检索结果-内蒙古大学图书馆

Asia-Pacific Conference on Communications

作者： Sebastian Luis S. Ortiz Justin Gabriel R. Enriquez Wilson M. Tan Cedric Angelo M. Festin Department of Computer Science Networks and Distributed Systems Laboratory University of the Philippines - Diliman Metro Manila Philippines

ISBN: (数字)9798331517816

ISBN: (纸本)9798331517823

Reliable internet access is a key enabler for economic growth. Although the Philippine government launched initiatives to improve connectivity, connection speeds remained below the global average, especially for mobile networks. This paper presents Hotspotter, a system that aims to aid implementers and stakeholders in quantifying and addressing network coverage issues. Hotspotter is an incentivized crowdsensing system that collects, maps, and visualizes WiFi and cellular data to pinpoint hotspots and dead zones for the effective deployment and relocation of WiFi access points. A mobile application for Android was developed to facilitate data collection on geolocation, nearby WiFi access points, and connected cellular networks. The user interface visualizes the aggregated data in a hexagon-grid map. Fieldwork was conducted in two sitios of Barangay San Lorenzo, Norzagaray, Bulacan to stress-test the Hotspotter system in a Geographically Isolated and Disadvantaged Area (GIDA). It was found that 2G and 4G had the widest coverage and strongest signals overall, with modal signal strengths of 4.0 and 3.0, respectively. Being at the cutting edge, 5G was not yet supported. In the end, the mobile application’s passive sensing, collecting, and caching of data successfully operated even in the most isolated areas without an internet connection.

关键词： Cellular networks Crowdsensing Geology Government Data visualization Sensors Mobile applications Stakeholders Reliability Wireless fidelity

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Static Analysis and Machine Learning Approaches for Detecting Android Banking Malware

Comparative Study of Static Analysis and Machine Learning Ap...

引用

Emerging Smart Technologies and Applications (eSmarTA), International Conference on

作者： Alaa M. Ahmed Mogeeb A. Saeed Amr A. Hamood Abduljabar A. Alazab Kamel A. Ahmed Faculty of Engineering Computer Networks & Distributed Systems Al-saeed IT Taiz University Taiz Yemen Computer Networks & Distributed Systems department Al-saeed Faculty of Engineering & IT Taiz University Taiz Yemen

Android currently dominates the smartphone market, accounting for an impressive market share of over 70%. However, because of its widespread acceptance, mobile operating systems have become a prime target for bad actors looking to profit from them. Particularly Android has been subjected to an increasing barrage of malware assaults, including the infamous Android Banking Trojans. This study investigates the effectiveness of static analysis in locating Android banking malware in order to counter this threat. It does so by utilizing a wide range of features, including permissions, application programming interface (API) calls, opcodes, API packages, system commands, intents, strings, services, receivers, and activities. The study suggests using machine learning techniques to assess the detection of Android malware by utilizing various sets of classifiers in order to achieve this goal. The study also uses a feature selection approach to determine which features are most useful for telling malicious code apart from good code. 500 samples of malicious code and 500 samples of benign code make up the dataset that was used. The XGboost algorithm outperforms others in terms of accuracy, achieving an impressive accuracy value of 99.5% in malware detection after conducting a thorough comparison of various classifier sets. These results demonstrate the potential of static analysis and machine learning as useful tools in fending off the growing threats posed by Android malware.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predicting fall in elderly people using machine learning

Predicting fall in elderly people using machine learning

引用

2021 International Congress of Advanced Technology and Engineering, ICOTEN 2021

作者： Saeed, Mogeeb A. Hashem Almourish, Mohammed Alqady, Yasmeen Ali Alsharabi, Hanadi Alkhorasani, Haleema Alsorori, Samah Saeed, Ahmed Y. A. Taiz University Faculty of Engineering and It Department of Computer Networks and Distributed Systems Taiz Yemen

ISBN: (纸本)9781665412247

Fall is a serious health problem, it may threaten the life of many people in general and the life of the elderly in particular. That is why we tried very hard to develop a system to notify the mechanisms of their fall from the lane by monitoring their movement by means of wearable sensors in certain places on their bodies. This paper presents five supervised machine learning algorithms (SVM, Neural Network, Decision Tree, Random Forest, and Naïve Bayes) to predict fifteen falls in the elderly. We compared the five models in terms of performance measures (accuracy, precision and recall), and the Random Forest model achieved the best result with an accuracy of 95.91%. In the future, we plan to improve the results by pre-processing the data for better features and then classifying and predicting them using advanced algorithms in artificial intelligence techniques to build a system that will be able to predict with high speed and accuracy. © 2021 IEEE.

关键词： Wearable technology

来源：评论

学校读者我要写书评

暂无评论

An Efficient Multi-band Infrared Small Objects Detection Approach for Low-Altitude Artificial Intelligence of Thing

引用

IEEE Internet of Things Journal 2025年第12期12卷 20757-20772页

作者： Peng, Yuhuai Wang, Jing Wang, Wenqian Liu, Lei Atiquzzaman, Mohammed Guizani, Mohsen Dustdar, Schahram Northeastern University School of Computer Science and Engineering Shenyang110819 China Zhiyuan Research Institute Hangzhou310024 China Northeastern University School of Computer Science and Engineering Shenyang110819 China Xidian University State Key Laboratory of Integrated Service Networks Xi'an710071 China University of Oklahoma School of Computer Science NormanOK73019 United States Mohamed Bin Zayed University of Artificial Intelligence Department of Machine Learning Masdar United Arab Emirates Technische Universität Wien Distributed Systems Group Vienna1040 Austria

As a cutting-edge technology of low-altitude Artificial Intelligence of Thing (AIoT), UAV object detection significantly enhances the surveillance services capabilities of low-altitude AIoT. However, the difficulty of object detection is exacerbated by the high proportion of small and obscure objects in the captured images. To address the mentioned challenges, we present an efficient multi-band infrared small object detection approach for low-altitude intelligent surveillance services. Firstly, we propose the Multi-band infrared Image Fusion algorithm based on Cascade-GAN (MIF-CGAN), which produces fused images with high information entropy and high contrast. Then, the Transformer-based Multi-scale Dense Small Object Detection (MsDSOD) algorithm is proposed. The algorithm consists of the Global-Local Object Detection (G-LOD) network, the Object Dense Area Extraction (O-DAE) module, and the Weighted Boxes Fusion (WBF) module. It extracts small objects features at different scales from infrared images and fuses the global and local detection results to accurately identify small objects in dense scenes. Furthermore, compared to the traditional algorithms, the mean Average Precision (mAP) of MsDSOD is improved by 0.80% and the Average Precision in small object detection (APs) is improved by 0.72%. The proposed algorithm is optimally suited to deal with complex scenes with dense small objects and background occlusion. © 2014 IEEE.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

distributed AI in Zero-touch Provisioning for Edge networks: Challenges and Research Directions

arXiv

引用

arXiv 2023年

作者： Hazra, Abhishek Morichetta, Andrea Murturi, Ilir Lovén, Lauri Dehury, Chinmaya Kumar Pujol, Víctor Casamayor Donta, Praveen Kumar Dustdar, Schahram Department of Computer Science and Engineering the Indian Institute of Information Technology Sri City India Communications & Networks Lab Department of Electrical and Computer Engineering National University of Singapore Singapore119260 Singapore Distributed Systems Group TU Wien Vienna1040 Austria Center for Ubiquitous Computing University of Oulu 90014 Finland Institute of Computer Science University of Tartu Tartu51009 Estonia

Zero-touch network is anticipated to inaugurate the generation of intelligent and highly flexible resource provisioning strategies where multiple service providers collaboratively offer computation and storage resources. This transformation presents substantial challenges to network administration and service providers regarding sustainability and scalability. This article combines distributed Artificial Intelligence (DAI) with Zero-touch Provisioning (ZTP) for edge networks. This combination helps to manage network devices seamlessly and intelligently by minimizing human intervention. In addition, several advantages are also highlighted that come with incorporating distributed AI into ZTP in the context of edge networks. Further, we draw potential research directions to foster novel studies in this field and overcome the current limitations. Copyright © 2023, The Authors. All rights reserved.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

EloMetrics: Advanced Outcome Prediction for Chess Matches with Elo Ratings and Logistic Regression

EloMetrics: Advanced Outcome Prediction for Chess Matches wi...

引用

International Conference on Electronics, Information and Communications (ICEIC)

作者： Ma. Julianna Re-an DG. Reyes Eirnan Dicreto Emmanuel Gabriel D. Santos Daniella Franxene P. Limbag Gabriel Avelino Sampedro College of Computer Studies De La Salle University Manila Philippines Networks and Distributed Systems Laboratory University of the Philippines Diliman Quezon City Philippines

ISBN: (数字)9798331510756

ISBN: (纸本)9798331510763

Chessis a complex game characterized by diverse strategies and time constraints, making quick decision-making essential for success. While Elo ratings are widely recognized as indicators of player skill, the predictability of match outcomes based solely on these ratings remains a challenge. The study aims to develop a model for accurately predicting the outcome of chess games using logistic regression, focusing on Elo rating differences and the number of moves in each game. The dataset includes over 20,000 games from ***, and only games with decisive outcomes (excluding draws) were used. The research categorizes Elo ratings into various classes and evaluates model performance across these ranges. The model achieves a predictive accuracy of 68.18%, demonstrating the significance of Elo ratings and move counts in determining game results. Performance metrics, including precision, recall, and Fl-score, further validate the model's effectiveness. The study concludes that while Elo ratings and move count are strong predictors of chess outcomes, further refinement is needed to improve performance at high-ranking skill levels. The model performs well for experts but loses accuracy in master-level games, reflecting higher skill-level complexities. The insights gained from this research contribute to a deeper understanding of predictive modeling in chess, sug-gesting potential avenues for further investigation into additional Influencing factors.

关键词： Training Measurement Analytical models Logistic regression Accuracy Focusing Psychology Games Predictive models Time factors

来源：评论

学校读者我要写书评

暂无评论

Business Intelligence Model for Customer Targeting Using Fuzzy-C-Means and FP-Growth

Business Intelligence Model for Customer Targeting Using Fuz...

引用

Emerging Smart Technologies and Applications (eSmarTA), International Conference on

作者： Sam Abdulilah Ahmed Mohammed Mogeeb A. Saeed Software Engineering Taiz University Taiz Yemen Computer Networks and Distributed systems Taiz University Taiz Yemen

In the era of business, business intelligence (BI) technology can inform the decision-maker of the right data and insight. In this study, a business intelligence model is built to help the marketing department build an efficient promotion strategy. This paper aims to understand the impact of segmenting customers using the soft clustering technique (fuzz-c-means) based on their spending behavior or Recency, Frequency, and Monetary Model (RFM model) on product affiliation or market basket analysis to develop more efficient promotions to target customers. This aim is approached first by, downloading a dataset called online retail from Kaggle, exploring data to remove the missing value and detect and remove outliers, and constructing an RFM model (Recency, frequency, and monetary). Second, the clustering algorithm is performed fuzzy-c-means, to segment customers into clusters with similar characteristics. Third, product affiliation or association rules are obtained as per cluster using the FP-growth algorithm. Eventually, spending behavior is concluded to show a significant impact on product affiliation which means that clustering based on spending behavior increases the efficiency of market basket analysis (MBA).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Int-BEB: Enhanced Binary Exponential Backoff using Q-learning

Int-BEB: Enhanced Binary Exponential Backoff using Q-learnin...

引用

International Conference on Pattern Analysis and Intelligent systems (PAIS)

作者： N. Zerguine Department of Computer Science Networks and Distributed Systems Laboratory Ferhat Abbas Setif 1 University Setif Algeria

Because of their development and success, MANETs are now preferred alternatives in many fields of study and application. The IEEE 802.11 standard is the basis of most wireless technologies. To treat collisions in wireless networks, IEEE 802.11 distributed Coordination Function (DCF) MAC layer employs Binary Exponential Backoff (BEB) algorithm, that is helpful in decreasing the potential of collision, but comes at the expense of several network performance metrics, such as medium access delay, bandwidth management, power use, and fairness. A Deep Learning technique called Deep Reinforcement Learning (DRL) allows an agent to communicate with the environment in order to accomplish a goal. In the present paper, we suggest Q-learning (QL), one of the DRL approaches to improve the Binary Exponential Backoff (BEB) in MANETs. The intelligently designed Int-BEB aims for better CW selection; this selection strikes to reduce collisions as much as possible and to give more chances to nodes that make collisions to access the channel by taking into consideration their residual energy. In-depth simulations are performed to evaluate the performance of the proposed mechanism. The performance of Int-BEB is evaluated in diverse networks with several criteria such as packet successful transmission, packet loss and energy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Effect of Taproot on Bitcoin Deanonymization

Analyzing the Effect of Taproot on Bitcoin Deanonymization

引用

International Conference on distributed Computing systems Workshop

作者： Felix Kleinwort Wolf Posdorfer Janick Edinger Department of Computer Science Distributed Operating Systems University of Hamburg Hamburg Germany Department of Computer Science Computer Networks University of Hamburg Hamburg Germany

Bitcoin was released in 2008 as an electronic peer-to-peer payment system. The aim was to enable financial transactions in an anonymous manner between participating parties. However, Bitcoin is considered a pseudonymous network rather than anonymous, as the identity of the address owner is unknown, but every transaction is permanently stored on the Bitcoin blockchain and can be tracked by anyone. The structure of the blockchain, its transactions, and the Bitcoin network make it possible to deanonymize pseudonyms through various methods such as flow analysis, heuristics, and network traffic observations. Once a connection is established between pseudonyms used in the Bitcoin network and the real world, all previous transactions can be attributed to that identity. In 2021, Taproot was introduced to further increase privacy within the Bitcoin Network by introducing a new address format which will allow transactions to be more indistinguishable from one another. In this paper, we analyze current methods for deanonymizing Bitcoin transactions to understand which parts of the Bitcoin protocol they exploit. In addition, we look at the changes introduced by Taproot and determine the extent to which these changes affect the methods and what assumptions must be made for these methods to remain applicable.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PpNNT: Multiparty Privacy-Preserving Neural Network Training System

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第1期5卷 370-383页

作者： Feng, Qi He, Debiao Shen, Jian Luo, Min Choo, Kim-Kwang Raymond Wuhan University School of Cyber Science and Engineering Wuhan430072 China Shandong Provincial Key Laboratory of Computer Networks Jinan250014 China School of Information Science and Technology Zhejiang Sci-Tech University Hangzhou310018 China Shanghai Technology Innovation Centre of Distributed Privacy-Preserving Artificial Intelligence Matrix Elements Technologies Shanghai201204 China University of Texas at San Antonio Department of Information Systems and Cyber Security San AntonioTX78249 United States

By leveraging smart devices [e.g., industrial Internet of Things (IIoT)] and real-time data analytics, organizations, such as production plants can benefit from increased productivity, reduced costs, enhanced self-monitoring, and autonomous decision-making. In such a setting, machine learning plays an important role in data analytics, but the use of conventional centralized machine learning solutions may raise uncomfortable concerns about data privacy. Hence, one can explore the use of federated learning. In this article, we propose privacy-preserving deep neural network training (PpNNT), which is designed to support federated learning in the multiparty setting. To minimize the overall costs, we further design a hybrid architecture to fully maximize resource utilization. Our proposed design allows the PpNNT system to provide high security, efficiency, and scalability for IIoT data analytics, as evidenced by our theoretical security proof and experimental results on the CIFAR10 dataset. © 2020 IEEE.

关键词： Decision making

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：