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

Development of A Deep Learning Hybrid Model for Classification of Plastic Waste Objects in the Coastal Environment

Development of A Deep Learning Hybrid Model for Classificati...

引用

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

作者： Djafar, Imran Indrabayu Syarif, Syafruddin Hasanuddin University Dipa Makassar University Doctoral Program of Electrical Engineering Department Makassar Indonesia Hasanuddin University Makassar Department of Informatics Indonesia Hasanuddin University Department of Electrical Engineering Makassar Indonesia

ISBN: (纸本)9798331513320

Plastic, glass, metal, and wood waste has become a global scourge and nightmare to the marine environment and the development of the coastal areas. This paper aims at developing a hybrid model of deep learning technique using Convolutional Neural Networks (CNN) and Vision transformers (ViT) in the performance of detecting underwater waste materials. The model is designed with the use of transfer learning and high-resolution imaging sourced from underwater drones to help overcome the challenges of underwater work such as poor visibility and insufficient ambient light. The local features are extracted using CNNs and the global spatial relationships of the images are attended to by the ViTs. The results achieved a waste detection accuracy rate of about 90%, which is effective even in difficult environmental conditions. The concept is for a waste management system where drones or underwater robotics systems can assist automated waste management, waste treatment processes, and aid marine renovation activities. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Technology-Enhanced Learning for User Security Awareness Using AI-based Naive RAG: A Design and Prototype

Technology-Enhanced Learning for User Security Awareness Usi...

引用

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

作者： Pratama, I. Putu Agus Eka Widyantara, I. Made Oka Linawati Gunantara, Nyoman Suakanto, Sinung Irawan, Eka Tresna Udayana University Doctoral Program of Engineering Sciences Faculty of Engineering Bali Badung Indonesia Udayana University Dept. of Electrical Engineering Faculty of Engineering Bali Badung Indonesia Telkom University Dept. of Information System West Java Bandung Indonesia Mayar International Pte. Ltd. Singapore

ISBN: (纸本)9798331513320

The increasing use of Information Technology (IT) in all areas of life, followed by increasing cybersecurity threats on the user side, makes cybersecurity awareness among users an obligation that must be met. Several solutions currently available (guides, discussion forums, workshops) have not been able to provide good results and are lacking in terms of user engagement, adaptability, and optimizing available resources, so technology-based learning is needed, especially AI. This paper introduces the design and prototype of an AI-based learning system, especially with the Naive Retrieval-Augmented Generation (Naive RAG) method with three steps, including Retrieval, Augmented, and Generation. The system combines contextual user questions and answers with internal and domain knowledge systems to explain cybersecurity awareness to users dynamically and personally. The prototype that has been developed is then tested using the Black Box Testing method to evaluate functionality and usability. The test results show that the functionality of the system built has run well with a percentage of success of 100%, so it can be used as a technologybased learning medium for education and learning of user security awareness. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Harnessing YOLO for Loose Fruits Detection: Boosting Productivity in Palm Oil Plantations

Harnessing YOLO for Loose Fruits Detection: Boosting Product...

引用

Advancement in Data Science, E-learning and Information Systems (ICADEIS), International Conference on

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

ISBN: (数字)9798331513320

ISBN: (纸本)9798331513337

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.

关键词： YOLO Productivity Training Automation Oils Plantations Manuals Rocks Robustness Testing

来源：评论

学校读者我要写书评

暂无评论

Development of A Deep Learning Hybrid Model for Classification of Plastic Waste Objects in the Coastal Environment

Development of A Deep Learning Hybrid Model for Classificati...

引用

Advancement in Data Science, E-learning and Information Systems (ICADEIS), International Conference on

作者： Imran Djafar Indrabayu Syafruddin Syarif Doctoral Program of Electrical Engineering Department Hasanuddin University Dipa Makassar University Makassar Indonesia Department of Informatics Hasanuddin University Makassar Indonesia Department of Electrical Engineering Hasanuddin University Makassar Indonesia

ISBN: (数字)9798331513320

ISBN: (纸本)9798331513337

关键词： Waste management Deep learning Transfer learning Sea measurements Metals Glass Feature extraction Transformers Convolutional neural networks Drones

来源：评论

学校读者我要写书评

暂无评论

Technology-Enhanced Learning for User Security Awareness Using AI-based Naive RAG: A Design and Prototype

Technology-Enhanced Learning for User Security Awareness Usi...

引用

Advancement in Data Science, E-learning and Information Systems (ICADEIS), International Conference on

作者： I Putu Agus Eka Pratama I Made Oka Widyantara Linawati Nyoman Gunantara Sinung Suakanto Eka Tresna Irawan Doctoral Program of Engineering Sciences Faculty of Engineering Udayana University Badung Bali Indonesia dept. of Electrical Engineering Faculty of Engineering Udayana University Badung Bali Indonesia dept. of Information System Telkom University Bandung West Java Indonesia Mayar International Pte. Ltd. Singapore

ISBN: (数字)9798331513320

ISBN: (纸本)9798331513337

关键词： Electronic learning Retrieval augmented generation Knowledge based systems Prototypes Learning (artificial intelligence) Computer security Usability Information technology Testing Information systems

来源：评论

学校读者我要写书评

暂无评论

A Neuroelectronic Interface with Microstructured Substrates for Spiral Ganglion Neurons Cultured In Vitro: Proof of Concept

Biosensors

引用

Biosensors 2025年第4期15卷 224-224页

作者： Delipetar, Boris Žarković Krolo, Jelena Bedalov, Ana Kovačić, Damir Department of Physics Faculty of Science University of Split Ruđera Boškovića 33 Split21000 Croatia University of Split Ruđera Boškovića 31 Split21000 Croatia The Doctoral Program in Mechanical Engineering Faculty of Electrical Engineering Mechanical Engineering and Naval Architecture University of Split Ruđera Boškovića 32 Split21000 Croatia The Doctoral Program in Biophysics Faculty of Science University of Split Ruđera Boškovića 33 Split21000 Croatia Bedalov d.o.o for Research Development and Consulting Ulica T. Antunovića 17 Kaštel Sućurac21212 Croatia

In this study, we present a proof-of-concept neuroelectronic interface (NEI) for extracellular stimulation and recording of neurophysiological activity in spiral ganglion neurons (SGNs) cultured in vitro on three-dimensional, micro-patterned substrates with customized microtopographies, integrated within a 196-channel microelectrode array (MEA). This approach enables mechanotaxis-driven neuronal contact guidance, promoting SGN growth and development, which is highly sensitive to artificial in vitro environments. The microtopography geometry was optimized based on our previous studies to enhance SGN alignment and neuron-electrode interactions. The NEI was validated using SGNs dissociated from rat pups in the prehearing period and cultured for seven days in vitro (DIV). We observed viable and proliferative cellular cultures with robust neurophysiological responses in the form of local field potentials (LFPs) resembling action potentials (APs), elicited both spontaneously and through electrical stimulation. These findings provide deeper insights into SGN behavior and neuron-microenvironment interactions, laying the groundwork for further advancements in neuroelectronic systems. © 2025 by the authors.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

MMA-Net: Multi-Modal Attention Network for 2-D Object Detection in Autonomous Driving

MMA-Net: Multi-Modal Attention Network for 2-D Object Detect...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Abhilash Gaur Shubh Goel Kanishk Goel Seshan Srirangarajan Po-Hsuan Tseng Kai-Ten Feng IIT Delhi-NYCU Taiwan Joint Doctoral Program Bharti School of Telecommunication Technology and Management Indian Institute of Technology Delhi (IIT Delhi) New Delhi India International College of Semiconductor Technology National Yang Ming Chiao Tung University (NYCU) Hsinchu Taiwan Department of Electrical Engineering IIT Delhi New Delhi India Department of Electrical Engineering Bharti School of Telecommunication Technology and Management IIT Delhi New Delhi India Department of Electronic Engineering National Taipei University of Technology Taipei Taiwan Department of Electronics and Electrical Engineering NYCU Hsinchu Taiwan

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Autonomous driving technology relies heavily on sensor data for environment perception. Heterogeneous sensors such as lidar, radar, and camera have their own strengths and limitations. Therefore, relying on any single sensor would restrict the effectiveness of autonomous driving technology. However, integrating data from such heterogeneous sensors poses challenges due to differences in their representations. This article outlines a deep learning network aimed at designing modality-agnostic multi-modal fusion architecture. We study sensor data from different modalities and learn fine-grained representations using modality-specific feature encoders independently. Then, a multimodal attention-based network (MMA-Net) is proposed to fuse the data from heterogeneous modalities. The proposed MMA-Net fuses multi-modal sensor data by jointly exploiting the inter-modality and intra-modality relationships among camera, lidar, and radar sensors. The effectiveness of the proposed multi-modal fusion architecture is demonstrated using 2-D object detection metrics through extensive experiments on a dataset generated using the CARLA simulator.

关键词： Laser radar Fuses Multimodal sensors Radar detection Object detection Signal processing Cameras Speech processing Autonomous vehicles Meteorology

来源：评论

学校读者我要写书评

暂无评论

Enhancing Diagnostic Accuracy for Knee Osteoarthritis Using a Deep Learning Approach

Enhancing Diagnostic Accuracy for Knee Osteoarthritis Using ...

引用

International Symposium on Applied Science 2024, ISAS 2024

作者： Raza, Aquib Ching, Congo Tak Shing Liu, Peng-Ta Phan, Thien-Luan Tran, Ngoc-Luan Nguyen, Ha Anh T. Rameez, Mohammad Li, Hung-Chung Linh, Dao Nguyen Phuong Van Hieu, Nguyen Tran, Trung Nghia National Taiwan University Taipei City10673 Taiwan Research Center for Information Technology Academia Sinica Taipei City11529 Taiwan Graduate Institute of Biomedical Engineering National Chung Hsing University Taichung402 Taiwan Department of Electrical Engineering National Chi Nan University Nantou County Taiwan Advanced Plant and Food Crop Biotechnology Center National Chung Hsing University Taichung402 Taiwan International Doctoral Program in Agriculture National Chung Hsing University Taichung402 Taiwan Fall Prevention Center Department of Physical Medicine & Rehabilitation Changhua Christian Hospital Changhua500 Taiwan Department of Physics and Electronic Engineering University of Science Vietnam National University - Ho Chi Minh City Ho Chi Minh City70000 Viet Nam Department of Computer Science University of York York HeslingtonYO10 5DD United Kingdom Undergraduate Program of Intellectual Creativity Engineering National Chung Hsing University Taichung402 Taiwan Ho Chi Minh City72409 Viet Nam HCMUT Vietnam National University Ho Chi Minh City Thu Duc Ho Chi Minh City71308 Viet Nam

This research introduces a deep learning framework that combines convolutional neural networks with autoencoders to improve the diagnostic accuracy of knee osteoarthritis. The study utilized a publicly available dataset from the Mendeley Data repository, where knee joint images were preprocessed using Contrast Limited Adaptive Histogram Equalization to enhance contrast and ensure consistent image sizing. Initially, an autoencoder was employed in an unsupervised manner to learn compressed representations of the data. These representations were then used to train a CNN to classify knee images into 'healthy' and 'osteoarthritic' categories. The model was trained using an 80:20 split for training and testing data, incorporating early stopping and data augmentation techniques to prevent overfitting and enhance generalization. Performance metrics such as accuracy, precision, recall, and the area under the Receiver Operating Characteristic curve (ROCAUC) were used to evaluate the model, resulting in a high test accuracy of 98.95%. The high precision and recall rates further confirmed the model's robustness in diagnosing KOA. To enhance interpretability, Gradient-weighted Class Activation Mapping (Grad-CAM) was applied to identify critical regions in the images that influenced the model's decisions. Additionally, t-Distributed Stochastic Neighbor Embedding (t-SNE) was used to visualize the high-dimensional encoded features in a two-dimensional space, providing deeper insights into how the model differentiates between classes. The promising results of this deep learning approach suggest its potential for broader applications in medical imaging diagnostics. By providing healthcare professionals with a tool that enhances diagnostic accuracy and operational efficiency, this framework lays the foundation for developing scalable, AI-driven diagnostic systems for various complex medical conditions. © 2025 Institute of Physics Publishing. All rights reserved.

关键词： Joints (anatomy)

来源：评论

学校读者我要写书评

暂无评论

Ant Colony Optimization-Based Path Planning for Autonomous Vehicle Navigation Systems 4

Ant Colony Optimization-Based Path Planning for Autonomous V...

引用

4th International Conference on electrical engineering and Computer Science, ICECOS 2024

作者： Sari, Desi Windi Dwijayanti, Suci Suprapto, Bhakti Yudho Universitas Sriwijaya Faculty of Engineering Department of Electrical Engineering Doctoral Program in Engineering Science Palembang Indonesia Universitas Sriwijaya Faculty of Engineering Department of Electrical Engineering Palembang Indonesia

ISBN: (纸本)9798350368253

A crucial aspect of autonomous vehicles is path planning, which involves using various algorithms to determine the most efficient routes. This study investigates the application of the Ant Colony Optimization (ACO) algorithm to create a system for identifying the shortest path. The process includes collecting coordinate data from specific test locations on the Universitas Sriwijaya Indralaya campus to generate a graph-based map for analysis. The study begins with gathering route data through the Google Maps application, which includes 182 routes. In simulation tests, the routes generated by ACO differ from those suggested by Google Maps;sometimes, the ACO route is longer and sometimes shorter, due to the probabilistic nature of the ACO algorithm in finding optimal routes. The average error compared to Google Maps is 11.7 meters. Additional tests introduce obstacles on the road, requiring the system to find alternative routes. For instance, the initial route from the auditorium to the Faculty of Science and Math is 38-39-11-53-110-54-111 with a route length of 670 m. After adding a roadblock in front of the Faculty of engineering, the route changes to 38-39-116-40-70-69-56-111, with a route length of 730 meters. These tests demonstrate that the ACO algorithm effectively identifies the best routes for autonomous vehicles, both under normal conditions and when obstacles are present. © 2024 IEEE.

关键词： Ant colony optimization

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：