检索结果-内蒙古大学图书馆

3rd International Conference on Computing and Communication Networks, ICCCN 2023

作者： Ajha, Oindrila Das, Souryadipta Dutta, Tiyasha Das, Soham Mishra, Sushruta Abualigah, Laith Kalinga Institute of Industrial Technology Deemed to Be University Bhubaneswar India Computer Science Department Al al-Bayt University Mafraq25113 Jordan MEU Research Unit Middle East University Amman11831 Jordan Applied Science Research Center Applied Science Private University Amman11931 Jordan Jadara Research Center Jadara University Irbid21110 Jordan

ISBN: (纸本)9789819708918

Stock analysis is a method used by traders and financial experts to evaluate the securities market and make informed decisions about buying and selling shares. It involves conducting extensive research to assess the performance and quality of a stock or an industry before investing. Stock analysis can take different forms, but traders usually use two main categories: technical and fundamental analysis. Technical analysis involves examining documented value outlines and researching previous market structures to predict future advances. On the other hand, fundamental analysis looks at data from the organization and its macroeconomic situation, such as financial history and revenue streams, to assess prospective gains from exchanges. The ultimate goal of stock analysis is to choose the best times to place trades and make the appropriate buying and selling decisions. Traders may specialize in one type of analysis or use a combination of both. Regardless of the approach, conducting extensive research is crucial to ensure wise investments that produce profit and avoid wasting hard-earned money. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Investments

来源：评论

学校读者我要写书评

暂无评论

An Architecture Approach to a Secure Home Area Network

An Architecture Approach to a Secure Home Area Network

引用

2022 IEEE International Conference on Electrical, computer, and Energy Technologies, ICECET 2022

作者： Nshimba, Kt Goede, Roelien Process Control and Computer Systems Vaal Univerisity of Technology Vanderbijlpark South Africa North-West University Unit for Data Science and Computing Potchefstroom South Africa

ISBN: (数字)9781665470872

ISBN: (纸本)9781665470872

Appliances in home networks come in various types and models. Homes are fitted with smart televisions, fridges, speakers and even smart locks. All these interact in a smart home area network and many store data in the cloud. The security risks of these devices include all risks involved with the collection of the data, the transmission of the data and the cloud storage of the data. Unauthorised user access may lead to disastrous consequences for the home owner. Home owners are not aware of the risks posed by the technical specifications of their latest appliance. When these seemingly different devices are investigated from a theoretical computer science architecture perspective, they share a layered architectural design, comprising of a perception layer, network layer, support layer and an application layer. This paper explores the security risks and threats from this architectural perspective. The theoretical investigation is supported by an empirical investigation of manufacture release documents and product reviewer documents using data from document and content analysis. The findings of the paper show how the network architecture design of the device along with specific design decisions of manufacturers impact the security risk of the device for the home owner. © 2022 IEEE.

关键词： Home networks

来源：评论

学校读者我要写书评

暂无评论

A Framework for Tile Processing on Edge Servers for Roadside Traffic Surveillance 23

A Framework for Tile Processing on Edge Servers for Roadside...

引用

Proceedings of the 7th International Conference on Algorithms, Computing and Systems

作者： Saumya Jaipuria Arani Bhattacharya Ansuman Banerjee Advanced Computing and Microelectronics Unit Indian Statistical Institute India Department of Computer Science Indraprastha Institute of Information Technology India

ISBN: (纸本)9798400709098

Roadside traffic monitoring is increasingly performed by deploying roadside high-resolution video cameras and then running computer Vision (CV) models on the video data. Since computer vision models are compute-intensive as they utilize Deep Neural Networks (DNNs), the data is usually sent to one or more edge servers located adjacent to mobile base stations. Recent techniques propose running CV models on tiles of videos separately to detect and track small objects. Several CV models exist, each with different requirements of compute and memory. Since more compute and memory-intensive CV models provide higher accuracy, a key challenge of such techniques is to determine which vision model should be used on which tile. This becomes even more challenging if multiple videos are processed by the same edge server. In this paper, we first formulate this problem of model selection on edge devices as an Integer Linear Programming (ILP) problem, and then propose a heuristic to solve it. Our experiments show that it is quite effective in practice.

关键词： computer Vision Edge Computing Integer Linear Programming

来源：评论

学校读者我要写书评

暂无评论

SelfHAR: Improving Human Activity Recognition through Self-training with Unlabeled Data

引用

Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 2021年第1期5卷 1-30页

作者： Tang, Chi Ian Perez-Pozuelo, Ignacio Spathis, Dimitris Brage, Soren Wareham, Nick Mascolo, Cecilia Department of Computer Science and Technology University of Cambridge Cambridge United Kingdom Alan Turing Institute London United Kingdom Department of Computer Science and Technology University of Cambridge Cambridge United Kingdom Mrc Epidemiology Unit School of Clinical Medicine University of Cambridge Cambridge United Kingdom

Machine learning and deep learning have shown great promise in mobile sensing applications, including Human Activity Recognition. However, the performance of such models in real-world settings largely depends on the availability of large datasets that captures diverse behaviors. Recently, studies in computer vision and natural language processing have shown that leveraging massive amounts of unlabeled data enables performance on par with state-of-the-art supervised models. In this work, we present SelfHAR, a semi-supervised model that effectively learns to leverage unlabeled mobile sensing datasets to complement small labeled datasets. Our approach combines teacher-student self-training, which distills the knowledge of unlabeled and labeled datasets while allowing for data augmentation, and multi-task self-supervision, which learns robust signal-level representations by predicting distorted versions of the input. We evaluated SelfHAR on various HAR datasets and showed state-of-the-art performance over supervised and previous semi-supervised approaches, with up to 12% increase in F1 score using the same number of model parameters at inference. Furthermore, SelfHAR is data-efficient, reaching similar performance using up to 10 times less labeled data compared to supervised approaches. Our work not only achieves state-of-the-art performance in a diverse set of HAR datasets, but also sheds light on how pre-training tasks may affect downstream performance. © 2021 Owner/Author.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Restoration of Dunhuang Murals on Large-scale pretraining 23

Restoration of Dunhuang Murals on Large-scale pretraining

引用

6th International Conference on Signal Processing and Machine Learning, SPML 2023

作者： Xu, Zishan Yao, Minda Chen, Wei Zhu, Min Tian, Zijian Zhang, Fan Zhang, Xiaofeng Zhang, Chuanlei China University of Mining and Technology China School of Computer Science & Technology China University of Mining and Technology Xuzhou221116 China Beijing100083 China Key Laboratory of Intelligent Mining and Robotics Ministry of Emergency Management China Department of Intensive Care Unit Xuzhou First People's Hospital Jiangsu221000 China China Shanghai Jiaotong University China Tianjin University of Science and Technology China

ISBN: (纸本)9798400707575

Dunhuang murals are a precious cultural heritage and their restoration is of vital importance. Traditional image restoration methods and methods based on generative adversarial networks (GANs) have limitations in the mural restoration task. In this paper, we propose a diffusion model-based method for restoring Dunhuang murals using the RePaint model for image restoration. We first collected and produced 5135 Dunhuang mural image data that had undergone data augmentation methods such as cropping and panning, and then pre-trained the RePaint model on a large public dataset and fine-tunedthe model on the Dunhuang mural data. The experimental results show that the fine-tuned RePaint model has significantly improved the evaluation metrics such as PSNR and SSIM in the Dunhuang mural restoration task compared to other recent excellent image restoration models. This suggests that the RePaint model has superior performance in mural restoration tasks, especially in the areas of texture generation and structure retention. This study provides a novel and effective method for the field of Dunhuang mural restoration, which is expected to provide more support for heritage conservation. © 2023 ACM.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Using Hybrid Genetic Algorithm for Data Aggregation in Wireless Sensor Networks

Using Hybrid Genetic Algorithm for Data Aggregation in Wirel...

引用

International Conference on Ubiquitous Information Management and Communication (IMCOM)

作者： Sharmin Sharmin Ismail Ahmedy Rafidah Md Noor Habibah Ismail Department of Computer System and Technology Universiti Malaya Kuala Lumpur Malaysia Computer Science Unit Centre of Foundation Studies Universiti Teknologi MARA Dengkil Selangor Malaysia

Efficient energy usage is vital for extending Wireless Sensor Networks (WSNs) lifespan. While Improved LowEnergy Adaptive Clustering Hierarchy (ILEACH) excels in energy-efficient data aggregation, challenges like premature cluster head $({\text{CH}})$ failure remain. Genetic Algorithm (GA) optimizes parameters, including energy, in WSNs. We propose a novel hybrid ILEACH-GA algorithm for data aggregation. ILEACH forms clusters, GA evaluates fitness, selecting optimal clusters for aggregation. GA mitigates ILEACH's premature CH failure. ILEACH-GA surpasses LEACH, ILEACH, and GA-LEACH, with significantly higher throughput $(10.0\%$ , $47.4{{\% }},21.9{{\% }}$ respectively), retaining higher residual energy (0.0805) and alive nodes $({25.5{{\% }}})$ . This innovation boosts sustainable WSN data aggregation, overcoming limitations, and enhancing performance. This innovation elevates sustainable WSN data aggregation, surmounting limitations, and augmenting performance, applicable in waste and crop management systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Machine Learning Algorithms for Email Phishing Detection Using TF-IDF, Word2Vec, and BERT

引用

computers, Materials & Continua 2024年第11期81卷 3395-3412页

作者： Arar Al Tawil Laiali Almazaydeh Doaa Qawasmeh Baraah Qawasmeh Mohammad Alshinwan Khaled Elleithy Faculty of Information Technology Applied Science Private UniversityAmman11931Jordan College of Engineering Abu Dhabi UniversityAbu DhabiAl AinP.O.Box 1790United Arab Emirates Faculty of Artificial Intelligence Al-Balqa Applied UniversitySalt19117Jordan Department of Civil and Construction Engineering Western Michigan UniversityKalamazooMI 49008USA MEU Research Unit Middle East UniversityAmman11831Jordan Department of Computer Science and Engineering University of BridgeportBridgeportCT 06604USA

Cybercriminals often use fraudulent emails and fictitious email accounts to deceive individuals into disclosing confidential information,a practice known as *** study utilizes three distinct methodologies,Term Frequency-Inverse Document Frequency,Word2Vec,and Bidirectional Encoder Representations from Transform-ers,to evaluate the effectiveness of various machine learning algorithms in detecting phishing *** study uses feature extraction methods to assess the performance of Logistic Regression,Decision Tree,Random Forest,and Multilayer Perceptron *** best results for each classifier using Term Frequency-Inverse Document Frequency were Multilayer Perceptron(Precision:0.98,Recall:0.98,F1-score:0.98,Accuracy:0.98).Word2Vec’s best results were Multilayer Perceptron(Precision:0.98,Recall:0.98,F1-score:0.98,Accuracy:0.98).The highest performance was achieved using the Bidirectional Encoder Representations from the Transformers model,with Precision,Recall,F1-score,and Accuracy all reaching *** study highlights how advanced pre-trained models,such as Bidirectional Encoder Representations from Transformers,can significantly enhance the accuracy and reliability of fraud detection systems.

关键词： Attacks email phishing machine learning security representations from transformers(BERT) text classifeir natural language processing(NLP)

来源：评论

学校读者我要写书评

暂无评论

GIS data support technique for forest fire management and decision support system: A Sebangau National Park, Kalimantan case 6

GIS data support technique for forest fire management and de...

引用

6th International Conference on Information and Communications technology, ICOIACT 2023

作者： Yuana, Kumara Ari Kusrini, Kusrini Setyanto, Arief Laksito, Arif Dwi Maruf, Zauvik Rizaldi Johari, Muhammad Zuhdi Fikri Adninda, Gardyas Bidari Kartikakirana, Renindya Azizza Nucifera, Fitria Widayani, Wiwi Orphanoudakis, Theofanis Universitas Amikom Yogyakarta Faculty of Computer Science Yogyakarta Indonesia Universitas Amikom Yogyakarta Magister of Informatic Engineering Yogyakarta Indonesia Universitas Amikom Yogyakarta Faculty of Science and Technology Yogyakarta Indonesia Netcompany-Intrasoft A. Research & Innovation Development Unit L1253 Luxembourg

ISBN: (纸本)9798350315639

Numerous science and engineering fields are involved when handling forest fire disasters. Social sciences contribute to analyze the human behavior behind the forest fire phenomena, while science and engineering principles can be applied to investigate the physical and environment variables involved. The use of a Geographic Information System (GIS) as a computer system that manages the comprehensive variables influence on the forest fire is proposed is proposed. Capturing, processing and displaying the data generating valuable information related to specific locations is possible through satellite and computer utilities, which turn into powerful assistants for forest fire management with the aid of a decision support system. Data fusion from different sources with different formats and the relevant processing requirements with a large variety of complexities are the challenges that are addressed in the present work. Our proposed method results in a specific informative map with specific characteristics of variables of the forest. These maps are very useful for mitigating forest fire disaster as well as for making informed decisions about optimal resources allocation. © 2023 IEEE.

关键词： Data acquisition

来源：评论

学校读者我要写书评

暂无评论

STRIDERNET: A Graph Reinforcement Learning Approach to Optimize Atomic Structures on Rough Energy Landscapes 40

STRIDERNET: A Graph Reinforcement Learning Approach to Optim...

引用

40th International Conference on Machine Learning, ICML 2023

作者： Bihani, Vaibhav Manchanda, Sahil Sastry, Srikanth Ranu, Sayan Anoop Krishnan, N.M. Department of Civil Engineering Indian Institute of Technology Delhi India Department of Computer Science and Engineering Indian Institute of Technology Delhi India Yardi School of AI Indian Institute of Technology Delhi India Theoretical Sciences Unit School of Advanced Materials Jawaharlal Nehru Centre for Advanced Scientific Research Bengaluru India

Optimization of atomic structures presents a challenging problem, due to their highly rough and non-convex energy landscape, with wide applications in the fields of drug design, materials discovery, and mechanics. Here, we present a graph reinforcement learning approach, STRIDERNET, that learns a policy to displace the atoms towards low energy configurations. We evaluate the performance of STRIDERNET on three complex atomic systems, namely, binary Lennard-Jones particles, calcium silicate hydrates gel, and disordered silicon. We show that STRIDERNET outperforms all classical optimization algorithms and enables the discovery of a lower energy minimum. In addition, STRIDERNET exhibits a higher rate of reaching minima with energies, as confirmed by the average over multiple realizations. Finally, we show that STRIDERNET exhibits inductivity to unseen system sizes that are an order of magnitude different from the training system. All the codes and datasets are available at https://***/M3RG-IITD/StriderNET. © 2023 Proceedings of Machine Learning Research. All rights reserved.

关键词： Silicates

来源：评论

学校读者我要写书评

暂无评论

Correction to: A hybrid model for lung cancer prediction using patch processing and deeplearning on CT images

引用

Multimedia Tools and Applications 2024年第15期83卷 43953-43954页

作者： Venkatesh, C. Chinna Babu, J. Kiran, Ajmeera Nagaraju, C. H. Kumar, Manoj Department of Electronics and Communication Engineering Annamacharya Institute of Technology and Sciences Rajampet India Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India School of Computer Science University of Wollongong in Dubai Dubai United Arab Emirates MEU Research Unit Middle East University Amman Jordan

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：