检索结果-内蒙古大学图书馆

3rd IEEE International Biomedical Instrumentation and Technology Conference, IBITeC 2023

作者： Muharram, Arief Purnama Taufikulhakim, Farhan Hilmi Purwarianti, Ayu Universitas Indonesia Faculty of Medicine Jakarta Indonesia Institut Teknologi Bandung School of Electrical Engineering and Informatics Master Program of Informatics Bandung Indonesia

ISBN: (纸本)9798350302424

COVID-19 is an acute respiratory disease that has become a pandemic worldwide. Many studies have been conducted to enhance our understanding of COVID-19. However, the abundance of information obtained from these studies has resulted in information overload. In this study, we purposed a simple COVID-19 Knowledge Graph in Bahasa Indonesia as a way to reconstruct knowledge to combat this information overload. We used Bahasa Indonesia in our study to explore its potential for constructing a Knowledge Graph (KG). The construction of our KG involved manual curation of medical literatures and annotation of entities and relationships by the domain experts. The KG was implemented using Neo4J version 5. We successfully demonstrated our COVID-19 KG, which consists of 240 nodes and 276 relationships with 15 and 14 node and relationship labels, respectively. Accessing the information within the KG is made effortless through the use of Cypher queries in Neo4J. Further research is still needed to develop the KG into a larger and better one. However, our COVID-19 KG can serve as a basis for further development. © 2023 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Unraveling Game Addiction Behavior Among Digital Native Students: Leveraging Machine Learning for Insights 13

Unraveling Game Addiction Behavior Among Digital Native Stud...

引用

13th IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2024

作者： Amriza, Rona Nisa Sofia Fadhilla, Cut Alna Telkom University Department of Information System Purwokerto Indonesia Universitas Samudra Informatics Study Program Faculty of Engineering Aceh Indonesia

ISBN: (纸本)9798350368086

The allure of gaming often leads to excessive engagement, which can result in addictive and problematic behaviors, negatively impacting academic performance and school achievements. While gaming becomes increasingly prevalent, concerns about game addiction have grown, particularly among students. The excessive and obsessive usage of video games that characterizes game addiction can have detrimental effects like academic deterioration, social isolation, and mental health problems. This study seeks to elucidate the complex patterns of game addiction among digital-native students by utilizing advanced machine learning techniques. We employed Random Forest, SVM, Decision Tree, and Naïve Bayes algorithms to classify game addiction data from students. To address the class imbalance, we applied Borderline-SMOTE. Our results demonstrate that decision tree and random forest outperformed other machine learning approaches, achieving an accuracy of 95% in classifying game addiction. These findings contribute to the expanding body of knowledge on game addiction. Furthermore, in order to provide real-time monitoring and intervention for students who are at risk of developing a game addiction, future research may investigate incorporating these findings into educational platforms or applications. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Security Authentication on the Edge: A Step Further to Defense in Depth for Internet of Battle Things 11

Security Authentication on the Edge: A Step Further to Defen...

引用

11th IEEE International Conference on Software Defined Systems, SDS 2024

作者： Lawisch, Marcio Antonio Dos Anjos, Julio Cesar S. De Freitas, Edison Pignaton Institute of Informatics RS Brazil Federal University of Ceara Campus Itapaje Graduate Program in Teleinformatics Engineering PPGETI CE Brazil

ISBN: (纸本)9798331518325

Currently, the demand for the security of network assets in companies grows dramatically because of several factors, including the growth of the attack surface combined with the variety of connection standards and correlated to the emerging Internet of Things (IoT) related devices and services. This reality is also evident regarding nodes connected to military networks, especially Tactical Edge (TE) devices. Due to the wide variety of equipment connected to the networks (from small sensors to powerful radars) and their possible limitations in resources and transmission means, mainly caused by the terrain and operational conditions, these networks called the Internet of Battle Things (IoBT), also face important security challenges. In this context full of many intentional and unintentional security challenges, this work proposes using blockchain technology as a network access security solution within an in-depth defense concept at three levels: hardware, network, and application. Tests for attacks against the network layer resulted in high resistance rates without consuming significant resources. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Advanced Design Pattern Selection Methodology through Weighted Semantic Ontologies for Microservices

Advanced Design Pattern Selection Methodology through Weight...

引用

2024 International Conference on Computer and Applications, ICCA 2024

作者： Attia, Rabab Atef Ghoniemy, Samy Hamdy, Abeer The British University in Egypt Faculty of Informatics and Computer Science Cairo Egypt Galala University Computer Science and Engineering Program Cairo Egypt

ISBN: (纸本)9798350367560

Seamless communication between authorities, people, and smart devices is crucial in today's globally interconnected world. Unprecedented demands on software design result from the advent of ubiquitous connectivity, which allows connections at any time and from any location. By structuring applications as separate services that can communicate both internally inside a platform and externally across platforms, microservices (MS) architecture satisfies these requirements. One of the most difficult parts, though, is still controlling communication between MS services, which calls for knowledge of the best design patterns. In order to solve this, we suggest a context-aware recommender system that is adapted to MS design patterns. This system not only makes recommendations for appropriate patterns, but it also gives statistical scores that show how relevant each solution is to the particular issue at hand. Other patterns with ratings indicating their possible feasibility are also displayed by our algorithm. On the other hand, sentence transformers handle intricate, human-like problem descriptions, while our method uses MS Domain Ontologies to distinguish pattern applications, constraints, and best practices. Our methodology provides a refined examination of solution suitability and recommendations through the use of weighing and correlation algorithms. Extensively tested with more than 237 developer-style scenarios, our framework offers qualitative and quantitative insights into its performance and efficacy, showing notable gains over current solutions in terms of offering pattern-specific, contextually accurate guidance for MS communication challenges. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Internet of Things for Real-Time Multi Room Monitoring System 1

Internet of Things for Real-Time Multi Room Monitoring Syste...

引用

1st IEEE International Conference on Smart Technology, ICE-SMARTec 2023

作者： Tae, Kim Sung Suhartomo, Antonius Vincent President University Study Program of Electrical Engineering Bekasi Indonesia School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia

ISBN: (纸本)9798350306156

Electronic devices have become an integral component in our daily activities. In fact, the consumption of electrical energy in households reached 49% in 2018, and is expected to increase to 58% in 2050. Concurrently, the LPG is the second highest consumed energy in the household and is expected to increase to 37% in 2050. However, the devices utilizing these energies could lead to a danger such as housefire if not operated and treated carefully. An Internet of Things (IoT)-based smart home monitoring system would solve this problem, especially by effectively monitoring several parameters in the house simultaneously. In this study, a system is built to monitor and control three rooms in the house independently and simultaneously. The sensors and/or actuators in all rooms are controlled by NodeMCU ESP8266s. All microcontrollers are linked via the Internet to a local server, where all data is analyzed, saved, and transmitted to the user using the MQTT protocol. The monitoring is done by the user via MQTT dashboard in the smartphone. Following testing, the three microcontrollers are fully capable of exchanging data with the user's smartphone. The humidity changed by 1%, while the temperature changed by 0.1 °C. Perfect data interchange is possible between the relays, flame, gas, and movement activity sensor. © 2023 IEEE.

关键词： Informatization

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence-Based System 'SiMoniK' for MSMEs 9

Artificial Intelligence-Based System 'SiMoniK' for MSMEs

引用

9th IEEE Information Technology International Seminar, ITIS 2023

作者： Lestari, Sri Yulmaini Aswin Sulyono Nul Fikri, Ruki Rizal Informatics Engineering Study Program Faculty of Computer Science Bandar Lampung Indonesia Management Study Program Faculty of Economics Business Bandar Lampung Indonesia

ISBN: (纸本)9798350306835

Artificial intelligence was recently implemented in various fields. One of these applied artificial intelligence systems was the Performance Monitoring System "SiMoniK"for MSMEs. This system was designed through the C4.5 algorithm and the Porat-Rank method. The C4.5 algorithm was applied to classify the MSMEs into three classifications, e.g. the micro enterprise classification, the small enterprise classification, and the medium enterprise classification. Moreover, the Porat-Rank method was also applied to distribute the solving-problem recommendations and to improve the independence of MSMEs. The result of this study was that the C4.5 algorithm could classify the MSME data correctly in the form of an accuracy value of 99.2%. Besides, the Porat-Rank method could also provide recommendations in the form of outstanding quality with an NDCG mean value of 0.87. © 2023 IEEE.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

New Energy-Efficient 3-2 and 4-2 Approximate Adder Compressors Topologies 30

New Energy-Efficient 3-2 and 4-2 Approximate Adder Compresso...

引用

30th IEEE International Conference on Electronics, Circuits and Systems, ICECS 2023

作者： Lopes, Rodrigo Antonietti, Leonardo Rosa, Morgana M. A. Costa, Eduardo Soares, Rafael Bampi, Sergio Graduate Program on Computing Pelotas Brazil Graduate Program on Electronic Engineering and Computing Pelotas Brazil PPGC & PGMICRO - Informatics Institute Porto Alegre Brazil

ISBN: (纸本)9798350326499

Addition units are present across many computational kernels inherent in various error-tolerant applications, including machine learning, signal, image, and video processing. Notably, adder compressors are the target when high speed and low power are the main design concerns. This work introduces energy-efficient structures of 3-2 approximate adder compressors (Ax3-2) and three distinct versions of 4-2 approximate adder compressors (Ax4-2). We compared our proposed Ax3-2 and Ax4-2 compressors with state-of-the-art energy-efficient approximate adder compressors (AxACs). Both Ax3-2 and Ax4-2 models passed through rigorous tests as standalone units. Furthermore, we integrated the Ax4-2 models into an essential application kernel appearing in video coding, i.e., the Sum Squared Differences (SSD) video accelerator. We introduce Ax3-2 and Ax4-2 that yield a new Pareto front concerning both energy-quality and area-quality trade-offs, thereby demonstrating a marked improvement over the prevailing state-of-the-art energy-efficient AxACs. © 2023 IEEE.

关键词： Adders

来源：评论

学校读者我要写书评

暂无评论

Fish Freshness Identification Using Machine Learning: Performance Comparison of k-NN and Naïve Bayes Classifier

引用

Journal of Computing Science and engineering 2022年第3期16卷 153-164页

作者： Yudhana, Anton Umar, Rusydi Saputra, Sabarudin Department of Electrical Engineering Universitas Ahmad Dahlan Yogyakarta Indonesia Master Program of Informatics Universitas Ahmad Dahlan Yogyakarta Indonesia

Fish is one of the food sources that should be examined for freshness before being consumed. The consumption of rotten fish can cause various diseases. The rotten fish have changed color on the gills, skin, flesh, and eyes and have a pungent odour. Fish freshness can be assessed using a variety of conventional methods, but these methods have limitations, such as requiring relatively expensive equipment, trained personnel and being destructive. The machine learning method is used because it is non-destructive, reduces costs, and is easy to use. This study aims to identify the freshness of fish using k-nearest neighbor (k-NN) and Naïve Bayes (NB) classification methods based on the fish-eye image. The features used in the classification process are RGB and GLCM. The research stages consist of the fish collection process, image acquisition and class division, preprocessing and ROI detection, feature extraction and dataset split, and the classification process. Based on these results, it can be stated that the k-NN method has better performance than NB with average accuracy, precision, recall, specificity, and AUC of 0.97, 0.97, 0.97, 0.97, and 0.97. © 2022. The Korean Institute of Information Scientists and Engineers

关键词： Fish

来源：评论

学校读者我要写书评

暂无评论

White Bread Mold Detection using K-Means Clustering Based on Grey Level Co-Occurrence Matrix and Region of Interest

White Bread Mold Detection using K-Means Clustering Based on...

引用

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

作者： Putra, Qori Alfatah Sari, Christy Atika Rachmawanto, Eko Hari Cahyo, Nur Ryan Dwi Mulyanto, Edy Alkhafaji, Mohamed Ayad University of Dian Nuswantoro Study Program in Informatics Engineering Semarang Indonesia University of Dian Nuswantoro Department of Informatics Engineering Semarang Indonesia National University of Science and Technology Department of Computer Science DhiQar Iraq

ISBN: (纸本)9798350339215

This research paper presents a bread mold identification system that utilizes digital image processing techniques, specifically K-means clustering and thresholding, to accurately detect and classify mold-infected areas on bread. The system aims to provide valuable information regarding the safety of consuming mold-contaminated bread, enabling consumers to make informed decisions and reduce the risk of health issues associated with consuming mold-infested bread. the K-means clustering algorithm for mold classification, considering factors such as the number of iterations and the distance metric within the feature space to determine its accuracy. The GLCM feature extraction technique is employed to extract texture information from bread images, encompassing features such as standard deviation (110.62), contrast (1.46), energy, and homogeneity (0.96 and 0.77, respectively). Experimental results demonstrate that the Euclidean Distance yielded the highest result of 72.73, the Cosine Distance obtained the highest result of 8.25, and the City Block Distance obtained the highest result of 92.11. These findings showcase the effectiveness of the system in accurately detecting and classifying mold-infected areas on bread, thereby aiding in ensuring food safety and reducing health risks for consumers. © 2023 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Robot and Human Interaction using Natural Language Understanding in Indonesian based on Mental Image Based Understanding 11

Robot and Human Interaction using Natural Language Understan...

引用

11th International Conference on Information and Communication Technology, ICoICT 2023

作者： Abrari, Muhammad Giriarda Hindersah, Hilwadi Rusmin, Pranoto Hidaya Bandung Institute of Technology Master Program in Electrical Engineering Bandung Indonesia Bandung Institute of Technology School of Electrical Engineering and Informatics Bandung Indonesia

ISBN: (纸本)9798350321982

Robots, in order to understand human commands, could be possible if there is an interaction between them. Possible interaction including the Natural Language, that humans have used to communicate with each other. The method used in this research for robots to understand Natural Language is Mental Image Directed Semantic Theory (MIDST) which uses unique Lmd formula as a basis for computing the Natural Language Understanding (NLU) processes. Equipped with support modules such as Speech to Text, Text to Speech, and Synonym Search Algorithm the robot successfully to receive, understand, and issue responses according to the Natural Language expressions given in Indonesian Language. The movement of the robot is also simulated in a two-dimensional plane to demonstrate its ability to serve humans. © 2023 IEEE.

关键词： Semantics

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：