检索结果-内蒙古大学图书馆

24th International Electronics Symposium, IES 2022

作者： Marta, Bayu Sandi Muhammad Amin, A. Sari, Dewi Mutiara Armono, Haryo Dwito Politeknik Elektronika Departement of Informatics and Computer Engineering Negeri Surabaya Indonesia Institut Teknologi Sepuluh Nopember Faculty of Marine Engineering Ocean Engineering Department Indonesia

ISBN: (数字)9781665489713

ISBN: (纸本)9781665489713

The implementation of computer vision in the field of underwater image is currently very popular. However, Indonesia's vision system for breakwater work has not yet been implemented. The work of the vision system is still manual using divers [1]. In addition, the application of computer vision in underwater images has a big obstacle because the resulting image in an underwater environment has poor color and contrast. This poor color and contrast are due to a density nearly 1000 times denser than air. This density directly affects the light transmission, which affects the resulting image, which has less color and contrast than the image taken through the air. So it takes image processing such as Image Enhancement and Image Color Restoration [2]. Another issue is building a real-time system. If the system that is built is not real-time, this makes the possibility of data reading errors being significant, and the movement of information is slow [3]. This research presents methods regarding image enhancement and color restoration built in the Graphical User Interface (GUI). The methods applied in this research are Histogram Equalization (HE), Contrast Limited Adaptive Histogram Equalization (CLAHE), and Multi-Scale Retinex with Color Restoration (MSRCR). Those methods are applied to the images produced by the two cameras and run on the single board processor and laptop for the comparison. The result by using 71 underwater images shows that for Underwater Color Image Quality Evaluation (UCIQE) value of the Histogram Equalization (HE) Method yields 20%, meanwhile for Contrast Limited Adaptive Histogram Equalization (CLAHE) yields 8%, and the Multi-Scale Retinex with Color Restoration (MSRCR) method yields 72%. © 2022 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

A Dense Retrieval System and Evaluation Dataset for Scientific Computational Notebooks 19

A Dense Retrieval System and Evaluation Dataset for Scientif...

引用

19th IEEE International Conference on e-Science, e-Science 2023

作者： Li, Na Zhang, Yangjun Zhao, Zhiming Multiscale Networked System Informatics Institute University of Amsterdam Netherlands School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom Amsterdam Netherlands

ISBN: (纸本)9798350322231

The discovery and reutilization of scientific codes are crucial in many research activities. Computational notebooks have emerged as a particularly effective medium for sharing and reusing scientific codes. Nevertheless, effectively locating relevant computational notebooks is a significant challenge. First, computational notebooks encompass multi-modal data comprising unstructured text, source code, and other media, posing complexities in representing such data for retrieval purposes. Second, the absence of evaluation datasets for the computational notebook search task hampers fair performance assessments within the research community. Prior studies have either treated computational notebook search as a code-snippet search problem or focused solely on content-based approaches for searching computational notebooks. To address the aforementioned difficulties, we present DeCNR, tackling the information needs of researchers in seeking computational notebooks. Our approach leverages a fused sparse-dense retrieval model to represent computational notebooks effectively. Additionally, we construct an evaluation dataset including actual scientific queries, computational notebooks, and relevance judgments for fair and objective performance assessment. Experimental results demonstrate that the proposed method surpasses baseline approaches in terms of F1@5 and NDCG@5. The proposed system has been implemented as a web service shipped with REST APIs, allowing seamless integration with other applications and web services. © 2023 IEEE.

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

Real-Time Health Monitoring Based ESP8266 and Fuzzy Logic

Real-Time Health Monitoring Based ESP8266 and Fuzzy Logic

引用

computer Sciences, engineering, and Technology Innovation (ICoCSETI), International Conference on

作者： Fadhillah Azmi Nurul Khairina Amir Saleh Department of Electrical Engineering Universitas Medan Area Medan Indonesia Department of Informatics Engineering Universitas Medan Area Medan Indonesia Department of Computer and Informatics Engineering Politeknik Negeri Medan Medan Indonesia

ISBN: (数字)9798331508616

ISBN: (纸本)9798331508623

This study aims to develop a health monitoring system using an ESP8266 microcontroller and fuzzy logic to view real-time health data and predict the patients’ heart health conditions. The system is designed to monitor various physiological data, including heart rate and blood pressure, by utilizing sensors connected to the ESP8266 microcontroller device. Data obtained from the sensors will be transmitted wirelessly to a web-based platform, which facilitates remote monitoring and real-time data visualization. In addition, fuzzy logic is used to analyze the sensor data, classifying the health status into defined categories, including normal, moderate, and critical. This method facilitates a comprehensive understanding of the health situation, which offers patients a precise and clear description of their health status. The results of this study indicate that the combination of ESP8266 with fuzzy logic offers an effective, economical, and scalable solution for real-time health monitoring. This device can be applied for remote patient monitoring and early identification of possible heart disease problems.

关键词： Fuzzy logic Accuracy Microcontrollers Real-time systems Blood pressure Sensors Batteries Biomedical monitoring Monitoring Diseases

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis for Curriculum of Independent Learning Based on Naïve Bayes with Laplace Estimator 2

Sentiment Analysis for Curriculum of Independent Learning Ba...

引用

2nd International Conference on Information Technology Research and Innovation, ICITRI 2023

作者： Ariefah, Amelia Widodo Nugraheni, Murien State University of Jakarta Dept. of Informatics and Computer Engineering Education Jakarta Indonesia State University of Jakarta Dept. of Information System and Technology Jakarta Indonesia

ISBN: (纸本)9798350324945

Curriculum changes have a significant impact on the field of education in Indonesia, especially in universities. This is because the curriculum is used as a means to achieve the goals of educational success as well as guidelines in the implementation of teaching at every level of education. This study aims to determine public sentiment regarding the implementation curriculum of independent learning (MBKM) through Twitter based on Naïve Bayes with Laplace Estimator. Tweet search results use the keywords 'kurikulum mbkm' and 'mbkm'. The data used in this study amounted to 2500 tweet data which will be divided into 2000 data as training data with details of 1000 positive tweets and 1000 negative tweets and 500 data as testing data. The results showed the performance of Naïve Bayes using Laplace Estimator which resulted in an accuracy value of 80.20%, precision value of 82.00%, and recall value of 79.00%. Meanwhile, the performance of Naïve Bayes without Laplace Estimator resulted in an accuracy value of 77.00%, precision value of 80.00%, and recall value of 74.00%. Naive Bayes with Laplace Estimator reached the highest value in all metrics. © 2023 IEEE.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

Comparison Between Bi-Directional LSTM And Transfer Learning in Correcting Typing Errors on Twitter Social Media Posts 11

Comparison Between Bi-Directional LSTM And Transfer Learning...

引用

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

作者： Lubis, Arif Ridho Prayudani, Santi Hamzah, Muhammad Luthfi Politeknik Negeri Medan Department of Computer Engineering and Informatics Medan Indonesia Universitas Islam Negeri Sultan Syarif Kasim Riau Faculty of Science and Technology Pekanbaru Indonesia

ISBN: (纸本)9798350305968

Typing errors are a behavior that often occurs in communication via short messages or posts on social media platforms. In communicating on social media, many individuals without realizing it often make typing errors that can affect the meaning of sentences. This research will apply a model that can check typing errors using Bi-Directional LSTM and transfer learning which results in the Bi-Directional LSTM model achieving an accuracy of 78% after being trained for 20 epochs with a batch size of 64. On the other hand, the transfer learning model achieves an accuracy of 80% with the same epoch and batch size settings. Furthermore, when the Bi-Directional LSTM model was set with 20 epochs and batch size 64, the accuracy increased to 83%, while the transfer learning model achieved 87% accuracy. Finally, with 20 epochs and a batch size of 64, the Bi-Directional LSTM model achieved 87% accuracy, while the transfer learning model achieved an impressive accuracy of 93%. © 2023 IEEE.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Designing R-CNN Algorithm to Detect Halal Composition of Korean Food and Beverages 8

Designing R-CNN Algorithm to Detect Halal Composition of Kor...

引用

8th International Conference on Wireless and Telematics, ICWT 2022

作者： Harika, Maisevli Ramdania, Diena Rauda Rahmadika, Sandi Suwastika, Novian Anggis Delilah, Gina Giftia Azmiana Politeknik Negeri Bandung Computer Engineering and Informatics Department Bandung Indonesia UIN Sunan Gunung Djati Department of Informatics Bandung Indonesia Universitas Negeri Padang Department of Informatics Engineering Padang Indonesia Telkom University Department of Informatics Engineering Bandung Indonesia Uin Sunan Gunung Djati Bandung Department of Religious Studies Bandung Indonesia

ISBN: (数字)9781665451222

ISBN: (纸本)9781665451222

The Korean Wave also influences the consumption patterns of Indonesian people, one of which is the culinary field. Thousands of tons of snacks typical of the country of Ginseng have entered Indonesia since 2015. Unfortunately, some products were found to contain non-halal ingredients. Ignorance of Korean food and beverage composition is crucial for Muslim communities who are obliged to consume halal food. An application was created to detect the halal composition of Korean product packaging. The R-CNN algorithm is applied to this application because of its fast detection ability. A total of 150 packaging product data has been involved in this application. A total of 37 data on haram and doubtful products were obtained. Based on data compiled from the Korean Muslim Federation (KMF), Amir Korea, the Korean Muslimah Indonesia group, and the Korean Muslim group. Application testing is done through the black-box testing method. The study results show that the halal detection application can detect the composition of the packaging in Korean products and provide a warning if there are no halal components. © 2022 IEEE.

关键词： Packaging

来源：评论

学校读者我要写书评

暂无评论

IoT-Enabled LoRa Wireless Sensor Network for Real-Time Air Quality Monitoring with Geographic Information System Mapping

IoT-Enabled LoRa Wireless Sensor Network for Real-Time Air Q...

引用

2023 International Conference on informatics, Multimedia, Cyber and Information Systems, ICIMCIS 2023

作者： Maulana, Nurhuda Matheus Edward, Ian Joseph Universitas Pembangunan Nasional Veteran Jakarta Faculty of Computer Science Jakarta12450 Indonesia Bandung Institute of Technology School of Electrical Engineering and Informatics Bandung40132 Indonesia

ISBN: (纸本)9798350307306

The Internet of Things (IoT) can potentially change how humans interact with the environment. This technology is able to be applied in various fields, such as urban management, agriculture, environmental monitoring, health, and transportation. Conventional air quality monitoring systems are complex sensing equipment and they can measure various parameters of air pollutants. This system requires very high costs and maintenance. Therefore, a low-cost air quality measurement system is required and is able to measure the surrounding air pollutants. By using wireless sensor network technology as the acquisition of environmental monitoring sensor data. A system design was created in the form of geographic information capable of describing air quality in a particular area. The air parameters used are carbon monoxide, dust particulate, light intensity, temperature, and relative humidity. The wireless network uses the LoRa module connected to the gateway. The web server provides a database and geographic information system interface from the gateway through the MQTT broker. Data transmission using a radio frequency of 915 Mhz and able to send data sensors from various points. Outdoor testing at many buildings is capable of transmitting sensor data with a packet loss of 0% at a distance of fewer than 111 meters and the largest packet loss of 51.28% at a distance of 442 meters. © 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

Blockchain-based trusted dispute resolution service architecture

Blockchain-based trusted dispute resolution service architec...

引用

International Conference on Artificial Intelligence, Blockchain, Computing and Security, ICABCS 2023

作者： Sharma, Ravi Mohan Krishna, V. Rama Saikia, Tirtha Suri, Ashish Rivera, Richard Mavaluru, Dinesh Department of Computer Science and Applications Makhanalal Chaturvedi National University of Journalism and Communication Madhya Pradesh Bhopal India CVR College of Engineering Hyderabad India Economics Mittal School of Business Lovely Professional University India School of Electronics and Communication Engineering Shri Mata Vaishno Devi University India Department of Informatics and Computer Science Escuela Politécnica Nacional Quito Ecuador College of Computing and Informatics Saudi Electronic University Riyadh Saudi Arabia

ISBN: (纸本)9781032669663

In the traditional service architecture (Service-Oriented Architecture, SOA), the Web Service provider registers its service description in the registry for service consumers to discover and call services. Although this architecture can provide open service calls, it lacks a dispute resolution mechanism. The trusted invocation of services between service consumers and providers who do not trust each other cannot be guaranteed. Blockchain technology has significant advantages in decentralization and anti-tampering and can be reasonably applied in traditional SOA to solve the problem of service credibility. Trusted SOA architecture based on blockchain is proposed to realize credible service invocation by combining traditional SOA architecture and blockchain technology. During a credible service invocation, or service consumption, The provider encrypts the parameters and sends them to the target service provider;the service provider receives the encrypted parameters and completes the decryption;the service provider completes the service execution and completes the encryption of the output result;finally, the service provider sends the encrypted result to the service provider Consumers complete the construction and chaining of trusted credentials at the same time. Based on the above, when a service dispute occurs, the ruling smart contract will be triggered to handle the service dispute correctly. The experimental results show that compared with the traditional invocation, the proposed method can correctly handle service disputes between service providers and requesters under the premise of ensuring that the growth rate of most Service trusted call times is not more excellent than 30%. by combining traditional SOA architecture and blockchain technology by combining traditional SOA architecture and blockchain technology. © 2024 The Author(s).

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

A Visual Interpretation-Based Self-improved Classification System Using Virtual Adversarial Training 9th

A Visual Interpretation-Based Self-improved Classification S...

引用

19th International Conference on Advanced Data Mining and Applications, ADMA 2023

作者： Jiang, Shuai Kamei, Sayaka Li, Chen Hou, Shengzhe Morimoto, Yasuhiko Graduate School of Advanced Science and Engineering Hiroshima University Hiroshima Japan Graduate School of Informatics Nagoya University Nagoya Japan College of Computer Science and Engineering Shandong University of Science and Technology Qingdao China

ISBN: (纸本)9783031466731

The successful application of large pre-trained models such as BERT in natural language processing has attracted more attention from researchers. Since the BERT typically acts as an end-to-end black box, classification systems based on it usually have difficulty in interpretation and low robustness. This paper proposes a visual interpretation-based self-improving classification model with a combination of virtual adversarial training (VAT) and BERT models to address the above problems. Specifically, a fine-tuned BERT model is used as a classifier to classify the sentiment of the text. Then, the predicted sentiment classification labels are used as part of the input of another BERT for spam classification via a semi-supervised training manner using VAT. Additionally, visualization techniques, including visualizing the importance of words and normalizing the attention head matrix, are employed to analyze the relevance of each component to classification accuracy. Moreover, brand-new features will be found in the visual analysis, and classification performance will be improved. Experimental results on Twitter’s tweet dataset demonstrate the effectiveness of the proposed model on the classification task. Furthermore, the ablation study results illustrate the effect of different components of the proposed model on the classification results. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Total Labelings of Graphs with Prescribed Weights

引用

Journal of Combinatorial Mathematics and Combinatorial Computing 2024年 120卷 367-376页

作者： Bača, Martin Miller, Mirka Phanalasy, Oudone Ryan, Joe Semaničová-Feňovčíková, Andrea Sillasen, Anita A. Department of Applied Mathematics and Informatics Technical University Košice Slovakia School of Mathematical and Physical Sciences The University of Newcastle Australia School of Electrical Engineering and Computer Science The University of Newcastle Australia Department of Mathematics University of West Bohemia Pilsen Czech Republic Department of Informatics King's College London United Kingdom Department of Mathematics National University of Laos Vientiane Laos Department of Mathematical Sciences Aalborg University Aalborg Denmark

The total labeling of a graph G = (V, E) is a bijection from the union of the vertex set and the edge set of G to the set {1, 2, . . . , |V(G)| + |E(G)|}. The edge-weight of an edge under a total labeling is the sum of the label of the edge and the labels of the end vertices of that edge. The vertexweight of a vertex under a total labeling is the sum of the label of the vertex and the labels of all the edges incident with that vertex. A total labeling is called edge-magic or vertex-magic when all the edge-weights or all the vertex-weights are the same, respectively. When all the edge-weights or all the vertex-weights are different then a total labeling is called edge-antimagic or vertex-antimagic total, respectively. In this paper we deal with the problem of finding a total labeling of some classes of graphs that is simultaneously vertex-magic and edge-antimagic or simultaneously vertex-antimagic and edge-magic, respectively. We show several results for stars, paths and cycles. © 2024 Charles Babbage Research Centre. All rights reserved.

关键词： Edge-antimagic total labeling Edge-magic total labeling Vertex-antimagic total labeling Vertex-magic total labeling

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：