检索结果-内蒙古大学图书馆

6th International Conference on computer and Informatics Engineering, IC2IE 2023

作者： Paulindino, Aedentrisa Yasmanda Pardamean, Bens Elwirehardja, Gregorius Natanael Bina Nusantara University Binus Graduate Program - Master of Computer Science Computer Science Department Jakarta Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9798350345162

The ability of Convolutional Neural Networks (CNNs) to accurately discriminate between normal and tumorous brain tissues has been promising. The review focuses on the different CNN models, pre-processing methods, data augmentation, and Transfer Learning (TL) strategies used in this research. This Systematic Literature Review (SLR) collected the data from Google Scholar. The results of this study indicate that open-source datasets from Kaggle and Brain MRI Images for Brain Tumor Detection are the most used datasets. However, limited data and imbalanced class problems remain common challenges across various datasets. To overcome those challenges, using a larger dataset, oversampling, Generative Adversarial Network (GAN), federated learning, and Self-Supervised Learning (SSL) to handle the imbalance are the potential solution. Additionally, popular CNN architectures for brain tumor classification extensively use pre-trained models such as VGG16, VGG19, DenseNet121, DenseNet201, GoogleNet, ResNet-50, and Inception-v3. TL strategies are preferred, allowing CNNs to leverage knowledge from large datasets, improving generalization even with limited labeled data. © 2023 IEEE.

关键词： brain tumor classification cnn mri pre-trained transfer learning

来源：评论

学校读者我要写书评

暂无评论

Pap Smear Medical Image Classification Using Deep Learning: A Systematic Review 6

Pap Smear Medical Image Classification Using Deep Learning: ...

引用

6th International Conference on computer and Informatics Engineering, IC2IE 2023

作者： Selvano, Elvan Elwiehardja, Gregorius Natanael Pardamean, Bens Bina Nusantara University Binus Graduate Program - Master of Computer Science Computer Science Department Jakarta Indonesia Bina Nusantara University Bioinformatics and Data Science Research Center Jakarta Indonesia

ISBN: (纸本)9798350345162

Cervical cancer has been known as one of the most prevalent medical disorders globally and a leading cause of death. Early detection, particularly through Pap tests, plays a vital role in its prevention. Previous studies have leveraged machine learning and deep learning techniques to classify the medical images obtained from Pap tests. In this study, a Systematic Literature Review methodology was used to examine 15 relevant papers that have been filtered from queries to Google Scholar which have gone through 4 stages of filtering that include: identification, screening, eligibility, and inclusion. This study addresses two research questions regarding the datasets and deep learning techniques for classifying pap smear images in recent years. The performance of the models was analyzed and potential areas for improvements are suggested. The findings of this study reveal that the Herlev University Hospital and SIPaKMed datasets are the most used. The methodologies used by researchers range from machine learning techniques, transfer learning using Convolutional Neural Networks, and utilize state-of-the-art models with novel optimizing methodology. While there are exciting opportunities in the field, challenges include model generalization and interpretability. © 2023 IEEE.

关键词： cervical cancer deep learning machine learning pap test

来源：评论

学校读者我要写书评

暂无评论

Jointprop: Joint Semi-supervised Learning for Entity and Relation Extraction with Heterogeneous Graph-based Propagation 61

Jointprop: Joint Semi-supervised Learning for Entity and Rel...

引用

61st Annual Meeting of the Association for Computational Linguistics, ACL 2023

作者： Yandan, Zheng Anran, Hao Tuan, Luu Anh School of Computer Science and Engineering Interdisciplinary Graduate Program-HealthTech Nanyang Technological University Singapore

ISBN: (纸本)9781959429722

Semi-supervised learning has been an important approach to address challenges in extracting entities and relations from limited data. However, current semi-supervised works handle the two tasks (i.e., Named Entity Recognition and Relation Extraction) separately and ignore the cross-correlation of entity and relation instances as well as the existence of similar instances across unlabeled data. To alleviate the issues, we propose Jointprop, a Heterogeneous Graph-based Propagation framework for joint semi-supervised entity and relation extraction, which captures the global structure information between individual tasks and exploits interactions within unlabeled data. Specifically, we construct a unified span-based heterogeneous graph from entity and relation candidates and propagate class labels based on confidence scores. We then employ a propagation learning scheme to leverage the affinities between labelled and unlabeled samples. Experiments on benchmark datasets show that our framework outperforms the state-of-the-art semi-supervised approaches on NER and RE tasks. We show that the joint semi-supervised learning of the two tasks benefits from their codependency and validates the importance of utilizing the shared information between unlabeled data. © 2023 Association for Computational Linguistics.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Concept, Technology, Barriers To Smart Village: A Systematic Literature Review 11

Concept, Technology, Barriers To Smart Village: A Systematic...

引用

11th International Conference on Cyber and IT Service Management, CITSM 2023

作者： Utamajaya, Joy Nashar Meyliana Prabowo, Harjanto Hidayanto, Achmad Nizar Ramadhan, Arief Bina Nusantara University Computer Science Department Binus Graduate Program - Computer Science Department Jakarta11480 Indonesia Telkom University School of Computing Bandung Indonesia

ISBN: (纸本)9798350305968

Smart villages that utilize digital technology are a solution to assist rural community services in meeting their needs, especially for developing countries. However, financial problems, namely the high cost of infrastructure, the size of the informal economy and governance are challenges in limiting the government's aspirations regarding the smart village concept. The presentation of this article examines the state of smart village development in developing countries, which includes conceptual understanding, motivations, drivers and barriers to smart villages. The purpose of this study is to find answers to research questions by reviewing several selected study articles. The method used was to search for selected studies and there were 60 selected studies identified from a search of five literature databases which initially contained 3394 articles. The results of the data were analyzed using synthetic analysis and thematic analysis. The results of this study found data related to Concept, Technology, Barriers To Smart Village which came from several articles by answering questions from the research, namely RQ1: How many articles from the 10 most populous countries discussed Smart Village, RQ2: What are the basic dimensions of Smart Village, RQ3: What new technologies are discussed in Smart Village digitization, RQ4: What are the Challenges in Smart Village. The results of this SLR can also later be used as a reference for further researchers to find out the background of research related to smart villages. The conclusion obtained in this research is the end of the explanation of this article concludes that there are still many shortcomings in this research and it is hoped that in the future many studies will be able to explore other aspects such as regulations and others that are not discussed in the article so that it is expected to be a reference for further researchers to examine information related to smart villages. in order to find an ideal and up-to-date con

关键词： Developing countries

来源：评论

学校读者我要写书评

暂无评论

TaxDiff: taxonomic-guided diffusion model for protein sequence generation

引用

science China(Information sciences) 2025年第4期68卷 385-386页

作者： Zongying LIN Hao LI Liuzhenghao LV Yu WANG Bin LIN Junwu ZHANG Zijun CHEN Calvin Yu-Chian CHEN Li YUAN Yonghong TIAN School of Electronic and Computer Engineering Peking University AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School Peng Cheng Laboratory School of Chemical Biology and Biotechnology Peking University

Protein design aims to generate protein variants with targeted biological functions, which is significant in multiple biological areas, including enzyme reaction catalysis, vaccine design, and fluorescence intensity. Protein design contains two paradigms: sequence generation and structure generation. Recently, EvoDiff [1] proposed a universal designing paradigm, combining structure and sequence generation using the diffusion framework, which improves the protein design efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Implementation of Lightweight PRNG on PLC for Industrial Control Systems 3

Implementation of Lightweight PRNG on PLC for Industrial Con...

引用

3rd International Conference on Intelligent Cybernetics Technology and Applications, ICICyTA 2023

作者： Sama, Andi Gaol, Ford Lumban Harso Supangkat, Suhono Ranti, Benny Binus Graduate Program Doctor of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Doctor of Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia Institute of Technology Bandung Faculty of Digital Communication and Hotel & Tourism Bandung Indonesia Universitas Indonesia Faculty of Computer Science Depok Indonesia

ISBN: (纸本)9798350394559

The Information Technology/Operational Technology convergence towards Industry 4.0 opens the opportunity to leverage recent advancements in Information Technology for Operational Technology, such as Cloud, Internet of Things, and Artificial Intelligence. Meanwhile, cyber-attacks are increasing for Operational Technology. The security aspect in Operational Technology systems has traditionally been a low priority, in contrast with speed. This introduces challenges as Industrial Control Systems such as programmable Logic Controller in Operational Technology have been traditionally optimized for speed rather than security due to limited computing power. As computations need to be as efficient as possible, security in Operational Technology has yet to be managed as robustly as in Information Technology. Operational Technology communication protocols for securing data transfer, for example, have no or just a few security capabilities, even for basic authentication and encryption. Common security algorithms rely on random numbers. However, Random Number Generator is not usually part of standard functions in programmable Logic Controllers, the core control component in Industrial Control Systems. In Industrial Control Systems, the Random Number Generator is mostly implemented as a software-based Pseudo Random Number Generator. This paper shows how to apply a Pseudo Random Number Generator in a Siemens Compact PLC S7-1200 using a modified lightweight XORshift algorithm. The XORshift algorithm can generate better randomness than the system's clock-based implementation in the Siemens Library of Generic Functions. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Model Prediction Using Random Forest Algorithm and Time Series Analysis Parts Distribution with in Indonesia Automotive Industry 8

Model Prediction Using Random Forest Algorithm and Time Seri...

引用

8th International Conference on Informatics and Computing, ICIC 2023

作者： Andy Achmad, H. Ramadhan, Arief Warnars Harco Leslie, H. Budiharto, Widodo Bina Nusantara University BINUS Graduate Program Computer Science Computer Science Department Jakarta11480 Indonesia Telkom University School of Computing Bandung40257 Indonesia

ISBN: (纸本)9798350342604

Car spare parts are parts of a car that consist of components that form a certain unity and function, there are some parts that are damaged more often and therefore must be replaced more often. In this research, to predict the availability of spare parts using the times series moving average prediction method with random forest. The dataset used in this research is 19,068 consisting of location, transaction number, transaction date, part number, quantity and odo-km. Distribution of spare parts classified based on recapitulation of spare part distribution is RAE=54.5541% and RSE=63.8888%, distribution of spare parts based on location is RAE=55.5541% and RSE=65.2118%, maintenance based on ODO-KM is RAE=33.0949% and RSE=41.2241 % and distribution quantity RAE=33.749% and RSE=36.2317%. The results of spare part distribution analysis using the Confusion Matrix with probability accuracy are TP Rate=0.903, FP Rate=0.067, Precision=0.911, Recall=0.903, F-Measure=0.893, MCC=0.857, ROC Area=0.983 and PRC Area=0.948. The aim of this research is to determine the factors needed to build a machine learning-based spare parts distribution model, implementation, measurement and prediction in the automotive industry in Indonesia. © 2023 IEEE.

关键词： Automotive industry

来源：评论

学校读者我要写书评

暂无评论

Systematic Literature Review of Transformer Model Implementations in Detecting Depression 6

Systematic Literature Review of Transformer Model Implementa...

引用

6th International Conference on computer and Informatics Engineering, IC2IE 2023

作者： Nanggala, Kenjovan Pardamean, Bens Elwirehardja, Gregorius Natanael Bina Nusantara University Binus Graduate Program - Master of Computer Science Computer Science Department Jakarta Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9798350345162

This systematic literature review explores the application of transformer models in early detection of human depression, encompassing text, audio, and video data modalities. Transformer architectures, notably BERT for text, have proven adept at capturing crucial contextual and linguistic patterns associated with depression. For audio and video data, hybrid approaches that combine transformer models with other architectures are prevalent. Key features considered include eye gaze, head pose, facial muscle movements, and audio characteristics such as MFCC and Log-mel Spectrogram, along with text embeddings. Performance comparisons underscore the superiority of text-based data in consistently delivering the most promising results, followed by audio and video modalities when utilizing transformer models. The fusion of multiple modalities emerges as an effective strategy for enhancing predictive accuracy, with the amalgamation of audio, video, and text data yielding the most precise outcomes. However, it is noteworthy that unimodal approaches also exhibit potential, with text data exhibiting superior performance over audio and video data. Nevertheless, several challenges persist in this research domain, including imbalanced datasets, the limited availability of comprehensive and diverse samples, and the inherent complexities in interpreting visual cues. Addressing these challenges remains imperative for the continued advancement of depression detection using transformer-based models across various modalities. © 2023 IEEE.

关键词： deep learning major depressive disorder multimodal transformer unimodal

来源：评论

学校读者我要写书评

暂无评论

Simulation of Electromagnetic Wave Propagation in Graphene-Coated 1D Photonic Crystals Using the Finite Volume Method

Simulation of Electromagnetic Wave Propagation in Graphene-C...

引用

2024 International Conference on Interdisciplinary Physics, ICIPs 2024

作者： Negara, Teguh Puja Hardhienata, Hendradi Alatas, Husin Study Program of Computer Science Faculty of Mathematics and Natural Science Universitas Pakuan Bogor Indonesia Theoretical Physics Division Department of Physics Faculty of Mathematics and Natural Science IPB University Bogor Indonesia

A numerical study on the interaction of electromagnetic waves with photonic crystals with one-dimensional periodicity has been carried out using the Finite Volume method. The photonic crystals with one-dimensional periodicity consists of 7 alternating layers of and with thicknesses of and, respectively. Electromagnetic field components have been simulated to propagate through the photonic crystal structure, experiencing reflection and transmission at each layer of the structure. The simulation results show the occurrence of absorption precisely at the Bragg frequency by the photonic crystal, which is referred to as the photonic band gap (PBG). A comparison of the simulation results has been conducted using different fluxes, such as the Lax-Friedrichs and upwind schemes, under PBG conditions. The results show smoother absorption using the Lax-Friedrichs scheme. Additionally, the use of a single-layer graphene on the front side of the photonic crystal has shown more perfect absorption compared to without the single-layer graphene. Therefore, the integrated graphene-photonic crystal system can be used as a perfect reflector. The simulation runs well using effective absorbing boundary conditions (ABCs) to reduce wave reflections at the edges of the computational window. Based on the simulation results, the Finite Volume method has been proven to be a powerful tool in describing electromagnetic wave propagation through photonic crystal systems with or without graphene. These findings provide a foundational model for fabrication approaches and holds potential for future advancements in sensor technologies, moreover two-dimensional and three-dimensional structures. © 2025 Institute of Physics Publishing. All rights reserved.

关键词： Photonic band gap

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Coffee Bean Binary Classification Through Deep Learning Techniques 1

引用

International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications, CITISIA 2022

作者： Islamy, Fajrul Muchtar, Kahlil Arnia, Fitri Dawood, Rahmad Febriana, Alifya Elwirehardja, Gregorius Natanael Pardamean, Bens Department of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh23111 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Computer Science Department Master of Computer Science Program BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia

ISBN: (数字)9783031290787

ISBN: (纸本)9783031290770

Coffee beans are one of the high-value commodities in Indonesia, but the sorting method for the quality of coffee beans still uses visual methods and sieves with mechanical machines. This study aims to provide an alternative to classifying coffee beans using Deep Learning algorithms, such as the ResNet-18 and MobileNetV2. The dataset used is USK-COFFEE which consists of two classes, the normal coffee bean class, and the defect coffee bean class. The models were trained using the balanced and imbalanced datasets, meaning that two scenarios were performed. From the results of this study, the accuracy value for the ResNet-18 model was 91.50% when trained on the balanced dataset and 90.87% on the imbalanced dataset. It outperformed the MobileNetV2 architecture, which only achieved 0.8125 and 0.8112 accuracy scores when trained on the balanced and imbalanced datasets, respectively. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： computer vision

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：