检索结果-内蒙古大学图书馆

2025 International Conference on Advancement in Data Science, E-learning and Information System, ICADEIS 2025

作者： Warni, Elly Indrabayu Achmad, Andani Syahsir, Aldilah Rezki Rhamadani Universitas Hasanuddin Doctoral Program of Electrical Engineering Department Informatics Department Makassar Indonesia Universitas Hasanuddin Electrical Engineering Department Makassar Indonesia Universitas Hasanuddin Informatics Department Makassar Indonesia

ISBN: (纸本)9798331513320

This study explores the use of the YOLOv5 algorithm to detect loose fruits palm oil in plantations, improve collection efficiency, and reduce reliance on manual labor. Loose fruits have high economic value due to their oil content, but they are often not collected, resulting in financial losses and the growth of weeds around oil palm trees. Conventional manual methods are often ineffective;thus, automatic detection is required. The dataset comprises 525 images of loose fruits, covering complex conditions on plantations, and secondary data from Roboflow, including nontarget objects, such as rocks and dry leaves, to train the model to accurately distinguish loose fruits. During training, several parameters were optimized: batch size, learning rate, optimizer type, weight decay, and momentum, which showed that small batch sizes provided higher mAP50 values, whereas large batches increased mAP50:95, indicating the ability to detect objects at higher levels of complexity. Testing in a scenario with loose fruits clearly visible and partially covered with leaves or grass showed that YOLOv5 could detect loose fruits well despite some constraints in the obstructed environment. The results of this study show that, with appropriate parameter settings, YOLOv5 can be a reliable basis for automated loose fruit collection systems, potentially improving operational efficiency in oil palm plantations and contributing to the development of automation in the agricultural sector. © 2025 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Analysis on Performance of Semi-Real-Time Transcription on Health App 18

Analysis on Performance of Semi-Real-Time Transcription on H...

引用

18th International Conference on Telecommunication Systems, Services, and Applications, TSSA 2024

作者： Indrasary, Yoenie Nugraha, Daniel Prihatmanto, Ary Setijadi Sarief, Ivany Gunawan, Rudy Yunautama, Dhema School of Electrical Engineering and Informatics Institut Teknologi Bandung Doctoral Program of Electrical Engineering and Informatics Bandung Indonesia State Polytechnic of Banjarmasin Banjarmasin Indonesia School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia Universitas Sangga Buana Faculty of Engineering Dept. of Electrical Engineering Bandung Indonesia Universitas Sangga Buana Directorate of Vocational Dept. of Informatics Engineering Bandung Indonesia

ISBN: (纸本)9798331527686

The fragmentation of health information systems has hindered seamless data exchange in healthcare services, posing challenges in achieving efficient, real-time access to patient health data. This study addresses these issues by evaluating the implementation of a semi-real-time transcription system using a distributed architecture with a message broker to enhance the documentation of clinical examination processes in primary health services. The research focuses on assessing the feasibility of this approach by measuring key performance indicators such as latency and word error rate (WER) during clinical conversation transcription. Audio recordings were segmented into shorter fragments to simulate real-time transcription, and data transmission was conducted through the Advanced Message Queuing Protocol (AMQP). The findings demonstrate that the average latencys achieved by semi-real-time transcription system is 7.7s, indicating its potential suitability for clinical documentation applications that do not require strict real-time processing. However, glitches observed in the message broker's forwarding mechanism suggest the need for further optimization to ensure consistent performance. Future work aims to develop strategies to minimize transcription errors, enhance reliability, and improve the overall integration of this system in healthcare settings. This study contributes to the advancement of health information systems by offering architecture into scalable and effective methods for semi-real-time data transcription and interoperability. © 2024 IEEE.

关键词： Audio recordings

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study of Code Pattern Reuse and Pattern Preference Consistency in Novice programmers 23rd

An Empirical Study of Code Pattern Reuse and Pattern Prefe...

引用

23rd International Conference on Web-Based Learning, ICWL 2024 was held in conjunction with the 9th International Symposium on Emerging Technologies for Education, SETE 2024

作者： Lei, Philip I. S. Mendes, António José Lam, Chan-Tong CISUC Department of Informatics Engineering University of Coimbra Coimbra Portugal Computing Program Macao Polytechnic University Macao SAR China

ISBN: (纸本)9789819644063

After learning the basic features of a programming language, such as expressions and control statements, novice programmers need to combine these features to solve programming questions. Some of these combined code snippets are reusable constructs useful to solve future questions. They are referred to as plans, schemas, or patterns in the literature. An example of such a pattern is determining the equality of three values using the ‘equal and logical and operators. Previous research has investigated the acquisition of these patterns by observing and interviewing novice programmers as they solve programming problems. In this paper, we test the hypothesis that students tend to reuse acquired patterns to solve subsequent problems by analyzing a computer science education dataset called CodeWorkout, which contains students’ code submissions for introductory-level programming questions. We employed directed labeled tree to represent the Abstract Syntax Tree (AST) of the submitted code and the patterns. To search for a pattern, we first applied the subgraph isomorphism algorithm VF2 with wildcard node labels to identify candidate matches, followed by enforcing the proper ordering of descendant nodes between the pattern and the candidate matches. Experimental results demonstrate that our approach effectively identifies common usage of patterns. Moreover, the findings indicate that if a student employs a pattern in one question, they are likely to reuse the same pattern in a subsequent question. This paper also reveals that when multiple alternative patterns exist for the same function, students tend to maintain their preference for a particular alternative while solving different questions. These insights can inform future curriculum design and instructional strategies in programming education. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Multi-Step-Ahead Prediction of User Movement on 5G Networks Using the Long Short-Term Memory Method 18

Multi-Step-Ahead Prediction of User Movement on 5G Networks ...

引用

18th International Conference on Telecommunication Systems, Services, and Applications, TSSA 2024

作者： Timoteo, Adriel Benyamin, Fabian Rafinanda Anargyarahman, Naufal Bhanu Iskandar Yuliana, Hajiar School of Electrical Engineering and Informatics Telecommunications Engineering Program Bandung Institute of Technology Bandung Indonesia Jenderal Achmad Yani University Faculty of Engineering Department of Electrical Engineering Cimahi Indonesia

ISBN: (纸本)9798331527686

Since the initial launch of 5G networks in 2018, 5G technology has rapidly expanded to cover about 40% of the world's population, offering higher bandwidth, faster connectivity, and lower latency than 4G. However, due to its higher frequency operation, 5G necessitates more frequent handovers, making efficient handover performance crucial. This research focuses on enhancing handover efficiency by predicting user movement using Long Short-Term Memory (LSTM) models for multi-step-ahead prediction. The model created will utilize 60 seconds of historical data to predict 10 seconds ahead, with a target to achieve an average prediction accuracy of less than 20 meters with a latency under 100 ms. The study employs TensorFlow for model training, leveraging the Grab-Posisi dataset, and utilizes Plotly and TensorBoard for result visualization. Six model variations were trained, with the 16-unit model trained for 3106 epochs performing best, achieving 16.99 meters accuracy and 31 ms latency. The findings suggest that LSTM is effective for predicting user movement in 5G networks, with potential accuracy improvements through extended training epochs. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Application of the K-Medoids Clustering Model and Borda Decision Group in Viewing Flood Area Groupings in North Aceh Regency

Application of the K-Medoids Clustering Model and Borda Deci...

引用

2023 International Workshop on Artificial Intelligence and Image Processing, IWAIIP 2023

作者： Fuadi, Wahyu Sahputra, Ilham Fariadi, Dedi Agustinar Universitas Malikussaleh Informatics Engineering Study Program Faculty of Engineering Lhokseumawe Indonesia Universitas Malikussaleh Information Systems Study Program Faculty of Engineering Lhokseumawe Indonesia Universitas Malikussaleh Electrical Engineering Study Program Faculty of Engineering Lhokseumawe Indonesia

ISBN: (纸本)9798350382914

The importance of the K-Medoid model in viewing disaster-prone areas in each sub-district in North Aceh. The advantage of the k-medoid model results is that it has better cluster centers than other models. The novelty of this research is the cluster results are assessed by each decision maker using the Borda group model in providing flood disaster assistance or areas that are a priority for handling, which are included in the flood-prone cluster. Therefore, this research is important because it can be used to identify areas most severely affected by flooding. This research aims to analyze and identify the impact of flood hazards based on grouping and decision-making using the Borda group model in each sub-district in North Aceh. The results of the k-medoids model show 3 clusters that can see potential areas for flood disasters, namely very vulnerable. There are six sub-districts. For the k-medoids results, ten sub-districts are vulnerable. Lastly, the safe zones are 11 sub-districts. This research's k-medoid model analysis is more precise in seeing clusters of places that are potentially affected by flooding based on spatial maps of their nearest neighboring areas. The percentage of each cluster is as follows: Cluster 1 is 4%, Cluster 2 is 55%, and Cluster 3 is 41%. The k-medoid model provided this result after three iterations, with a closeness difference of 1.594510537. The results of the Borda model group research can be used as a recommendation for the areas that receive the highest priority in disaster management. © 2023 IEEE.

关键词： Floods

来源：评论

学校读者我要写书评

暂无评论

IoT-Integrated Machine Learning for Real-Time Soil Nutrient Monitoring and Horticultural Crop Recommendations 10

IoT-Integrated Machine Learning for Real-Time Soil Nutrient ...

引用

10th IEEE Information Technology International Seminar, ITIS 2024

作者： Wahid, Abdul Parenreng, Jumadi Mabe Aswandi Alwi, Ananta Dwi Prayoga Zain, Satria Gunawan Setialeksana, Wirawan Universitas Negeri Makassar Informatics and Computer Engineering Department Makassar Indonesia Politeknik Negeri Lhokseumawe Network Engineering Technology Study Program Lhokseumawe Indonesia

ISBN: (纸本)9798331521295

Farmers and agricultural newcomers often rely on intuition for plant nutrient management, leading to inaccuracies. This study presents a real-time soil nutrient monitoring and plant recommendation system using IoT and machine learning. The prototype integrates an ESP32 microcontroller, NPK sensor, soil pH sensor, and DHT11 with an application and a machine learning model. The model employs a hard voting method combining random forest, LightGBM, and support vector machine algorithms, deployed via Flask API and hosted on Vercel. Testing showed the system effectively monitors soil nutrients in real-time, with a pH sensor error margin of ±0.51 and NPK sensor readings displaying a non-linear increase in levels. The hard voting method achieved 98.5% accuracy, with recommendation processing taking less than one second (371.17ms) and CPU usage at 7%. System performance depends on internet speed, while recommendation accuracy is influenced by temperature and humidity. This system offers a practical solution for precision agriculture by optimizing nutrient application and plant recommendations. © 2024 IEEE.

关键词： pH sensors

来源：评论

学校读者我要写书评

暂无评论

Web-Based Incentive Calculations System at CV Karya Prima using Prototyping Method 7

Web-Based Incentive Calculations System at CV Karya Prima us...

引用

7th International Conference on New Media Studies, CONMEDIA 2023

作者： Cornelia, Monica Suryasari Universitas Multimedia Nusantara Information Systems Study Program Faculty of Engineering and Informatics Tangerang Indonesia

ISBN: (纸本)9798350307504

Consumption is an essential aspect of daily life, and fulfilling customer needs requires efficient distribution of goods. Therefore, distributors are needed and they frequently set targets for their employees to achieve, and motivation plays a significant role in employee performance. An organization that distributes goods called CV Karya Prima motivates its employees by offering incentives. However, manual incentive calculation sets out problems such as a lack of progress tracking, irregular payout dates, and probable inaccuracies. This study aims to develop a web-based incentive calculation system using the analytical hierarchy process method and a database for data retrieval. The system utilizes PHP, CodeIgniter, and MySQL and adopts the SDLC prototyping method. The developed system is focused on the sales division and variables like total sales, effective calls, calls, and outlets. The web-based system is capable of solving the issues using the features that were built based on user needs and have already been tested through user acceptance testing. © 2023 IEEE.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Empirical mode decomposition of near-infrared spectroscopy signals for predicting oil content in palm fruits

引用

Information Processing in Agriculture 2023年第3期10卷 289-300页

作者： Inna Novianty Ringga Gilang Baskoro Muhammad Iqbal Nurulhaq Muhammad Achirul Nanda Computer Engineering Study Program College of Vocational StudiesIPB UniversityBogor 16680Indonesia Informatics Management Study Program College of Vocational StudiesIPB UniversityBogor 16680Indonesia Technology and Plantation Production Management Study Program College of Vocational StudiesIPB UniversityBogor 16680Indonesia Department of Agricultural and Biosystem Engineering Faculty of Agro-Industrial TechnologyUniversitas PadjadjaranJatinangor 45363Indonesia

Oil content estimation in palm fruits is a precious property that significantly impacts oil palm production,starting from the upstream and *** content can be used to monitor the progress of the oil palm fresh fruit bunch(FFB)and be applied to identify product *** on the near-infrared(NIR)signals,this study proposes an empirical mode decomposition(EMD)technique to decompose signals and predict the oil content of palm ***,350 palm fruits with Tenera varieties(Elaeis guineensis ***),at various ages of maturity,were harvested from the Cikabayan Oil Palm Plantation(IPB University,Indonesia).Second,each sample was sent directly to the laboratory for NIR signal measurements and oil content ***,the EMD analysis and arti-ficial neural network(ANN)were employed to correlate the NIR signals and oil ***,a robust EMD-ANN model is generated by optimizing the lowest possible *** on performance evaluation,the proposed technique can predict oil content with a coefficient of determination(R2)of 0.933±0.015 and a root mean squared error(RMSE)of 1.446±*** results demonstrate that the model has a good predictive capacity and has the potential to predict the oil content of palm fruits directly,without neither solvents nor reagents,which makes it environmentally ***,the proposed technique has a promising potential to be applied in the oil palm *** like this will lead to the effective and efficient management of oil palm production.

关键词： Artificial neural network Empirical mode decomposition Oil palm Oil content prediction

来源：评论

学校读者我要写书评

暂无评论

Building a Simple COVID-19 Knowledge Graph in Bahasa Indonesia: A Preliminary Study 3

Building a Simple COVID-19 Knowledge Graph in Bahasa Indones...

引用

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

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：