检索结果-内蒙古大学图书馆

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 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

Mobile Application for Elderly Care 2

Mobile Application for Elderly Care

引用

2nd International Conference on Artificial Intelligence and Smart Energy, ICAIS 2022

作者： Jose, Fernando Livaldo Mahardhika, Mozan Hafiz Sukiman, Nathanael Adolf Warnars, Harco Leslie Hendric Spits Ramadhan, Arief Utomo, Wiranto Herry Bina Nusantara University School of Information Systems Information Systems Department Jakarta11480 Indonesia Bina Nusantara Univerisity Binus Graduate Program Computer Science Computer Science Department Jakarta11480 Indonesia President University Faculty of Computing Department of Magister Science of Information Technology West Java17530 Indonesia

ISBN: (纸本)9781665400527

This paper discusses the design and implementation process of mobile applications used by nurses to communicate with the elderly or with people appointed to represent the elderly in using this mobile application. This mobile application is expected to help caregivers or nurses monitor the health condition of the elderly, and this mobile application has several functions that make it complete. These functions include submitting weekly reports, communicating with others via forums, and providing relevant information about the elderly and how to deal with them, including news and government regulations on elderly care. This mobile application uses case diagrams to describe business processes and class diagrams to illustrate database design. As for the implementation, android studio and MySQL database are used for database storage. This paper is limited to 9 references for literature review previous similar research by searching for publication titles with the sentences 'mobile application'+elderly+care using quotation marks and without quotation marks for the words elderly and care for all years of publication. © 2022 IEEE.

关键词： Mobile computing

来源：评论

学校读者我要写书评

暂无评论

Using compression tables to improve HiveQL Performance with Spark A Case study on NVMe Storage Devices

Using compression tables to improve HiveQL Performance with ...

引用

International computer science and Engineering Conference (ICSEC)

作者： Youppadee Intasorn Kritwara Rattanaopas Yanapat Chuchuen Computer Science Program Faculty of Science and Technology Songkhla Rajabhat University Songkhla Thailand Information Technology Program Faculty of Science and Technology Songkhla Rajabhat University Songkhla Thailand

ISBN: (纸本)9781665462730

Query language execution is widely used in big data. The SQL standard is the major query language. Big data has a lot of SQL-like tools, for example: Spark-SQL, Hive, Drill, and Presto. This paper focused on Hive with the Spark engine. To increase Hive’s query performance in a case study, NVMe Solid State Devices, we proposed the compressed Parquet file including SNAPPY, gzip, and Zstandard (zstd). Query workloads use TPC-H benchmark. Thus, this compression codec can reduce the main transaction table of TPC-H benchmark by 56%, and some queries have lower CPU usage than Text file. However, the Hive on Spark engine with our proposed compression codecs for Parquet files has lower CPU usage than Text file in some TPC-H queries. Thus, NVMe storage with the Parquet file compression codec is more efficient than text files for improving query performance on the Spark engine.

关键词： Performance evaluation Structured Query Language Codecs Solid state drives Big Data Benchmark testing Virtual machining

来源：评论

学校读者我要写书评

暂无评论

Based-on computer Vision Applications for Bus Stop Passenger Detection System

Based-on Computer Vision Applications for Bus Stop Passenger...

引用

Electronic Communications, Internet of Things and Big Data (ICEIB), International Conference on

作者： Yu-Cheng Chang Hua-Wen Tsai Chao-Yi Huang Zong-Rong Wu Department of Computer Information and Network Engineering Lunghwa University of Science and Technology Taiwan Department of Bachelor's Program in Intelligent Robot National Yunlin University of Science and Technology Taiwan Department of Technical and Vocational Program in Artificial Intelligence National Yunlin University of Science and Technology Taiwan

Passenger transport is one of the most common ways of commuting in Taiwan. It plays an important role in the transportation system due to its large number of stations, dense frequency, and cheap transportation. Due to the unfriendly transportation environment and a large number of passengers, a blind spot of passenger transportation exists, which leads to traffic accidents at the station. We research to make the "Bus Stop Passenger Detection System". Taking the object detection of "Wheelchairs" into consideration, it is more convenient to assist the disabled to find the passenger transportation system, which makes Taiwan's transportation system more convenient.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comments on a Computation-Transferable Authenticated Key Agreement Protocol for Smart Healthcare

Comments on a Computation-Transferable Authenticated Key Agr...

引用

International Conference on Applied System Innovation (ICASI)

作者： Ya-Fen Chang Chung-Yi Tsai Wei-Liang Tai Department of Computer Science and Information Engineering National Taichung University of Science and Technology Taichung Taiwan Bachelor Degree Program of Artificial Intelligence National Taichung University of Science and Technology Taichung Taiwan

Recently, Wang et al. proposed a computationally transferable authenticated key agreement protocol for smart healthcare by adopting the certificateless public-key cryptography. They claimed that their protocol could ensure privacy, resist various attacks, and possess superior properties. After analyzing their protocol, we find that it suffers from some flaws. Firstly, user privacy is not ensured as claimed. Secondly, some statements are inaccurate or missing. Thirdly, it cannot resist DoS attack. In this paper, the details of how these flaws threaten Wang et al.’s protocol are shown.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Physician Scheduling using Constraint Satisfaction programming

Physician Scheduling using Constraint Satisfaction Programmi...

引用

Electronics, Communications, and Computations (JAC-ECC), International Japan-Africa Conference on

作者： Hend A. Bakr Ahmed M. Salama Ahmed Fares Ahmed B. Zaky Biomedical Engineering Program Faculty of Engineering Cairo University Giza Egypt Computer Systems Engineering Program Faculty of Engineering at Shoubra Benha University Banha Egypt Computer science and information technology Programs Egypt-Japan University of Science and Technology (E-JUST) Alexandria Egypt On leave from Computer Systems Engineering Program Faculty of Engineering at Shoubra Benha University

Physician scheduling is a critical task that impacts the quality of patient care, staff satisfaction, and operational efficiency in healthcare institutions. The traditional approach to physician scheduling is manual and time-consuming, which can result in errors, staff burnout, and suboptimal schedules. To address these challenges, researchers have turned to optimization techniques like CSP, which has shown promise in solving physician scheduling problems. This paper reviews the existing literature on CSP for physician scheduling and highlights the benefits and limitations of this approach. CSP's benefits include generating schedules quickly and efficiently, incorporating complex constraints and preferences, and handling changes and disruptions in real time. However, CSP also has some limitations, such as the need for a formalized model and the fact that it may not always generate the most intuitive schedules. Overall, the findings suggest that CSP is a promising approach to physician scheduling that can produce high-quality schedules while minimizing staff burnout and improving operational efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Neural Networks for Brain Tumor Image Segmentation and Detection

Deep Neural Networks for Brain Tumor Image Segmentation and ...

引用

International Conference on Electrical Engineering, computer science and Informatics (EECSI)

作者： Ritesh Chandra Sadhana Tiwari Shashi Shekhar Kumar Sonali Agarwal M. Syafrullah Krisna Adiyarta Department of Information Technology Indian Institute of Information Technology Allahabad Prayagraj India Program of Master of Computer Science Universitas Budi Luhur Indonesia

Medical image analysis is a challenging and complex field these days. This discipline focuses especially on the processing of MRI (Magnetic Resonance Imaging) images. It offers multiple methods for locating brain tumors in MRI brain images and compares the precision of all the findings. Convolutional neural networks (CNN) and ResNet architectures are used to train the model. As deep learning models are highly efficient and correctly identify whether the MRI picture of a tumor is healthy or unhealthy. In this work, high-level features are extracted from the input images using the CNN architecture, which has multiple pooling layers. To create the final classification model, fully connected layers are then routed through the extracted characteristics. However, CNN has some drawbacks, and to overcome these issues, a ResNet based architecture has been used. Additionally, U-Net-based MRI brain tumor segmentation algorithms have gained popularity because they significantly improve segmentation accuracy by infusing high-level and low-level feature information via skip connections. The suitability of an attention module called Attention Gate, which was recently developed, for tasks involving the segmentation of brain tumors has also been explored in this work.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Efficient In-memory Computing Hardware for Quantized Neural Networks: State-of-the-art, Open Challenges and Perspectives

arXiv

引用

arXiv 2023年

作者： Krestinskaya, Olga Zhang, Li Salama, Khaled Nabil Electrical and Computer Engineering Program the Division of Computer Electrical and Mathematical Sciences and Engineering King Abdullah University of Science and Technology Thuwal23955 Saudi Arabia

The amount of data processed in the cloud, the development of Internet-of-Things (IoT) applications, and growing data privacy concerns force the transition from cloud-based to edge-based processing. Limited energy and computational resources on edge push the transition from traditional von Neumann architectures to In-memory Computing (IMC), especially for machine learning and neural network applications. Network compression techniques are applied to implement a neural network on limited hardware resources. Quantization is one of the most efficient network compression techniques allowing to reduce the memory footprint, latency, and energy consumption. This paper provides a comprehensive review of IMC-based Quantized Neural Networks (QNN) and links software-based quantization approaches to IMC hardware implementation. Moreover, open challenges, QNN design requirements, recommendations, and perspectives along with an IMC-based QNN hardware roadmap are provided. © 2023, CC BY.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Autism Spectrum Disorder Detection using Autistic Image Dataset

Autism Spectrum Disorder Detection using Autistic Image Data...

引用

International Conference on Electrical Engineering, computer science and Informatics (EECSI)

作者： Ritesh Chandra Sadhana Tiwari Ashutosh Kumar Sonali Agarwal M. Syafrullah Krisna Adiyarta Information Technology Department Indian Institute of Information Technology Allahabad Prayagraj India Program of Master of Computer Science Universitas Budi Luhur Indonesia

Autism spectrum disorders (ASD) are neurodevelopmental disorders that are marked by enduring difficulties with speech, nonverbal communication, and restricted or repetitive behaviors. Early detection and intervention can greatly improve outcomes for people with ASD. Recently, deep learning algorithms have been applied to aid in the early detection of ASD using facial images. In this work, modifications of the commonly used VGG16 and VGG19 models for image recognition tasks are proposed to improve the performance of detecting ASD from a child’s frontal face image. The proposed model is unique, as it alters the architecture of existing models, adds an attentional mechanism, and applys transfer learning. These changes are intended to decrease the chance of overfitting and enhance the model’s capacity to capture subtle face characteristics. The performance of the updated model is assessed through accuracy, which is 82.55% for VGG19 and 80% for VGG16 model, and contrasted the outcomes of the original model. Performance of the modified model is also compared with that of the original model. The obtained results show that the modified model outperforms in detecting ASD from facial images, suggesting that the proposed modification is non-invasive for early detection of ASD and has the potential to contribute to the development of efficient tools.

关键词：

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：