential connectivity map of single neurons based on their dendritic and axonal arbors. With such an anatomy–morphology–connectivity mapping, we defined neuron connectivity subtypes for neurons in 31 brain regions. We found that cell types defined by connectivity show distinct separation from each other. Within this context, we were able to characterize the diversity in secondary motor cortical neurons, and subtype connectivity patterns in thalamocortical pathways. Our findings underscore the importance of connectivity in characterizing the modularity of brain anatomy at the single-cell level. These results highlight that connectivity subtypes supplement conventionally recognized transcriptomic cell types, electrophysiological cell types and morphological cell types as factors to classify cell classes and their identities. © The Author(s) 2025.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Herb compounds screening as meningitis inhibitor candidates using neural network and random forest methods

引用

AIP Conference Proceedings 2025年第1期3250卷

作者： Riska Aprilia Mohammad Hamim Zajuli Al Faroby Muhammad Adib Kamali Muhammad Dzulfikar Fauzi Information Technology Study Program Faculty of Information Technology and Business Institut Teknologi Telkom Surabaya Surabaya Indonesia Data Science Study Program Faculty of Information Technology and Business Institut Teknologi Telkom Surabaya Surabaya Indonesia Informatics Study Program Faculty of Information Technology and Business Institut Teknologi Telkom Surabaya Surabaya Indonesia

Meningitis is an inflammation of the meninges that occurs in the protective lining of the brain and spinal cord caused by bacterial, viral, or fungal infections. This disease is difficult to recognize because it has initial symptoms like the flu where the patient has a fever and headache. Current efforts to prevent the disease by strengthening antibodies. Meanwhile, drug candidates for the treatment of this disease still have not found optimal results in reducing mortality due to meningitis. This study aims to find and analyses herbal compound candidates that might be inhibitors of meningitis. Compound data was acquired from a validated open database. The data acquired are smiles of the chemical bond structure of the compounds. In the data processing process, compound feature extraction is required by applying the concept of molecular fingerprint. The results of feature extraction are used as datasets to build classification models by applying the Multilayer Perceptron (MLP) and Random Forest algorithms. The two models are compared, and a more robust model is selected to be used as a prediction model for herbal compound search. The MLP model has a better accuracy of 0.97 compared to the Random Forest model. The results of screening using the MLP learning model obtained Symphytine, cis-Linalool oxide, and 3-O-Methylcalopocarpin compounds have the highest probability compared to thousands of other herbal compounds. This candidate compound can be used as a recommendation for drug discovery to treat patients who contract Meningitis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network for Cataract Clasification Using Primary Dataset 9

Convolutional Neural Network for Cataract Clasification Usin...

引用

9th International Conference on Business and Industrial Research, ICBIR 2024

作者： Totok Suryawan, I Gede Putra, I Wayan Murmayasa Adi Informatics Engineering Study Program Faculty of Technology and Informatics Denpasar Indonesia

ISBN: (纸本)9798350383010

Cataracts are the main factor causing blindness in Indonesia. Traditional diagnostic methods involving clinical examination by an ophthalmologist using a slit-lamp and visual tests have many challenges such as limited resources, time, and medical expertise may not be available in all locations, especially in less developed areas. Utilizing medical image technology is a wise choice because it allows early detection and monitoring of the development of this cataract disease Technology is needed to identify medical images that have valuable information so that early detection or monitoring of cataract development can be carried out. CNN as a part of deep learning has the ability to perform automatic feature extraction so that it can identify eye images. A CNN model for recognizing cataracts in eye images taken directly from Bhayangkara Hospital in Denpasar Bali has been developed in this research. The model developed is equipped with a dropout layer technique to prevent overfitting. The test results show that the CNN developed in this research produces very good performance with an average accuracy level of 92% on public dataset images, and 94% on primary dataset images. Tested using the primary dataset and public dataset, this CNN model shows very good performance because it can correctly identify an average of 94% of eye images in the primary dataset, and 92% of eye images in the public dataset.. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Secure E-Voting System for Student Associations in Private University Using Paillier Algorithm 21

Secure E-Voting System for Student Associations in Private U...

引用

21st IEEE Student Conference on Research and Development, SCOReD 2023

作者： Tenusa, Ivan Surbakti, Eunike Endariahna Tobing, Fenina Adline Twince Kusnadi, Adhi Universitas Multimedia Nusantara Informatics Study Program Informatics and Engineering Faculty Indonesia

ISBN: (纸本)9798350318821

The representatives of student associations at Private University are entrusted with the responsibility of empowering, facilitating, and nurturing the growth of the students, lecturers, and alumni within their respective programs. If the elected representatives do not align with the general consensus, problems are bound to arise. Therefore, student participation during the annual voting period is of utmost importance. When voting participation is low, the risk of the majority voice not being heard increases. Data from the General Election Commission in the private university reveals that among the four student associations in the Tech and IT Faculty, three of them have a participation rate lower than 50%.This research aims to develop an E-Voting system for Student Associations within the university, with the intention of replacing the currently utilized Google Form system and enhancing student participation in future voting periods. While constructing an electronic voting system, the security and confidentiality of participants are vital. The Paillier homomorphic encryption algorithm is employed in the system to encrypt and decrypt voting messages sent by voters, ensuring their confidentiality. This algorithm was chosen due to its relative recency, speed, and relevance to this research in comparison to other algorithms. A user acceptance test conducted using the Technology Acceptance Model (TAM) has demonstrated that the application has been successfully developed, with user assessments of 87.50% for perceived ease of use, 72.27% for perceived usefulness, 74.74% for behavioral intention, and 86.46% for actual usage. © 2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Personality Analysis Based on The Handwriting Shape using Integration of Image Processing and Machine Learning Algorithm 7

Personality Analysis Based on The Handwriting Shape using In...

引用

7th International Conference on New Media Studies, CONMEDIA 2023

作者： Rosalina Sahuri, Genta Fahmi, Hasanul Moerland, Joe Wesley Mandala, Rila President University Informatics Study Program Indonesia President University Information System Study Program Indonesia President University Magister of Informatics Study Program Indonesia President University Faculty of Computing Indonesia

ISBN: (纸本)9798350307504

In Indonesia, mental health awareness is not as prominent as physical health, and many adolescents have experienced mental health problems. Some people hide their mental and emotional problems by appearing cheerful and peaceful, but research shows that body language and voice tone can reveal a person's inner psychological state. Similarly, handwriting can be analyzed through graphology to reveal personality traits such as honesty, emotional stability, and fears. Graphology is a time-consuming and expensive process, using image processing and machine learning, graphology can be done quickly without human bias. This research aims to predict the personality traits by implement image processing combined with machine learning to analyze handwriting features. Using lazy learner algorithm of K-Nearest Neighbor algorithm, SVM and Naïve Bayes, the application can predict the MBTI personality from handwriting image with an accuracy of 94%, 78%, and 93% respectively. From the experiment, it is shown that the application able to do the analysis of one's handwriting and then predict the personality traits, fully automated using a computer © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Optical character recognition and long short-term memory neural network approach for book classification by librarians 6

Optical character recognition and long short-term memory neu...

引用

6th International Conference on Mathematics, Science, and Education, ICMSE 2019

作者： Rosita, Y.D. Sukmaningtyas, Y.N. Study Program of Informatics Engineering Universitas Islam Majapahit Indonesia

The book is classified by librarians that use Decimal Dewey Classification (DDS) System. It is used for cataloging and indexing books. DDC has three divisions, a ten, a hundred, and a thousand. The book subject is reflected in each division. Commonly, to know the book content, librarians read the book title. Then, they identify the book index in DDC system. Nevertheless, it requires more time. To read the book title, Optical Character Recognition (OCR) aids them to get the book title efficiently that convert the image of the book cover into the text-editable. Librarians use a web camera to scan the book cover, especially the book title area. There are three steps for pre-processing, the lowercase changing, the useless word removing, and tokenizing. To detect the book categories, Long Short-Term Memory Neural Network is good implemented in this research. It is almost used for text classification. In this research, It gives high performance that achieves more than 92% accurately. © Published under licence by IOP Publishing Ltd.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Work system method as an e-learning design framework in private universities 3

Work system method as an e-learning design framework in priv...

引用

3rd International Conference on Vocational Education and Technology, IConVET 2020

作者： Supriana, C.E. Informatics Engineering Study Program Pasundan University Bandung Indonesia

The development of information and communication technology, especially the internet provides opportunities to improve the ability of lecturers to deliver courses to students without being limited by distance and time. This can be done by utilizing e-learning which will accelerate the transfer of knowledge and skills. E-learning is distance education that utilizes various digital tools and platforms. These tools and platform are used to support interaction, lectures and delivery of instructions between lecturers and students. This study will discuss the use of work system methods and the use of e-learning technology in a business entity. The work system methods are used to design information systems. Meanwhile e-learning technology in a business entity serves lecturers and students, conduct lectures at private universities in increasing knowledge dissemination, educational affordability and the use of technology and information as its support. The result of this research is the works system method model which refers to the analysis of data from the internet accessibility survey of students, analysis of its components, the system development cycle, the revision of the vision, mission and resources in private universities and recommendations of opportunities for the development of higher quality e-learning implementation. © Published under licence by IOP Publishing Ltd.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Analysis of online market system design strategy based on external and internal factor evaluation matrix 6

Analysis of online market system design strategy based on ex...

引用

6th International Seminar on Mathematics, Science, and Computer Science Education, MSCEIS 2018

作者： Primawati, A. Paramita, A. Lukman, L. Rangka, I.B. Informatics Study Program Universitas Indraprasta PGRI Jakarta Indonesia

The development of e-commerce or e-Market technology today creates a culture of Smartphone usage as the main media in communicating and doing business so it makes the opportunity to be utilized in overcoming every conventional issues in doing business. One of the issues in Tanah Abang Market is the congestion due to the large number of visitors coming from outside Jakarta. Therefore, a proper market development strategy is needed. The method used in this research was SWOT (Strengths, Weaknesses, Opportunities & Threats). The strategy is composed of the calculations described in the EFE (External Factor Evaluation) and IFE Matrix (Internal Factor Evaluation). The result of internal factor analysis from IFE matrix obtained value equal to 3,27, while result of External factor analysis from EFE matrix obtained score equal to 3,35. Based on the data, the strategy of market development by designing the Online Market application is legally specific for the official seller in Tanah Abang Market is one of the right strategy in overcoming the issues in Tanah Abang Market. Furthermore, the design of Online Market System application for Tanah Abang Market (Blok F) produced in this research is part of the implementation of market development strategy. © Published under licence by IOP Publishing Ltd.

关键词： Factor analysis

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：