检索结果-内蒙古大学图书馆

International Conference on Emerging Technologies, ICET

作者： Hassan Bin Khalid Abu Bakar Siddique Raja Hashim Ali Faculty of Computer Science & Engineering GIK Institute of Engg. Sciences & Technology Topi Pakistan Dept. of Technology & Software Engineering University of Europe for Applied Sciences Berlin Germany

Hidden Markov Models have proved to be a very significant tool for various time-series related problems, especially where context is important. One such problem is Part-of-speech tagging. The work uses a customized HMM to propose an effective and advanced solution to POS tagging. With a precision rate of 0.9657, recall of 0.9656, and F1-score of 0.9655, this proposed HMM-based model achieves an exceptional level of accuracy, exhibiting its accurate identification of the POS of words in a sentence. The statistical model employed by the HMM-based method predicts the most likely POS tags while taking into account the probabilities of transition between various POS tags. The model's dependability and resilience were demonstrated when it was tested on a different dataset after being trained on a extensive collection of text data. The study's findings demonstrate that the HMM-based strategy outperforms current POS tagging techniques, making it a significant contribution to the field of natural language processing. In addition, this research has significant implications for a number of NLP applications, including sentiment analysis, machine translation, and text categorization, paving the way for additional innovation and exploration in this domain.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Impact of COVID-19 on Predicting 2020 US Presidential Elections on Social Media 16th

Impact of COVID-19 on Predicting 2020 US Presidential Electi...

引用

16th International Conference on Information Technology and Applications, ICITA 2022

作者： Khan, Asif Zhang, Huaping Boudjellal, Nada Hayat, Bashir Dai, Lin Ahmad, Arshad Al-Hamed, Ahmed School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China The Faculty of New Information and Communication Technologies University Abdelhamid Mehri Constantine 2 Constantine25000 Algeria Institute of Management Sciences Peshawar Peshawar Pakistan Institute of Software Systems Engineering Johannes Kepler University Linz4040 Austria Department of IT and Computer Science Pak-Austria Fachhochschule: Institute of Applied Sciences and Technology Mang Khanpur Road Haripur22620 Pakistan

ISBN: (纸本)9789811993305

By the beginning of 2020, the world woke up to a global pandemic that changed people’s everyday lives and restrained their physical contact. During those times Social Media Platforms (SMPs) were almost the only mean of individual-to-individual and government-to-individuals communications. Therefore, people’s opinions were more expressed on SM. On the other hand, election candidates used SM to promote themselves and engage with voters. In this study, we investigate how COVID-19 affected voters’ opinions through the months of the US presidential campaign and eventually predict the 2020 US Presidential Election results using Twitter’s data. Mainly two types of experiments were conducted and compared;(i) transformer-based, and (ii) rule-based sentiment analysis (SA). In addition, vote shares for the presidential candidates using both approaches were predicted. The results show that the rule-based approach nearly predicts the right winner, Joe Biden with MAE 2.1, outperforming the predicted results from CNBC, Economist/YouGov, and transformer-based (BERTweet) approach, except for RCP (MAE 1.55). © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Diving into Brain Complexity: Exploring Functional and Effective Connectivity Networks

Diving into Brain Complexity: Exploring Functional and Effec...

引用

International Conference on Emerging Technologies, ICET

作者： Abu Bakar Siddique Hassan Bin Khalid Raja Hashim Ali Faculty of Computer Science & Engineering GIK Institute of Engg. Sciences & Technology Topi Pakistan Dept. of Technology & Software Engineering University of Europe for Applied Sciences Berlin Germany

The human brain's intricate functions are under-pinned by a vast network of synapses that enable chemical impulses between neurons. Neuroscientists employ two key approaches, functional and effective connectivity, to understand the brain's complexity, focusing on its operations, cognition, and behavior. While both methods utilize graph theory for network analysis, functional connectivity, which investigates associated brain activity, has seen more substantial research efforts than effective connectivity, which examines information processing's inter-regional impacts. In this research paper, we aim to present an extensive examination of the emerging discipline that combines graph theory with the analysis of brain characteristics, shedding light on how these characteristics arise from the interactions among different groups of neurons. Our primary focus lies in exploring the diverse cognitive and neurological applications that leverage functional Magnetic Resonance Imaging (fMRI) as a tool. Additionally, we offer a comprehensive overview of the methods employed to construct brain networks based on functional and efficient connections. Throughout the discussion, we emphasize the advantages and limitations associated with these approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Boost Decentralized Federated Learning in Vehicular Networks by Diversifying Data Sources

Boost Decentralized Federated Learning in Vehicular Networks...

引用

International Conference on Network Protocols

作者： Dongyuan Su Yipeng Zhou Laizhong Cui College of Computer Science and Software Engineering Shenzhen University Shenzhen China Faculty of Science and Engineering School of Computing Macquarie University Sydney Australia

ISBN: (数字)9781665482349

ISBN: (纸本)9781665482356

Recently, federated learning (FL) has received intensive research because of its ability in preserving data privacy for scattered clients to collaboratively train machine learning models. Commonly, a parameter server (PS) is deployed for aggregating model parameters contributed by different clients. Decentralized federated learning (DFL) is upgraded from FL which allows clients to aggregate model parameters with their neighbours directly. DFL is particularly feasible for vehicular networks as vehicles communicate with each other in a vehicle-to-vehicle (V2V) manner. However, due to the restrictions of vehicle routes and communication distances, it is hard for individual vehicles to sufficiently exchange models with others. Data sources contributing to models on individual vehicles may not diversified enough resulting in poor model accuracy. To address this problem, we propose the DFL-DDS (DFL with diversified Data Sources) algorithm to diversify data sources in DFL. Specifically, each vehicle maintains a state vector to record the contribution weight of each data source to its model. The Kullback–Leibler (KL) divergence is adopted to measure the diversity of a state vector. To boost the convergence of DFL, a vehicle tunes the aggregation weight of each data source by minimizing the KL divergence of its state vector, and its effectiveness in diversifying data sources can be theoretically proved. Finally, the superiority of DFL-DDS is evaluated by extensive experiments (with MNIST and CIFAR-10 datasets) which demonstrate that DFL-DDS can accelerate the convergence of DFL and improve the model accuracy significantly compared with state-of-the-art baselines.

关键词： Data privacy Protocols Federated learning Soft sensors Aggregates Vehicular ad hoc networks Data models

来源：评论

学校读者我要写书评

暂无评论

Boost Decentralized Federated Learning in Vehicular Networks by Diversifying Data Sources

arXiv

引用

arXiv 2022年

作者： Su, Dongyuan Zhou, Yipeng Cui, Laizhong College of Computer Science and Software Engineering Shenzhen University Shenzhen China School of Computing Faculty of Science and Engineering Macquarie University Sydney Australia

Recently, federated learning (FL) has received intensive research because of its ability in preserving data privacy for scattered clients to collaboratively train machine learning models. Commonly, a parameter server (PS) is deployed for aggregating model parameters contributed by different clients. Decentralized federated learning (DFL) is upgraded from FL which allows clients to aggregate model parameters with their neighbours directly. DFL is particularly feasible for vehicular networks as vehicles communicate with each other in a vehicle-to-vehicle (V2V) manner. However, due to the restrictions of vehicle routes and communication distances, it is hard for individual vehicles to sufficiently exchange models with others. Data sources contributing to models on individual vehicles may not diversified enough resulting in poor model accuracy. To address this problem, we propose the DFL-DDS (DFL with diversified Data Sources) algorithm to diversify data sources in DFL. Specifically, each vehicle maintains a state vector to record the contribution weight of each data source to its model. The Kullback-Leibler (KL) divergence is adopted to measure the diversity of a state vector. To boost the convergence of DFL, a vehicle tunes the aggregation weight of each data source by minimizing the KL divergence of its state vector, and its effectiveness in diversifying data sources can be theoretically proved. Finally, the superiority of DFL-DDS is evaluated by extensive experiments (with MNIST and CIFAR-10 datasets) which demonstrate that DFL-DDS can accelerate the convergence of DFL and improve the model accuracy significantly compared with state-of-the-art baselines. Copyright © 2022, The Authors. All rights reserved.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Classifier Performance on Reduced Feature Sets

Comparative Analysis of Classifier Performance on Reduced Fe...

引用

Computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Raed Alazaidah Wael Hadi Suhaila Abu Owaida Alaa Bani-bakr Mo'ath Alluwaici Muhyeeddin Alqaraleh Department of Data Science Faculty of Information Technology Zarqa University Zarqa Jordan Department of Information Security Faculty of Information Technology University of Petra Amman Jordan Department of Computer Science Faculty of Information Technology Al-al-Bayt University Mafraq Jordan Department of Cyber Security Faculty of Information Technology Zarqa University Zarqa Jordan Department of Computer Science Faculty of Information Technology Zarqa University Zarqa Jordan Software Engineering Department Faculty of Information Technology Zarqa University Zarqa Jordan

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

In this study, we examine the impact of feature reduction on the performance of various classifiers within the Weka environment. Utilizing the Pima Indians Diabetes Database, we compare the Accuracy, Precision, Recall, F1-measure, and other relevant metrics across classifiers like BayesNet, NaiveBayes, and NaiveBayesMul when applied to full and reduced feature sets. The reduction process involves halving the attribute count, aiming to assess the efficacy of machine learning models in scenarios with constrained feature availability. Our results indicate significant differences in the performance of the models, offering insights into the trade-offs between model complexity and predictive power in medical dataset applications.

关键词： Measurement Productivity Data analysis Accuracy Systematics Databases Machine learning Predictive models Diabetes Reliability

来源：评论

学校读者我要写书评

暂无评论

Improved Time-Saving Face Detection in Video

Improved Time-Saving Face Detection in Video

引用

International engineering Conference (IEC)

作者： Jihad Anwar Qadir Shayan Ihsan Jalal Samer Kais Jameel Abdulbasit Al-Talabani Department of Computer Science College of Basic Education University of Raparin Rania Kurdistan Region Iraq Department of Software Engineering Faculty of Engineering Koya University Koya Kurdistan Region Iraq

Human face detection from video sequences is a difficult problem in computer vision. Face detection is the process of determining the location of a face or faces in each frame of a video. Face detection in real-time videos is an ongoing under-investigated research problem. This paper proposes a new method for face detection in videos that significantly reduces the time required to detect faces. The method targets a Search Area Boundary (SAB) in the next frames that are determined based on the position of the detected faces in the current frame. The model will look for the face in a box that is slightly larger than the SAB from the previous frame. This means that it will not search the entire video frame for the face, so it will take less time to find the face. After a few frames, the method will begin searching the entire frame for new faces. The results show that the proposed method can save up to 73.5% of the time, especially when the SAB is small, with an accuracy degradation of no more than 7% in the best case.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Effect of Using Continuous Integration (CI) and Continuous Delivery (CD) Deployment in DevOps to reduce the Gap between Developer and Operation

Effect of Using Continuous Integration (CI) and Continuous D...

引用

Information Technology (ACIT)

作者： Abrar Mohammad Mowad Hamed Fawareh Mohammad A. Hassan Software Engineering Dept Faculty of Information Technology Zarqa University Computer Science Dept Faculty of Information Technology Zarqa University

ISBN: (数字)9798350320244

ISBN: (纸本)9798350320251

This paper focuses on how to use continuous integration (CI) and continuous Delivery (CD) methodology in DevOps to reduce the developer-operator gap. It also, shows how CI can be a CD bridge. The paper review DevOps and analyze strategies, methodologies, issues, and processes identified for the adoption and implementation of continuing practices. The result of our case studies shows the benefits, and advantages of using CI/CD in software development. Furthermore, this paper presents DevOps as a new model for reducing the gaps between development (Dev) and operations (ops). The Azure tool is used as DevOps CI/CD for the empowerment of continuous delivery of software to enable rapid and frequent releases, this enables rapid responses to changing customer requirements and thus it may be a decisive competitive advantage. This paper also measures the effectiveness of using CI/CD for reducing the time and effort in software development. We also, focus on the DevOps initiative to benefit of CI/CD and to effect of enhances flexibility in delivering the program with the expected quality on time to determine the areas that bridge the gap between Continuous Integration for Continuous Delivery. The methodology used in this paper by exploring and tracking a project developed by the company using the Azure software development tool. The experiment includes a project performance and evaluation.

关键词： Bridges Codes Source coding Pipelines Companies software Time measurement

来源：评论

学校读者我要写书评

暂无评论

Security-based Safety Hazard Analysis using STAMP, STPA & HAZOP: A DAM Case Study

Security-based Safety Hazard Analysis using STAMP, STPA & HA...

引用

Frontiers of Information Technology (FIT)

作者： Muhammad Farooq Irum Inayat Maya Daneva Department of Software Engineering National University of Computer Emerging Sciences Islamabad Pakistan Department of Creative Technology Air University Islamabad Pakistan LERO University College Cork Cork Ireland Faulty of Electrical Engineering Mathematics and Computer Science (EEMCS) Services Cybersecurity & Safety (SCS) University of Twente Enschede The Netherlands

Security and safety emerged as an interconnected concept for Cyber-Physical Systems (CPS). In recent years, CPS witnessed an enormous cyber-attack that endorsed the significance of security over safety of the CPS. Many cyber incidents have been recorded where intruders exploit security vulnerabilities that result in safety hazards. In literature, often times security and safety are discussed as a combined concern. This presses the need to treat security and safety as a mutual apprehension. However, more empirical evidence is required to support this mutuality of security and safety. To close this gap, we conducted an empirical study to identify hazard(s) using several methods including the Systematic Theoretical Accidental Model and Process (STAMP), Systematic Theoretic Process Analysis (STPA), Hazard and Operability Study (HAZOP) of a CPS i.e., case study of a Dam , and to performed the risk management (risk identification, risk analysis and mitigation) for the mentioned case study. Our focus remained on security and safety risks only. As a result, we identified all the possible unsafe control events and their potential hazards along with the severity level. Moreover, we suggested the risk mitigation mechanism against the identified hazards which may contribute to the accidents. This study holds implications for CPS practitioners and researchers exploring risk in CPS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Campus Exploration with GikiLenS: A Deep Learning-Powered Object Detection App

Revolutionizing Campus Exploration with GikiLenS: A Deep Lea...

引用

International Conference on Emerging Technologies, ICET

作者： Iqra Mueed Usama Arshad Raja Hashim Ali Faculty of Computer Science & Engineering GIK Institute of Engg. Sciences & Technology Topi Pakistan Dept. of Technology & Software Engineering University of Europe for Applied Sciences Berlin Germany

For newcomers and tourists, navigating university campuses can be difficult, resulting in aggravation and lost time. We respond by introducing “GikiLenS”, an object identification application driven by deep learning that revolutionizes campus exploration by accurately identifying buildings and landmarks while enhancing user experience. GikiLenS is a comprehensive and user-friendly smartphone application that precisely caters to the demands of newcomers and visitors, unlike previous studies in campus navigation. Our study intends to close this gap and develop a reliable method for identifying campus buildings, optimizing navigation, and enhancing user experience. Through rigorous testing, GikiLenS has proven to have remarkable real-time building detection accuracy, highlighting its potential as an important tool for campus exploration. The app's outcomes and conclusions demonstrate how well it works to give users specific building information, promoting a more knowledgeable and enjoyable campus experience. The importance of our findings lies in the development of a unique, user-centered app that offers a cutting-edge method of campus mobility. Our contribution consists of a game-changing method for building detection that improves campus exploration and user pleasure.

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：