检索结果-内蒙古大学图书馆

25th International Seminar on Intelligent Technology and Its Applications, ISITIA 2024

作者： Satwika, I Putu Suciati, Nanik Yuniarti, Anny Suwardhi, Deni Department of Informatics Surabaya Indonesia Spatial System and Cadastral Research Group Faculty of Earth Science and Engineering Bandung Indonesia

ISBN: (纸本)9798350378573

The improvement of cadastral systems has become a major problem in Indonesia. Despite continuous efforts to digitize land cadastral maps, persistent difficulties such as gaps and overlaps remain in the cadastral data. This study utilizes the least squares adjustment method to improve the quality of land cadastral maps in Indonesia and address these difficulties. This method is preferred because of its ability to maintain the integrity of polygon forms and parcel areas, which are essential characteristics of cadastral mapping. In addition, the implementation seeks to provide visual indicators of the accuracy of adjustments, such as error ellipses and changes in parcel sizes. While errors in the vertex transformations within segments cause some gaps and overlaps to persist, these problems are addressed by post-processing approaches. The results indicate that this method can enhance the quality of land cadastral maps in Indonesia. © 2024 IEEE.

关键词： boundary alignment land parcel least squares adjustment parcel adjustment

来源：评论

学校读者我要写书评

暂无评论

Decomposition-Based Memetic Algorithm for Multi-Objective Fleet Size and Mix Vehicle Routing Problem 13

Decomposition-Based Memetic Algorithm for Multi-Objective Fl...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Ba, Yunpeng Zheng, Ruihao Wang, Zhenkun School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China School of System Design and Intelligent Manufacturing Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen China

ISBN: (纸本)9798350308365

The heterogeneous fleet vehicle routing problem (HFVRP) is of great significance in logistics and transportation. This paper considers a crucial and challenging HFVRP variant, namely multi-objective fleet size and mix vehicle routing problem with unlimited fleet, fixed cost, and dependent cost (MO-FSMVRPFD). A decomposition-based memetic algorithm called MOEA/D-ALS is proposed to cope with MO-FSMVRPFD. MOEA/D-ALS uses the multi-objective evolutionary algorithm based on decomposition (MOEA/D) as the backbone. Beyond that, it adopts a replacement strategy based on maximal fitness improvement (MFI). In addition, the local search is conducted on difficult subproblems for further refinement. The experimental studies on 18 instances show that MOEA/D-ALS exhibits a significant performance superiority over two other representative algorithms. The effectiveness of both the MFI strategy and the adaptive local search procedure is also validated. © 2024 IEEE.

关键词： Vehicle routing

来源：评论

学校读者我要写书评

暂无评论

Discrete Incremental Voting 27

Discrete Incremental Voting

引用

27th International Conference on Principles of Distributed systems, OPODIS 2023

作者： Cooper, Colin Radzik, Tomasz Shiraga, Takeharu Department of Informatics King’s College University of London United Kingdom Department of Information and System Engineering Faculty of Science and Engineering Chuo University Tokyo Japan

ISBN: (纸本)9783959773089

We consider a type of pull voting suitable for discrete numeric opinions which can be compared on a linear scale, for example, 1 ("disagree strongly"), 2 ("disagree"), . . ., 5 ("agree strongly"). On observing the opinion of a random neighbour, a vertex changes its opinion incrementally towards the value of the neighbour’s opinion, if different. For opinions drawn from a set {1, 2, . . ., k}, the opinion of the vertex would change by +1 if the opinion of the neighbour is larger, or by −1, if it is smaller. It is not clear how to predict the outcome of this process, but we observe that the total weight of the system, that is, the sum of the individual opinions of all vertices, is a martingale. This allows us analyse the outcome of the process on some classes of dense expanders such as complete graphs Kn and random graphs Gn,p for suitably large p. If the average of the original opinions satisfies i ≤ c ≤ i + 1 for some integer i, then the asymptotic probability that opinion i wins is i + 1 − c, and the probability that opinion i + 1 wins is c − i. With high probability, the winning opinion cannot be other than i or i + 1. To contrast this, we show that for a path and opinions 0, 1, 2 arranged initially in non-decreasing order along the path, the outcome is very different. Any of the opinions can win with constant probability, provided that each of the two extreme opinions 0 and 2 is initially supported by a constant fraction of vertices. © Colin Cooper, Tomasz Radzik, and Takeharu Shiraga

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Leveraging Transfer Learning for Spatio-Temporal Human Activity Recognition from Video Sequences

引用

computers, Materials & Continua 2023年第3期74卷 5017-5033页

作者： Umair Muneer Butt Hadiqa Aman Ullah Sukumar Letchmunan Iqra Tariq Fadratul Hafinaz Hassan Tieng Wei Koh School of Computer Sciences Universiti Sains MalaysiaPenang1180Malaysia Department of Computer Science The University of ChenabGujrat50700Pakistan Department of Software Engineering and Information System Universiti Putra MalaysiaSelangor43400Malaysia

Human Activity Recognition(HAR)is an active research area due to its applications in pervasive computing,human-computer interaction,artificial intelligence,health care,and social ***,dynamic environments and anthropometric differences between individuals make it harder to recognize *** study focused on human activity in video sequences acquired with an RGB camera because of its vast range of real-world *** uses two-stream ConvNet to extract spatial and temporal information and proposes a fine-tuned deep neural ***,the transfer learning paradigm is adopted to extract varied and fixed frames while reusing object identification *** state-of-the-art pre-trained models are exploited to find the best model for spatial feature *** temporal sequence,this study uses dense optical flow following the two-stream ConvNet and Bidirectional Long Short TermMemory(BiLSTM)to capture *** state-of-the-art datasets,UCF101 and HMDB51,are used for evaluation *** addition,seven state-of-the-art optimizers are used to fine-tune the proposed network ***,this study utilizes an ensemble mechanism to aggregate spatial-temporal features using a four-stream Convolutional Neural Network(CNN),where two streams use RGB *** contrast,the other uses optical flow ***,the proposed ensemble approach using max hard voting outperforms state-ofthe-art methods with 96.30%and 90.07%accuracies on the UCF101 and HMDB51 datasets.

关键词： Human activity recognition deep learning transfer learning neural network ensemble learning spatio-temporal

来源：评论

学校读者我要写书评

暂无评论

Edge-Computing-Enabled Deep Learning Approach for Low-Light Satellite Image Enhancement

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2024年 17卷 4071-4083页

作者： Bui, Trong-An Lee, Pei-Jun Liang, Chun-Sheng Hsu, Pei-Hsiang Shiu, Shiuan-Hal Tsai, Chen-Kai National Taiwan University of Science and Technology Department of Electronic and Computer Engineering Taipei10607 Taiwan Liscotech System Company Ltd. Department of Research and Development Taipei100213 Taiwan

Edge computing enables rapid data processing and decision-making on satellite payloads. Deploying deep learning-based techniques for low-light image enhancement improves early detection and tracking accuracy on satellite platforms, but it faces challenges due to limited computational resources. This article proposes an edge-computing-enabled inference model specifically designed onboard satellites. The proposed model follows an encoder-decoder architecture to generate the illumination map with low multiplication matrix complexity, 25.52 GMac of $1920 \times 1200$ image size. To reduce nanosatellite hardware consumption with a single-precision floating-point format, the edge-computing-enabled inference model proposes a quantized convolution that computes signed values. The proposed inference model is deployed on Arm Cortex-M3 microcontrollers onboard satellite payload (86.74 times faster than normal convolution model) but also has a similar quality with the low-light enhanced in full-precision computing of lightweight training model by using the peak signal-to-noise ratio (average of 28.94) and structural similarity index (average of 0.85) metrics. © 2008-2012 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

KENKO - an AI system to hold health records and assist individuals across cross domains 6

KENKO - an AI system to hold health records and assist indiv...

引用

6th International Conference on Recent Trends in Advance Computing, ICRTAC 2023

作者： Ignisha Rajathi, G. Sneharajalakshmi, P. Midhun Kumar, V.N. Vikash Kumar, S. Sri Krishna College of Engineering and Technology Department of Computer Science and Business System Coimbatore India

ISBN: (纸本)9798350394702

According to HCPro, an unfinished medical record signifies that the provided care was not comprehensive, showing gaps that indicate subpar clinical care and a failure to adhere to organizational policies. In addition, such incomplete records can be utilized as evidence to substantiate claims of negligence and allegations of fraudulent practices. In the fast-growing world of technology and great development of health sciences, we as common people have no independence to our health history. Imagine using regular insulin without realizing it might lead to heart complications due to sudden blood sugar spikes. Consider a scenario where you're involved in an accident, and the ER doctors are unaware of your penicillin allergy because your medical history is inaccessible. Picture a situation where your dermatologist prescribes new medications, but you're unaware of the potential risk of developing skin cancer. Envision the possibility of receiving urgent painkillers, only to discover that the dosage is actually excessive for your body. This is precisely where Kenkō steps in as a comprehensive solution for all your medical assistance requirements. © 2023 IEEE.

关键词： Image processing

来源：评论

学校读者我要写书评

暂无评论

Model-Based Optimization of Vaccination Strategies in Different Phases of Pandemic Virus Spread 18th

Model-Based Optimization of Vaccination Strategies in Diff...

引用

18th International Conference on Informatics in Control, Automation and Robotics, ICINCO 2021

作者： Liu, Zonglin Omayrat, Muhammed Stursberg, Olaf Control and System Theory Department of Electrical Engineering and Computer Science University of Kassel Kassel Germany

ISBN: (纸本)9783031264733

This paper aims at applying optimal control principles to investigate optimal vaccination strategies in different phases of a pandemic. Background of the study is that many countries have started their vaccination procedures against the COVID-19 disease in the beginning of 2021, but supply shortages for the vaccines prevented that everyone could be vaccinated immediately. At the beginning of 2022, in contrast, the vaccine supply was ample, but the effectiveness of different existing vaccines to avoid infection by new virus variants was in doubt, as well as the acceptance of booster doses decreased over time. To account for these effects, two formulations of optimization tasks based on different epidemic models are proposed in this paper. The solution of these tasks determines optimal distribution strategies for available vaccines, and optimized vaccination schemes to reduce the need of booster doses for later phase. Effectiveness of these strategies compared with other popular strategies (as applied in practice) is demonstrated through a series of simulations © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Vaccines

来源：评论

学校读者我要写书评

暂无评论

Keyphrase Extraction Using Pre-Trained Language Models BERT and Topic-Guided Graph Attention Networks 7

Keyphrase Extraction Using Pre-Trained Language Models BERT ...

引用

7th International Conference on Data science and Its Applications, ICoDSA 2024

作者： Yusliani, Novi Nurmaini, Siti Firdaus, Firdaus Nabilah, Aini Darmawahyuni, Annisa Abdiansah, Abdiansah Universitas Sriwijaya Faculty Engineering South Sumatera Palembang Indonesia Universitas Sriwijaya Informatic Engineering Faculty of Computer Science South Sumatera Palembang Indonesia Universitas Sriwijaya Intelligent System Research Group Faculty of Computer Science South Sumatera Palembang Indonesia

ISBN: (纸本)9798350365351

Keyphrase extraction aims to extract a set of keyphrases from the input document that highly summarizes the document. One of the issue in keyphrase extraction is how to extract representative keyphrases that is relevance and describe the information in the document. This study addresses pretrained language model (PLM) and topic-guided graph attention network (TgGAT) to extract a set of keyphrases from the input document. PLM can effectively capture knowledge from massive data and well perform on both language understanding and language generation tasks. BERT is one of PLM that designed to process bidirectionally, allowing BERT to understand word context based on the surrounding words. To enhance the keyphrase relevance, latent-dirichlet allocation used to learn the latent topic information and aiding the semantic understanding of the input document. For capturing semantic relationships between phrases in document based on their topics, this study used TgGAT. TgGAT models the anchoraware graph which organizes the initial anchor phrases. Experiment was conducted on a dataset containing 100 Indonesian accredited scientific article, Sinta 2 and Sinta 3, to evaluate the system' $s$ performance. The experimental results show a precision value of 0.058, a recall value of 0.070, and an F1-score of 0.062 for the five generated keywords across the entire tested dataset. Further in-depth analyses shows that pattern of phrases used has the important role in determining the representative phrases in input document. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

SHOPSPHERE - Recommendation system to develop a warehouse with personalized troupe of products 6

SHOPSPHERE - Recommendation system to develop a warehouse wi...

引用

6th International Conference on Recent Trends in Advance Computing, ICRTAC 2023

作者： Ignisha Rajathi, G. Prakalya, B.S. Nitin Sailesh, V. Sanchana, M. Anbu Gandhi, P. Sri Krishna College of Engineering and Technology Department of Computer Science and Business System Coimbatore India

ISBN: (纸本)9798350394702

With the rapidly increasing technology and globalization, the internet has become an inevitable part of one's day-to-day life. The use of a sophisticated recommendation system has revolutionized the way consumers interact with online shopping platforms. To keep in pace with the emerging technology, every field needs to be digitalized and made up to date. In this context, the commercial shops and dealers too need to upgrade their traditional shopping methods. The old conventional methods don't always serve the new generation. The transition to online mode of shopping has made it mandatory for retailers and producers to customize according to the customer's requirement and providing various options than what was possible before. The focus in this system is to increase customer engagement, enhance the customer shopping experience, and boost sales by suggesting relevant products based on a user's browsing and purchase history, these products that are most likely to interest and satisfy individual customers. This paper reviews recent developments in recommendation systems in the domain of ecommerce. © 2023 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Sentirec - A Sentiment Analysis with Recommendation system 8

Sentirec - A Sentiment Analysis with Recommendation System

引用

8th International Conference on Communication and Electronics systems, ICCES 2023

作者： Oswalt Manoj, S. Catherine Chandralekha, T. Dharshini, R.M. Hemadharsini, P. Sri Krishna College of Engineering and Technology Department of Computer Science and Business System Coimbatore India Sri Krishna College of Engineering and Technology Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350396638

The standard language is assessed, and the feelings transmitted by the individual are brought up. The purpose of sentiment analysis is to determine the polarity of a person's textual opinion. Most of the people use social media to market ourselves and share all knowledge, thoughts, ideas, and experiences with the rest of the world. Sentiment analysis has been studied by several internet companies that offer materials based on human emotions expressed through social media. Many people use social media to post and share their thoughts and feelings. The sentiment analysis standard assorts a sentence with all forms of emotions, each of which has an intensity. This study includes a sentiment analysis of diverse perspectives on social topics that are trending on social media, along with a recommendation system. This method recommends related content to viewers based on their current statement or issue. The algorithm also suggests customized video sets to users based on their social media activity, such as diverse perspectives on a particular social problem about which they actively express their thoughts on social media. NLP algorithms are utilized for sentiment analysis and recommendation systems. © 2023 IEEE.

关键词： Recommender systems

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：