检索结果-内蒙古大学图书馆

12th International Conference on Image Processing Theory, Tools and Applications, IPTA 2023

作者： Yassin, Mahmoud Y. M. Nasir, Ali A. Taha, Mostafa Iqbal, Naveed Department of Electrical Engineering Dhahran Saudi Arabia Center for Communication Systems and Sensing Kfupm Dhahran Saudi Arabia Carleton University Systems and Computer Engineering OttawaON Canada

ISBN: (纸本)9798350325416

Chaotic image encryption has been investigated extensively in the literature in different domains, including the frequency domain using Discrete Fourier Transform (DFT). Despite DFT-based chaotic image cryptosystems exhibiting good confusion properties, they suffer from poor diffusion characteristics and non-uniform histograms. Therefore, they are vulnerable to many attacks, such as differential attacks, and statistical cryptanalytic attacks. This paper presents an enhanced block cipher image cryptosystem with several modes of operation based on the concept of bit reversal using the 2D chaotic Baker map and DFT. The proposed enhancement develops an improved image encryption scheme that involves properly diffusion-confusion enhanced operations within modified versions of the known block cipher modes of operation, namely Cipher Block Chaining Mode (CBC), Cipher Feedback Mode (CFB), and Output Feedback Mode (OFB). These enhanced operations are based on a 2D chaotic baker map in the Fourier domain. The proposed enhancement is validated using a MATLAB simulation. Results show that the proposed work manages to overcome the abovementioned problems outstandingly and outperforms the existing results in the literature in many encryption quality metrics. © 2023 IEEE.

关键词： Discrete Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

Worst-Case Execution Time Analysis of Real-Time Robotic Algorithms Using Reinforcement Learning

Worst-Case Execution Time Analysis of Real-Time Robotic Algo...

引用

Collaborative Advances in Software and COmputiNg (CASCON), International Conference on

作者： Arvin Samiei Nafiseh Kahani Mohammadreza Dehghanitafti Mojtaba Ahmadi Systems and Computer Engineering Carleton University Canada Mechanical and Aerospace Engineering Carleton University Canada

ISBN: (数字)9798331504830

ISBN: (纸本)9798331515621

This study investigates the application of Reinforce-ment Learning (RL) for estimating the Worst-Case Execution Time (WCET) of real-time robotic algorithms, crucial for ensuring reliable robotic navigation and interaction. The research eval-uates these computational techniques through two industrial case studies: (1) collision detection among two mobile cylinders and a stationary box; and (2) a six-degree-of-freedom (6-DOF) robotic model executing complex tasks. By leveraging RL, the study explores extensive input spaces to identify scenarios approaching the WCET within a controlled simulation environment. Through an experimental evaluation, we compare RL against Genetic Algorithms (GA) and random search approaches. The results demonstrate that RL outperforms both GA and random search. This research highlights the potential of RL to provide more accurate and reliable W CET estimations, thereby enhancing the safety and efficiency of real-time robotic systems.

关键词： Machine learning algorithms Service robots Software algorithms Estimation Real-time systems 6-DOF Space exploration Reliability Collision avoidance Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Mathematical Models for Task Assignment with Service Level Agreement in Fog Computing

Mathematical Models for Task Assignment with Service Level A...

引用

2022 International Conference on Smart Applications, Communications and Networking, SmartNets 2022

作者： Salem, Ahmed St-Hilaire, Marc Khan, Muhammad Sajjad Carleton University Department of Systems and Computer Engineering Ottawa Canada Carleton University Internarional Islamic University Islamabad Pakistan

ISBN: (纸本)9781665487580

Fog computing networks are being used to provide low latency connectivity to end users. However, to efficiently operate fog networks, service providers need tools to optimally assign users' requests. In this paper, we propose two mathematical models for the task assignment problem in fog computing. The main objective of both models is to maximize the fog service provider's profit while satisfying the Service Level Agreement (SLA) requirements of the offloaded tasks. In addition, each model focuses on a specific requirement to satisfy various service providers' needs. More precisely, the first model considers green computing practices through an energy-efficient fog nodes operation. The second model addresses load balancing requirements by minimizing the difference between the node's utilization across the fog network. Since these models provide optimal solutions, they can be useful for benchmarking various real-time algorithms. © 2022 IEEE.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

Improved IMU/GNSS EKF Fusion Using XGBoost Machine Learning Algorithm

Improved IMU/GNSS EKF Fusion Using XGBoost Machine Learning ...

引用

Electrical engineering (ICEENG), 12th International Conference on

作者： Rohan Kumar Reddy Damagatla Mohamed Atia Systems and Computer Engineering Carleton University Ottawa Canada

ISBN: (数字)9798350343427

ISBN: (纸本)9798350343434

For years, Inertial Measurement Unit (IMU) and Global Positioning System (GPS) have been playing a crucial role in navigation systems. The emergence of inexpensive IMU sensors has offered a lightweight alternative, yet they suffer from larger errors that build up gradually, leading to drift errors in navigation. Traditionally, IMUs are combined with GPS to ensure stable and accurate navigation. However, this integration fails during challenging GPS environments. This work introduces an inventive approach to alleviate navigation drifts by eradicating IMU errors through the utilization of the Extreme Gradient Boosting (XGBoost) algorithm. Unlike traditional approaches relying on high-end IMUs, this paper utilizes Inverse Kinematics to obtain pseudo-clean IMU training data from PVA values estimated by the EKF when GPS signals are available. The proposed approach is evaluated using both simulated and real-world datasets across various GPS outage durations, demonstrating significant enhancements in PVA estimation.

关键词： Electrical engineering Measurement units Machine learning algorithms Training data Estimation Kinematics Inertial navigation

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Approximation of Formal Implicit Interaction Analysis for Cyber-Physical System Designs

Data-Driven Approximation of Formal Implicit Interaction Ana...

引用

2024 Resilience Week, RWS 2024

作者： Newton, Luke Jaskolka, Jason Rouland, Quentin Hamid, Brahim Carleton University Systems and Computer Engineering Ottawa Canada Université du Québec en Outaouais Computer Science and Engineering Gatineau Canada Université de Toulouse CNRS UT2 Irit France

ISBN: (纸本)9798350388985

Implicit interactions are a type of system vulnerability which refer to sequences of communication between components in a system that are unplanned, unexpected, and/or unforeseen by system designers. The presence of implicit interactions can have impacts on system safety, security, stability, and resilience. The existing work to identify and analyze implicit interactions, as well as locate areas in a system for redesign to mitigate implicit interactions, all require the use of formal methods, which limits industry adoption. In this work, we identify measurements based on graph abstractions of system design models that can be used to produce similar results as the aforementioned formal analyses. We demonstrate this on a model of a real-world wastewater dechlorination system. By combining data collected from formal and graph measurements, we provide alternate methods to evaluate the prevalence of implicit interactions within a system design that can make security-by-design more accessible and widely adopted for more secure and resilient cyber-physical systems. © 2024 IEEE.

关键词： Dechlorination

来源：评论

学校读者我要写书评

暂无评论

Dynamic Audio-Visual Speech Enhancement using Recurrent Variational Autoencoders

Dynamic Audio-Visual Speech Enhancement using Recurrent Vari...

引用

International Workshop on Acoustic Signal Enhancement (IWAENC)

作者： Z. Foroushi R. M. Dansereau Department of Systems & Computer Engineering Carleton University Canada

ISBN: (数字)9798350361858

ISBN: (纸本)9798350361865

Audio-visual speech enhancement (AVSE) has emerged as a promising approach to enhance speech perception in noisy environments by leveraging both auditory and visual cues present in speech signals. We propose an audio-visual recurrent variational autoencoder (AV-RVAE) for speech enhancement. This model incorporates visual lip motion along with audio to improve speech quality. We extend the RVAE model, which has shown superior performance in audio-only speech enhancement, to handle audio-visual data. Our approach uses both a dedicated video encoder for visual feature extraction and a recurrent neural network (RNN) for temporal modeling. Additionally, we introduce both causal and non-causal variants of AV-RVAE to capture temporal dynamics of speech data. Experimental results on the NTCD-TIMIT dataset show that AV-RVAE outperforms existing methods, showing improvements in scale-invariant signal-to-distortion ratio (SISDR), perceptual evaluation of speech quality (PESQ), and short-term objective intelligibility (STOI) metrics.

关键词： Visualization Recurrent neural networks Lips Conferences Speech enhancement Feature extraction Acoustics Data models Noise measurement Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

A Parallel Processing Approach for Video Data Filtering Using NLP and Object Detection

A Parallel Processing Approach for Video Data Filtering Usin...

引用

IEEE/ACM International Symposium on Big Data Computing (BDC)

作者： Arshdeep Kaur Shikharesh Majumdar Department of Systems and Computer Engineering Carleton University Ottawa

ISBN: (数字)9798350367300

ISBN: (纸本)9798350367317

In scenarios where users need to extract specific information from large video datasets, an efficient system is essential to filter the relevant segments. This helps in enhancing the overall search and retrieval experience. This paper presents a technique designed to manage large volumes of video data by efficiently identifying and extracting user-preferred content based on user defined criteria. The proposed system uses Natural Language Processing (NLP) to filter audio content and machine learning-based object detection to filter video content. This enables precise extraction based on both spoken dialogue and visual elements. The proposed system also addresses the challenge of time delays associated with analyzing large video datasets by employing advanced filtering methods that utilize parallel processing. This approach reduces the data volume thereby shortening the time required for users to locate specific information. The performance of the technique was assessed through a series of experiments conducted on a large video dataset. The experimental results demonstrate the effectiveness of the system in improving search efficiency within huge volumes of video data.

关键词： Visualization computer vision Delay effects Object detection Machine learning Parallel processing Big Data Information filters Natural language processing Data mining

来源：评论

学校读者我要写书评

暂无评论

Enhanced Phonocardiogram Classification Performance through Outlier Detection

Enhanced Phonocardiogram Classification Performance through ...

引用

IEEE International Workshop on Medical Measurement and Applications (MEMEA)

作者： Ebrahim A. Nehary Sreeraman Rajan Systems and Computer Engineering Carleton University Ottawa Canada

ISBN: (数字)9798350307993

ISBN: (纸本)9798350308006

Deep learning has been utilized in binary classi-fication of phonocardiogram (PCG) signals. Current learning techniques, segment PCG records into cycles for training. As the cycles are unlabelled, the cycle labels are inherited from the record labels, leading to wrong labelling of some of the abnormal cycles. Moreover, the heterogeneity within the training dataset arising from the use of different sensors, location of data acquisition, and different pathology further negatively impact the learning and subsequently the binary classification of the record as either normal or abnormal. Therefore, this work proposes a novel individual record-based method, instead of the whole dataset-based method to mitigate mislabelling of abnormal cycles during the training process and to simultaneously addressing heterogeneity in the dataset. Specifically, each abnormal PCG record undergoes individual outlier detection (due to hetero-geneity), enabling the detection and removal of outlier cycles before the PCG record is utilized for training. Thus, training is conducted using properly labelled abnormal and normal cycles. Comprehensive evaluations comparing with baseline methods across various data subsets is carried out. A range of performance metrics is considered to evaluate the proposed method. Results emphasize the effectiveness of integrating outlier detection into the proposed methodology, thereby significantly enhancing the accuracy of PCG classification.

关键词： Training Measurement Heart Deep learning Pathology Data acquisition Sensors

来源：评论

学校读者我要写书评

暂无评论

Towards Intelligent Intent-based Network Slicing for IoT systems: Enabling Technologies, Challenges, and Vision

引用

IEEE Transactions on Network and Service Management 2025年

作者： Hussein, Dana Haj Ibnkahla, Mohamed Carleton University Department of Systems and Computer Engineering OttawaON Canada

The rapid integration of intelligence and automation into future Internet of Things (IoT) systems, empowered by Intent-based Networking (IBN) and Network Slicing (NS) technologies, is transforming the way novel services are envisioned and delivered. The automation capabilities of IBN depend significantly on key facilitators, including data management and resource management. A robust data management methodology is essential for leveraging large-scale data, encompassing service-specific and network-specific data, enabling IBN systems to extract insights and facilitate real-time decision-making. Another critical enabler involves deploying intent-based mechanisms within an NS system that translate and ensure user intents by mapping them to precise Management and Orchestration (MO) commands. Nevertheless, data management in IoT systems faces significant security and operational challenges due to the diverse range of services and technologies involved. Furthermore, intent-based resource management demands intelligent proactive, and adaptive MO mechanisms that can fulfill a wide range of intent requirements. Existing surveys within the field have focused on technology-specific advancements, often overlooking these challenges. In response, this paper defines Intelligent Intent-Based Network Slicing (I-IBNS) systems exemplifying the integration of intelligent IBN and NS for the MO of IoT systems. Furthermore, the paper surveys I-IBNS systems, focusing on two critical domains: resource management and data management. The resource management segment examines recent developments in IBN mechanisms within an NS system. Meanwhile, the second segment explores data management complexities within IoT networks. Moreover, the paper envisions the roles of intent, NS, and the IoT ecosystem, thereby laying the foundation for future research directions. © 2004-2012 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Methods for Transferring Data from a Compute to a Storage Cloud 9

Methods for Transferring Data from a Compute to a Storage Cl...

引用

9th International Conference on Future Internet of Things and Cloud, FiCloud 2022

作者： Contreras, Juan Pablo Majumdar, Shikharesh El-Haraki, Ali Carleton University Systems and Computer Engineering Ottawa Canada Telus Ottawa Canada

ISBN: (数字)9781665493505

ISBN: (纸本)9781665493505

This research, done in collaboration with our industrial partner TELUS, concerns systems that use different platforms for the compute and storage infrastructures thus requiring data transfers between the two platforms. This paper focuses on four different data transfer techniques and analyzes their performance. An architectural framework and a proof-of-concept prototype are described and the analysis of the performance of the data transfer techniques are presented. The performance results described in this paper provide insights into system behavior and the performance of the different data transfer techniques. © 2022 IEEE.

关键词： Data transfer

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：