检索结果-内蒙古大学图书馆

International Conference of Information and Communication Technology (ICoICT)

作者： Syariful Ikhwan Purwanto Purwanto Adian Fatchur Rochim Doctoral Program of Information System School of Postgraduate Studies Diponegoro University Semarang Indonesia D3 Telecommunication Engineering Institut Teknologi Telkom Purwokerto Banyumas Indonesia Department of Chemical Engineering Faculty of Engineering Diponegoro University Semarang Indonesia Department of Computer Engineering Faculty of Engineering Diponegoro University Semarang Indonesia

This study focuses on network security for Internet of Things (IoT) devices, which are particularly vulnerable to attack due to limited security measures. To protect IoT networks from attackers, the research implemented intrusion detection on the networks. The study compared several Deep Learning algorithms, including DNN, CNN, LSTM, and AE, to identify the most effective algorithm for solving network security problems using intrusion detection. The research used the UNSW-NB15 dataset for testing and employed binary classification for evaluation. The results showed that the DNN algorithm achieved an accuracy value of 99.76% and a loss value of 0.006%, outperforming the other algorithms. This study highlights the importance of implementing intrusion detection in protecting IoT devices and networks and demonstrates the efficacy of the DNN algorithm in detecting and preventing network security breaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recognition of Real-time Traffic Signals Using the Algorithm Fusion of On-board Graphic Chip-based Machine Learning and Deep Learning

引用

Journal of Institute of Control, Robotics and systems 2022年第2期28卷 88-94页

作者： Lee, Jaewook Baek, Seungbeom Choi, Eunji Moon, Heechang Industrial Convergence Interdepartmental Program Autonomous Vehicle·Intelligent Robotics Hongik University Korea Republic of Mechanical and System Design Engineering Hongik University Korea Republic of

The recognition of traffic light in unmanned autonomous driving is one of the key functions. In general, to achieve this goal, deep learning and image processing technology are mainly used in autonomous driving industry. Both technologies have high recognition rates alone, but misrecognition can occur because of interference of the environment. misrecognitions are considered important problem because it may lead to big accidents. In this paper, we suggest using machine learning based on LabVIEW and deep running grounded in Python to increase recognition rate at intersection. By using both technologies, we can minimize the impact of the environment on traffic light recognition and reduce misrecognition. © ICROS 2022.

关键词： Image processing

来源：评论

学校读者我要写书评

暂无评论

A Development of Object Detection system based on Deep Learning Approach to Support the Laparoscope Manipulating Robot (LMR)

A Development of Object Detection System based on Deep Learn...

引用

2022 International Electrical engineering Congress, iEECON 2022

作者： Sonsilphong, Suphachoke Sonsilphong, Amornthep Hormdee, Daranee Khampitak, Kovit Khon Kaen University Data Science Health Informatics Program Academic Affairs Faculty of Medicine Khon Kaen Thailand Rajamangala University of Technology Isan Department of Electrical Engineering Khon Kean Thailand Khon Kaen University Embedded System RD Group Department of Computer Engineering Faculty of Engineering Khon Kean Thailand Khon Kean University Faculty of Medicine Department of Obstetrics and Gynecology Khon Kean Thailand

ISBN: (纸本)9781665402064

This paper presents the development of an object detection system based on the deep learning approach of computer vision to support the laparoscopic surgical robotic position control system. The system comprises two main phases, the training phase, and the real-time operating phase. In the training phase, a modified YOLOv4 algorithm is proposed to be adopted within the Darknet framework for training the weights of detection models. The best detection model is then selected to be assigned to the object detector in the real-time operating phase. The validation result of the detection model across the experiment datasets is 90% accuracy on average during the training phase. To validate the viability of real-time object detection, the proposed system was implemented in two test-cases of gynecologic surgery with the soft-body cadavers. © 2022 IEEE.

关键词： Laparoscopy

来源：评论

学校读者我要写书评

暂无评论

Optimizing Wireless Sensor Network Topology with Deep Reinforcement Learning for Multi-Source/Destination Scenarios

Optimizing Wireless Sensor Network Topology with Deep Reinfo...

引用

IEEE/ACM International Symposium on Big Data Computing (BDC)

作者： Kosei Kobayashi Masayoshi Aritsugi Pedro Henrique González Israel Mendonça Graduate School of Science and Technology Kumamoto University Kumamoto Japan Faculty of Advanced Science and Technology Kumamoto University Kumamoto Japan System Engineering and Computer Science Program Federal University of Rio de Janeiro Rio de Janeiro Brazil

ISBN: (数字)9798350367300

ISBN: (纸本)9798350367317

Wireless sensor networks are widely valued for their effectiveness in real-time data collection. As the amount of data exchanged within such networks grows, designing a robust network topology that maximizes area coverage with minimal sensors has become a critical challenge. The choice of topology impacts key network metrics, including sensor coverage, communication range, connectivity, inference, and installation and management costsIn this paper, we address the Wireless Sensor Network Planning Problem with Multiple Sources/Destinations, presenting an optimization approach based on deep reinforcement learning. This problem is noteworthy, as sensors in various applications are often required to share data within distinct destinationsWe leverage deep reinforcement learning to effectively address the complex task of selecting optimal sensor locations. Our reinforcement learning agent dynamically learns network structure by iteratively adding and removing sensors, optimizing both sensor coverage and the total number of sensors used. Experiment across diverse scenarios demonstrate the effectiveness of our method for network planning problems of varying scales, achieving full coverage with fewer sensors than traditional approaches. Additionally, our approach also produce solutions for large instances where Mixed Integer programming solvers were not able to. Overall, our method was able to reduce the number of sensors used by up to 22.3% compared to other methods.

关键词： Measurement Integer programming Wireless sensor networks Network topology Deep reinforcement learning Real-time systems Sensors Planning Topology Optimization

来源：评论

学校读者我要写书评

暂无评论

Efficient Node Reduction Heuristic for GNN-Based Traffic Speed Forecasting

Efficient Node Reduction Heuristic for GNN-Based Traffic Spe...

引用

IEEE/ACM International Symposium on Big Data Computing (BDC)

作者： Yuto Inokuchi Pedro Henrique González Masayoshi Aritsugi Israel Mendonça Graduate School of Science and Technology Kumamoto University Kumamoto Japan System Engineering and Computer Science Program Federal University of Rio de Janeiro Rio de Janeiro Brazil Faculty of Advanced Science and Technology Kumamoto University Kumamoto Japan

ISBN: (数字)9798350367300

ISBN: (纸本)9798350367317

In this paper, we aim to reduce the number of nodes from Graph Neural Networks (GNNs), thereby simplifying models and reducing computational costs. GNNs are highly effective for various tasks, such as prediction, classification, and clustering, due to their ability to learn node and edge attributes and relationships, and they have been utilized for intelligent transportation systems recently by converting sensor networks into graph structures. Deep spatio-temporal neural networks, including Spatio-Temporal Graph Convolutional Networks (STGCNs), capture spatial and temporal dependencies, making them suitable for traffic speed forecasting, traffic demand prediction, and travel time estimation. Despite their success, GNNs face challenges in industrial applications due to significant memory usage and time consumption. In this paper, we propose a new approach to node reduction that outperforms existing methods in computational efficiency. Our experiments on two real-world traffic datasets demonstrate that using the heuristic and edge information to reduce nodes can cut computation time of optimization up to 95% and, by eliminating noise, can even enhance prediction accuracy.

关键词： Graph convolutional networks Noise Memory management Estimation Computational efficiency Forecasting Optimization Intelligent transportation systems Faces Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Optimization of Node Reduction Using BRKGA for GNN-Based Traffic Speed Forecasting

Optimization of Node Reduction Using BRKGA for GNN-Based Tra...

引用

Congress on Evolutionary Computation

作者： Yuto Inokuchi Pedro Henrique González Israel Mendonça Masayoshi Aritsugi Graduate School of Science and Technology Kumamoto University Kumamoto Japan System Engineering and Computer Science Program Federal University of Rio de Janeiro Rio de Janeiro Brazil Faculty of Advanced Science and Technology Kumamoto University Kumamoto Japan

ISBN: (数字)9798350308365

ISBN: (纸本)9798350308372

While Spatio-Temporal Graph Convolutional Networks (STGCNs) are an effective method for traffic speed fore-casting, their training and inference tend to be time-consuming. In this paper, we aim to refine these networks by strategically reducing their number of nodes, thereby boosting computational efficiency. The nodes in these graphs represent data observed for road segments, and by analyzing the interconnections and layout of the graph, we can identify nodes with minimal contribution to overall performance. Removing these nodes can potentially decrease computation time while maintaining the prediction accuracy. We employ the Biased Random-Key Genetic Algorithm (BRKGA) to identify a good set of nodes for removal, based on a predefined percentage reduction of the original graph size (e.g., retaining 95 % of the original graph). We evaluate different graph size configurations, ranging from 95 % to 70 % node retention, to determine the least impactful node set performance. Our experiments on three real-world datasets reveal that reducing nodes can decrease computation time by up to 29%, and as a byproduct of removing noise, even improve the prediction accuracy.

关键词： Training Accuracy Graph convolutional networks Roads Noise Layout Evolutionary computation

来源：评论

学校读者我要写书评

暂无评论

Efficient Hyperparameter Optimization Using Deep Q-Network and BRKGA

Efficient Hyperparameter Optimization Using Deep Q-Network a...

引用

Congress on Evolutionary Computation

ISBN: (数字)9798350308365

ISBN: (纸本)9798350308372

Hyperparameter optimization (HPO) is paragon to maximize performance when designing machine learning models. Among different HPO methods, Genetic Algorithm (GA) based optimization is considered effective because it allows a wide and diverse range of solutions to be explored. However, GA's exploratory nature makes this type of algorithm to evaluate many solutions that do not improve the overall performance. This is specially costly when the objective function to be evaluated is time-consuming, like in the HPO field. In this paper, we propose an efficient hybrid algorithm that is able to reduce computational cost by combining deep reinforcement learning with the Biased Random Key Genetic Algorithm (BRKGA), a variant of genetic algorithms. Our reinforcement learning agent has a decision-making role during the population's fitness calculation, in which it filters out chromosomes that would not improve the overall fitness of the population. The agent uses small amounts of pre-trained data to identify trends in potentially good solutions, and carry out its decision process. We conduct experiments on eight different datasets to assess the effectiveness of the proposed method, and the results show that the proposed method can significantly reduce the computation time of hyperparameter search using BRKGA (up to 44% reduction in computational time) without compromising the quality of the solution (no statistically difference in results).

关键词： Machine learning algorithms Filters Sociology Evolutionary computation Hyperparameter optimization Market research Linear programming

来源：评论

学校读者我要写书评

暂无评论

Surgical Instrument Detection for Laparoscopic Surgery using Deep Learning 19

Surgical Instrument Detection for Laparoscopic Surgery using...

引用

19th International Conference on Electrical engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2022

作者： Boonkong, Apiwat Hormdee, Daranee Sonsilphong, Suphachoke Khampitak, Kovit Khon Kaen University Embedded System RandD Group Computer Engineering Khon Kaen Thailand Khon Kaen University Data Science and Health Informatics Program Academic Affairs Khon Kaen Thailand Khon Kaen University Faculty of Medicine Department of Obstetrics and Gynecology Khon Kaen Thailand

ISBN: (纸本)9781665485845

Laparoscopic surgery has transformed conventional open surgery. Robot-Assisted laparoscopic surgery which is minimally invasive is effective for operations in limited space. Nevertheless, the robotic system which is utilized in such surgery can inflict impair to the surgical instruments, organs, or tissues as a consequence of the narrow field of view and space available to operate, and insufficient tactile response. In laparoscopy, the surgeon observes what he operates via digital images which are displayed on a monitor. In addition to the surgeon's expertise, the image-guided surgery system could offer him significant support if that system is capable of understanding those images. Computer Vision has been able to proceed due to the emergence of Machine Learning, and especially Deep Learning. This paper applies Deep Learning for surgical instrument detection for laparoscopic surgery. The fastest model, based on results trained on the COCO 2017 Dataset on TensorFlow Framework, for each of 4 algorithms-Faster-RCNN, SSD, CenterNet and EfficientDet-from Model Zoo, along with YOLOv4 on Darknet Framework, have been investigated in this work. The evaluation metrics used are Precision, Recall and F1-score. The results reveal that each model plays its part well;however, YOLOv4 seemed to breakthrough this statement by offering grate result for all three accuracy metrics. © 2022 IEEE.

关键词： Laparoscopy

来源：评论

学校读者我要写书评

暂无评论

High-Performance Chip Design With Parallel Architecture for Magnetic Field Imaging system

引用

IEEE Transactions on Instrumentation and Measurement 2024年 73卷 1-13页

作者： Lin, Ming-Yi Hsieh, Sheng-Hsien Chen, Ching-Han Lin, Chun-Hung Yuan Ze University Department of Computer Science and Engineering Taoyuan320315 Taiwan National Pingtung University of Science and Technology Program of Artificial Intelligence and Mechatronics Pingtung912301 Taiwan National Central University Department of Computer Science and Information Engineering Taoyuan32001 Taiwan International Games System Company Ltd. New Taipei City248 Taiwan

To address the limitations of typical coil detection systems and enhance the performance of traditional magnetic field imaging (MFI) systems, we propose a MFI system that uses a 4×4 array of anisotropic magnetoresistance (AMR) sensors. The core controller of the proposed system was designed using a pipelined parallelization algorithm and implemented on a high-speed field-programmable gate array (FPGA) in a fully hardware-based architecture. The designed MFI system can achieve parallel acquisition of magnetic field components from the 16-channel AMR sensor array, parallel data processing, parallel data transmission, and parallel computations in a single cycle of only 4 ms. Compared with typical detection systems, the proposed solution not only exhibits superior performance but can also provide dynamic visual representations of sensed information. © 1963-2012 IEEE.

关键词： Parallel architectures

来源：评论

学校读者我要写书评

暂无评论

Distributed Observer Approach for Scalable Formation Control of Multi-Agent Network

Distributed Observer Approach for Scalable Formation Control...

引用

2020 International Seminar on Intelligent Technology and Its Application, ISITIA 2020

作者： Djamari, Djati Wibowo Fikri, Muhamad Rausyan Mechanical Engineering Study Program Sampoerna University Jakarta Indonesia Information System Study Program Sampoerna University Jakarta Indonesia

ISBN: (纸本)9781728174136

This work studies formation control of Multi-Agent systems (MASs) where its formation size is scalable via a scaling factor (scalable formation). Previous works on scalable formation are limited to either fixed undirected graph or fixed directed graph with p-rooted graph condition. This work proposes a novel distributed algorithm for scalable formation based on a distributed observer to estimate agents' positions. The novel algorithm results in a new matrix, a Laplacian matrix with additional diagonal terms, where the desired formation pattern is embedded in this diagonal terms. With the proposed algorithm, only spanning tree condition is needed as the necessary and sufficient condition to achieve the scalable formation. Numerical examples are shown to illustrate the proposed method. © 2020 IEEE.

关键词： Directed graphs

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：