检索结果-内蒙古大学图书馆

IEEE Networking Letters 2025年第1期7卷 51-55页

作者： Metaferia, Getahun Lemma, Frezewd Adama Science and Technology University Department of Computer Science and Engineering Adama1881 Ethiopia

Software-defined Networking (SDN) is an innovative network architecture tailored to address the modern demands of network virtualization and cloud computing, which require features such as programmability, flexibility, agility, and openness to foster innovation. However, this architecture also brings forth new security challenges, particularly due to the separation of the data plane from the control plane. Our investigation centers on a specific vulnerability termed link fabrication, which can lead to topology poisoning. A compromised network topology can cause substantial disruptions across the entire network infrastructure. Through a systematic survey, we identified that significant research efforts have been directed towards mitigating link fabrication attacks. We classified the existing studies into six categories of vulnerabilities: Host-based, port amnesia, invisible assailant attack, topology freezing, switch-based link fabrication, and link latency. Furthermore, our survey highlights several open challenges in areas such as Programmable dataplane, dedicated attack trees and threat models, active defense and mitigation strategies, as well as controller awareness and machine learning. To address the vulnerabilities identified, we propose the implementation of a distance-bounding protocol concept at the control plane as a potential solution. © 2019 IEEE.

关键词： Fabrication Topology Network topology Control systems Relays Threat modeling Switches Routing Software defined networking Security

来源：评论

学校读者我要写书评

暂无评论

ASSESSING THE ROLE OF PROJECT MANAGER IN AGILE ENVIRONMENTS

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical engineering and computer Science 2024年第4期2024卷 95-108页

作者： Tudose, Cătălin Boiangiu, Costin Anton Bădoi, Iulia Bianca Iordache, Elena Alexandra Computer Science and Engineering Department National University of Science and Technology POLITEHNICA Bucharest Romania

Agile methodology does not formally define the role of a project manager, and the Scrum methodology distributes this role among team members. However, the success of software development projects often depends heavily on this role, so typically, one person assumes the responsibility of a project manager in Agile environments. Project managers must adapt their strategies to address the various challenges of this constantly evolving market as more companies embrace Agile approaches to improve their flexibility and responsiveness. The objective of this article is to evaluate project managers’ roles in Agile environments by examining various aspects of their responsibilities and contributions. Project managers play crucial roles in planning, organizing, and guiding teams, with a primary focus on enhancing communication, managing resources, mitigating risks, and fostering collaboration. Key insights into the role of project managers in Agile software teams will be explored through a systematic review of the literature. The paper will also investigate how project managers balance internal and external dynamics, embrace change, and promote innovation to lead successful relationship management in Agile environments. © 2024, Politechnica University of Bucharest. All rights reserved.

关键词： Project management

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Crowd Surveillance and Density Estimation

Deep Learning-Based Crowd Surveillance and Density Estimatio...

引用

2024 International Conference on Artificial Intelligence and Quantum Computation-Based Sensor Applications, ICAIQSA 2024

作者： Deokate, Sarika Rajput, Satpalsingh Nair, Mahima Parale, Disha Mahamuni, Asmita Nalla, Priyanka PCCOE Department of Computer Engineering Maharashtra Pune India VIT Department of Computer Engineering Maharashtra Pune India

ISBN: (纸本)9798331517953

Crowd counting and surveillance are crucial for maintaining public safety and managing large gatherings effectively. Existing methodologies primarily include manual counting, traditional image processing, and various machine learning techniques. In this paper, we propose an enhanced deep learning-based methodology for more accurate crowd counting. Our study evaluated three human detection models: YOLO v3 with Canny Edge Detector, YOLO v3 with Hungarian & Kalman filtering and YOLO v5 with OpenCV functionalities. Among these, YOLO v3 with Canny Edge Detector demonstrated superior performance, achieving the highest accuracy (86.8%) and precision (75%). These results highlight the effectiveness of the YOLO model for crowd counting applications. Our findings indicate that advanced deep learning models significantly improve crowd surveillance and density estimation, offering promising implications for enhancing public safety measures and event management strategies. © 2024 IEEE.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Fuzzy conceptualization of the search queries

引用

International Journal of Information Technology (Singapore) 2024年第2期16卷 957-965页

作者： Sijin, P. Champa, H.N. Department of Computer Science and Engineering University Visvesvaraya College of Engineering Bangalore India

Deciding the context of the search query based on its representation over a concept network using fuzzy methods provides a better thrust to the overall search process. The existing context based search diversification methods emphasize the importance of the numerical representation of the query over a data repository and derive a query peace which is conceptually measured. The search operation can use these semantically meaningful segments as a confident segment in the conceptual network. The proposed Fuzzy Conceptual Search Model (FCM) derives a query string which is contextually measured by means of valid segmentation, Pairwise Type Detection and concept labeling on its Concept Network. The approach measures the semantic coherence among segments in the search query and prepares a valid query piece. The Maximal Clique Cycle Count (MCCC) algorithm is used in valid segmentation process. The novel randomized MCCC algorithm improved the quality of query segmentation process and considered shared segments and conceptual ring count to improvise the efficiency of the search. The segmented query paths are processed with proper instances to pinpoint the context of the search at an earlier phase. The instance ambiguity is removed by conducting a threshold pair wise modeling of typed terms followed by a weighted voting approach called Concept labeling. The proposed FCM shows good results in terms of precision for both query and tweet data sets with varying impact lexical feature indication values. © The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s);author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

关键词： Concept labeling Concept network Conceptual ring Maximal clique Singleton score

来源：评论

学校读者我要写书评

暂无评论

A Predictive Model of the Stock Market Using the LSTM Algorithm with a Combination of Exponential Moving Average (EMA) and Relative Strength Index (RSI) Indicators

引用

Journal of The Institution of Engineers (India): Series B 2024年第5期105卷 1145-1157页

作者： Dhokane, Rahul Maruti Agarwal, Sohit Computer Science and Engineering Department Suresh Gyan Vihar University Rajasthan Jaipur India

This research paper has focused on the integration of promising stock market indicators such as the relative strength index (RSI) and different versions of the exponential moving average (EMA) (i.e., 50-day, 100-day, and 150-day EMA) with the long short-term memory (LSTM) machine learning algorithm for stock price prediction. LSTM is the most robust version of recurrent neural network because it can handle the "vanishing gradient" problem effectively and handle lengthy time series data. The selected dataset was taken from NSE India using Yahoo Finance. In our proposed research, we used RSI and EMA data along with basic features such as open, high, low, close, and volume (OHLCV) information. The selected technical indicators and OHLCV data act as input features for the LSTM model. The results show that the integration of technical indicators along with traditional OHLCV improves the performance of the stock closing price prediction model. The evaluation metrics used in this research are the RMSE, MAPE, and R2 score. The improvements in the R2 score and decreases in the RMSE and MAPE indicate that the proposed technique performs well in stock closing price prediction. The proposed technique helps to improve intraday trading by predicting the closing price of the stock for the next day and the trends of selected stocks in the near term. © The Institution of Engineers (India) 2024.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Multi-level Data Integrity Model with Dual Immutable Digital Key Based Forensic Analysis in IoT Network

引用

SN computer Science 2024年第1期5卷 1-13页

作者： Deepthi, J. V. N. Raghava Khan, Ajoy Kumar Acharjee, Tapodhir Department of Computer Science and Engineering Assam University Silchar Assam Silchar 788011 India Department of Computer Engineering Mizoram University Aizawl India

Over the last decade, the proliferation of Internet of Things (IoT) devices has risen dramatically. The exponential growth of IoT device ecosystems has led to a rise in the risks and cybercrimes associated with the IoT. Because of their malleability, IoT devices are more susceptible to persistent attacks. Forensic investigation of attacks on IoT devices can be challenging for security experts due to the limited processing and memory capabilities of these devices. The existing methods are often complex for IoT environment and providing moderate results. The primary objective of this research is to determine and recommend a secured framework for the IoT that maintains data integrity. This research proposes a simple scheme called Multi-level Data Integrity Model with Dual Immutable Digital Key based Forensic Analysis (MLDIM-DIDKbFA) for securing the IoT data. A digital key is generated which is used for validation of nodes during data transmission. Cyber-attack detection Forensic analysis due to possible cyber-attack is performed if any violation to data integrity is detected in IoT network. The proposed model was contrasted with two state-of-the-art existing models Binary Classifiers for Data Integrity Detection in Wearable IoT Edge Devices (BCDTED) and Distributed Estimation against Data Integrity Attacks in IoT Systems (DEA-DIA). The parameters used for comparison are time and accuracy for node registration, immutable key generation, intermediate node verification, multi-level data integrity verification, forensic analysis etc. It is found that our proposed method is providing better results compared to the other two existing systems. As a result, the proposed forensic system boosts the effectiveness and credibility of IoT environment forensics. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Cyber-attacks Data confidentiality Data integrity Data security Digital key Forensics Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Thermal-energy-efficient-secured-link reliable and delay-aware routing protocol (TESLDAR) for wireless body area networks

引用

International Journal of computers and Applications 2024年第9期46卷 715-727页

作者： Mohanty, Rasmita Kumari Sahoo, Satya Prakash Kabat, Manas Ranjan Department of Computer Science and Engineering Veer Surendra Sai University of Technology Burla India

Wireless Body Area Networks (WBANs) have emerged as a transformative technology for health monitoring, leveraging sensor nodes placed on or within the human body. This paradigm offers real-time insights into physiological parameters, enabling remote healthcare applications and enhancing patient well-being. However, the WBANs bring challenges that demand innovative solutions to ensure their seamless integration into healthcare ecosystems. Secondly, trustworthiness becomes paramount in healthcare applications, where the sensitivity of health-related data necessitates secure and reliable communication. Lastly, congestion issues, arising from bandwidth constraints and concurrent data transmissions, affect the performance of WBANs, impacting data integrity, energy consumption, and quality of service. Therefore, this paper proposes a TESLDAR protocol that incorporates the proposed Jellyfish Updated Aquila Narrow ExploExpand (JUANE) method aims to address issues such as hotspot-induced thermal stress, trustworthiness concerns, and congestion challenges. The proposed algorithm incorporates Jellyfish Optimization (JFO), inspired by the adaptable movement of jellyfish, with characteristics inspired by the Aquila bird. The method's innovative integration of jellyfish and bird-inspired behaviors positions it as a promising solution for efficient route maintenance in WBANs addressing thermal, trust, and congestion challenges for enhanced reliability in healthcare monitoring applications. © 2024 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Diabetic retinopathy detection by fundus images using fine tuned deep learning model

引用

Multimedia Tools and Applications 2024年第39期83卷 86657-86679页

作者： Singh, Satya Prakash Gupta, Pankaj Dung, Rakshita Department of Computer Science & amp Engineering Birla Institute of Technology Ranchi Mesra India

This study employs transfer learning using a fine-tuned pretrained EfficientNetB0 convolutional neural network (CNN) model to accurately detect the various stages of Diabetic Retinopathy. The training process involved utilizing three datasets: Messidor, IDRiD (Indian Diabetic Retinopathy Detection), and APTOS 2019 Blindness Detection, which collectively encompassed 5,379 fundus images. Different types of processed fundus images were fed into the model to determine the optimal pre-processing approach for stage detection in Diabetic Retinopathy. The model was assessed on the original dataset with some augmentation techniques applied. According to the training data, the model achieved a maximum accuracy of 72%. However, converting the dataset to grayscale yielded an improved accuracy of 80%. Similarly, extracting the green, red, and blue channels individually resulted in accuracies of 72%, 76%, and 73% respectively. Notably, when the green channel extracted images underwent histogram equalization, the model achieved its highest accuracy of 83%. Furthermore, the application of a Sobel filter to the red channel images led to a maximum accuracy of 51%. Finally, to determine the effectiveness of each processed image type, sensitivity and specificity measures were compared. Among all the variations, the green channel extracted images with histogram equalization demonstrated superior performance in correctly identifying the respective classes, outperforming the other approaches. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Exploration, Collaboration, and Applications in Multi-Agent Reinforcement Learning

引用

Performance Evaluation Review 2025年第3期52卷 31-34页

作者： Chen, Jingdi Department of Electrical and Computer Engineering Carnegie Mellon University PittsburghPA United States

In recent years, the field of humancentric decision-making has emerged as a critical area of research, driven by its potential to fundamentally reshape how decisions are made across a variety of complex systems. Human-centric decision-making is characterized by considerable variability, which can be both advantageous and problematic. Variability is beneficial in contexts like brainstorming or problem-solving, where diverse perspectives lead to innovation. However, in situations where consistency is crucial- such as public health, safety, and fairness-this variability can have negative consequences. For instance, when radiologists interpret the same mammogram differently, it can result in unnecessary medical procedures. Similarly, in military operations, inconsistent judgments by sonar technicians regarding potential threats can jeopardize both crew safety and mission success. This highlights the critical need for a deeper understanding of decisions where the stakes are high. Thus, it is important to deepen our understanding of the decision-making process in completed and dynamic scenarios that involve multiple decisionmakers. This should guide the creation of validated methods to identify, measure, model, and adjust variability in judgments to improve decision-making in multi-agent environments. © 2025 Copyright is held by the owner/author(s).

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

An improved method for classifying depth-based human actions using self-adaptive evolutionary technique

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第1期15卷 157-173页

作者： Pareek, Preksha Thakkar, Ankit Department of Computer Science and Engineering Institute of Technology Nirma University Gujarat Ahmedabad India

Automatic Human Action Recognition (HAR) using RGB-D (Red, Green, Blue, and Depth) videos captivated a lot of attention in the pattern classification field due to low-cost depth cameras. Feature extraction in action recognition is an important aspect. As compared to Depth Motion Maps (DMM), Depth Motion Maps–Local Binary Pattern (DMM–LBP) provides compact representation of features. After extracting features using DMM–LBP, Principal Component Analysis (PCA) is used for dimensionality reduction. For classification task, randomly generated input weights of Extreme Learning Machine (ELM) can lead to non-optimal results. Therefore, in this paper, we have used an improved learning algorithm named Self-adaptive Differential Evolution (SaDE) ELM for action classification. In the proposed approach, DMM–LBP is used for feature extraction and SaDE–ELM is used for action classification. To evaluate strength of the proposed approach, experiments are performed on four public datasets, namely, MSRAction3D, MSRDaily Activity3D, UTD–MHAD, and MSRGesture3D. The proposed approach gives better accuracy compared to existing approaches Kernel ELM (KELM), l2-Collaborative Representation Classifier (l2-CRC), and Probabilistic CRC (ProCRC) methods. We have also presented statistical significance of results in the paper. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022.

关键词： Local binary pattern

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：