检索结果-内蒙古大学图书馆

Intelligent and Autonomous Edge Slicing for IoT systems

IEEE Internet of Things Journal 2025年第12期12卷 21210-21224页

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

Edge intelligence is rapidly emerging as a pivotal platform for supporting future IoT networks. The integration of Artificial Intelligence and Machine Learning (AI/ML) with edge computing furnishes a new era in which edge systems can learn environment dynamics and optimize resource autoscaling policies. However, the heterogeneity of IoT networks, characterized by diverse applications and requirements, necessitates edge systems with advanced intelligence to tailor resource autoscaling policies to specific environments. Despite ongoing research in edge intelligence, most studies have focused on a single environment or service type, thereby limiting their applicability to real-world scenarios with varied IoT services. To address this limitation, we propose the Intelligent and Autonomous Edge Slicing (IAES) system, a novel approach designed to recognize diverse IoT environments and implement per-slice resource allocation policies. IAES leverages Deep Reinforcement Learning (DRL), namely, Dueling Double Deep Q-Networks (D3QN), to optimize resource autoscaling across distinct IoT environments, such as smart cities, eHealth, and smart factories. Additionally, IAES incorporates an intelligent environment classification component that utilizes joint traffic prediction and classification models. Several AI algorithms such as Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), and Multi-Layer Perceptron Networks (MLP), are evaluated for their efficacy in predicting IoT environments. Simulation experiments demonstrate that the IAES system achieves a 50-60% reduction in system costs compared to both rule-based commercial autoscaling employed in Kubernetes systems and an intelligent prediction-based autoscaling algorithm. © 2014 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Thermography-based Breast Abnormality Detection using Pre-Trained RadImageNet Models

Thermography-based Breast Abnormality Detection using Pre-Tr...

引用

2024 International Symposium on Sensing and Instrumentation in 5G and IoT Era, ISSI 2024

作者： Sheikh, Huda Dey, Ankita Rajan, Sreeraman Carleton University Systems and Computer Engineering Ottawa Canada

ISBN: (纸本)9798350378689

With breast cancer accounting for a large number of cancer-related deaths worldwide, there exists a need to develop tools and imaging modalities that aid in the early detection of breast abnormalities. While mammography is considered the standard imaging modality for breast cancer diagnosis, it cannot be used on pregnant women and is not as effective with denser breasts. Thermography, which is a non-invasive and radiation-free technique, is an adjunct tool to help detect breast abnormalities. Various pre-trained models have been applied to breast thermograms in the literature to detect breast abnormalities. This is a preliminary study that explores the use of pre-trained models trained on a medically sourced database like RadImageNet, in the analysis of breast thermograms from the Database for Mastology Research (DMR). Models trained from medically-sourced databases like RadImageNet have been known to extract features and patterns more relevant for medical imaging analysis and classification. In this study, the performances of RadImageNet models were compared with models trained on non-medically sourced databases, like ImageNet. Preliminary findings suggest that ImageNet models outperform their equivalent RadImageNet models. This preliminary study emphasizes the importance of using relevant and targeted datasets for the development of models that aid in breast abnormality detection. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Comparison of Different Color Spaces for Abnormality Detection in Breast Thermograms

Comparison of Different Color Spaces for Abnormality Detecti...

引用

2024 IEEE International Conference on Consumer Electronics, ICCE 2024

作者： Dey, Ankita Rajan, Sreeraman Carleton University Systems and Computer Engineering Ottawa Canada

ISBN: (纸本)9798350324136

Breast cancer is one of the most diagnosed cancers in women worldwide. Thermography serves as a potential screening modality for early breast abnormality detection. A breast thermogram is a pseudo-colored RGB image that is obtained using a thermal palette. Different types of thermal palettes can be used for pseudo-coloring breast thermograms and may influence abnormality detection in RGB breast thermograms. Universal color spaces/ color models that are derived from RGB color space can be used to mitigate the influence of the choice of different thermal palettes. In this work, RGB breast thermograms are mapped to five different color spaces (namely YIQ color space, YCbCr color space, XYZ color space, LAB color space, and HSV color space). The performance of an existing novel, non-learning, threshold-based breast abnormality detection methodology using these mapped thermograms is investigated. An exhaustive channel-wise analysis of different color spaces is also explored to study the influence of each color space channel on breast abnormality detection. © 2024 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Formal Metamodel for Software Architectures with Composite Components 12th

A Formal Metamodel for Software Architectures with Composi...

引用

12th International Conference on Model and Data engineering, MEDI 2023

作者： Baak, James Rouland, Quentin Jaskolka, Jason Systems and Computer Engineering Carleton University OttawaON Canada

ISBN: (纸本)9783031493324

Formal component-based modeling has been shown to be invaluable for verifying the compatibility of specified components, discovering flaws early in design stages, and enabling the reuse of components, across multiple projects and teams. However, complex system specifications are large and difficult to reason with which has limited the adoption of formal approaches. In this paper, we use a formal language to build a metamodel to represent software architectures consisting of composite components. First, we propose a metamodel to describe the high-level concepts of software architectures in a component-port-connector fashion. We focus on providing hierarchical modeling capabilities by considering the construction of composite components from existing ones. Second, using Alloy as a tooled formal language, we formalize the metamodel concepts to build a reusable framework for modeling complex systems consisting of composite component structures that can be automatically constructed and checked for architectural conformance. We use a smart metering system to demonstrate the use our formal metamodel. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Formal languages

来源：评论

学校读者我要写书评

暂无评论

Understanding Defects in Generated Codes by Language Models 34

Understanding Defects in Generated Codes by Language Models

引用

34th Annual International Conference on Collaborative Advances in Software and Computing, CASCON 2024

作者： Esfahani, Ali Mohammadi Kahani, Nafiseh Ajila, Samuel A. Carleton University Systems and Computer Engineering OttawaON Canada

ISBN: (纸本)9798331504830

This study investigates the reliability of code generation by Large Language Models (LLMs), focusing on identifying and analyzing defects in the generated code. Despite the advanced capabilities of LLMs in automating code generation, ensuring the accuracy and functionality of the output remains a significant challenge. By using a structured defect classification method to understand their nature and origins this study categorizes and analyzes 367 identified defects from code snippets generated by LLMs, with a significant proportion being functionality and algorithm errors. These error categories indicate key areas where LLMs frequently fail, underscoring the need for targeted improvements. To enhance the accuracy of code generation, this paper implemented five prompt engineering techniques, including Scratchpad Prompting, Program of Thoughts Prompting, Chain-of-Thought Prompting, Chain of Code Prompting, and Structured Chain-of-Thought Prompting. These techniques were applied to refine the input prompts, aiming to reduce ambiguities and improve the models' accuracy rate. The research findings suggest that precise and structured prompting significantly miti-gates common defects, thereby increasing the reliability of LLM-aenerated code. © 2024 IEEE.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Interaction-Aware Trust Management Scheme for IoT systems With Machine-Learning-Based Attack Detection

引用

IEEE Internet of Things Journal 2025年第11期12卷 17169-17182页

作者： Farhat, Ali Eldosouky, Abdelrahman Ibnkahla, Mohamed Matrawy, Ashraf Carleton University Department of Systems and Computer Engineering OttawaONK1S 5B6 Canada Carleton University School of Information Technology OttawaON Canada

The recent Internet of Things (IoT) adoption has revolutionized various applications while introducing significant security and privacy challenges. Traditional security solutions are unsuitable for IoT systems due to their dynamicity, heterogeneity, and resource constraints. Trust-based solutions are emerging as promising alternatives due to their ability to track the dynamic behavior in IoT systems. However, existing trust management schemes are implemented at the device level, raising several challenges, including device modification, that compromises certification and scalability, increased network overhead, and higher device resource utilization. To address these challenges, this article proposes a novel trust management scheme that shifts its implementation to a higher layer in the IoT system, specifically to the IoT access layer (e.g., gateway). The proposed scheme establishes trust based on typical device interactions with the gateway without requiring additional information from the device. It relies on objective attributes spanning communication, security, and advanced dimensions to compute the trust value of an IoT device. Additionally, an artificial neural network (ANN) is integrated to determine if the device acts maliciously or behaves normally. Simulation results demonstrate a notable improvement in the detection rate, primarily due to incorporating the proposed ANN, compared to the threshold-based approaches in the literature. Overall, the improvements highlight the significant advantage of the proposed scheme’s robustness. © 2014 IEEE.

关键词： Gateways (computer networks)

来源：评论

学校读者我要写书评

暂无评论

DDoS Flood Detection and Mitigation using SDN and Network Ingress Filtering - an Experiment Report 4

DDoS Flood Detection and Mitigation using SDN and Network In...

引用

4th IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2024

作者： Marleau, Sebastien Rahman, Prianna Lung, Chung-Horng Carleton University Department of Systems and Computer Engineering Ottawa Canada

ISBN: (纸本)9798350360721

Distributed Denial of Service (DDoS) attacks are a common security threat to overwhelm a target server. IP source spoofing is a common approach used for DDoS attacks. It is claimed that all large DDoS attacks require IP spoofing and around 20% of the Internet still allows IP spoofing. DDoS attacks can also be launched much more easily using low-cost Internet of Things (IoT) devices. DDoS attacks originating from IoT devices have increased 5-fold in a year. Software-defined networking (SDN) has been proposed as a new paradigm to reduce complexity. However, security issues are still challenging for SDN, as DDoS attacks on the controller could fail the entire network. A mechanism that can detect and mitigate DDoS attacks on SDN is crucial. Ingress filtering has been adopted to reduce the probability of exploiting a network to launch an attack. This, among other things, mandates the dropping of packets if the source IP address of incoming packets is inconsistent with the configured one. Best Current Practice 38 (BCP 38) is a network ingress filtering technique to prevent source IP spoofing. By validating incoming packets, their IP addresses, and possibly other attributes at the ingress devices, it provides a first line of defense against suspicious traffic. We present an approach to DDoS detection and mitigation using BCP 38 and SDN. To evaluate the effectiveness of the proposed approach, a simple method was designed to detect and mitigate DDoS floods using BCP 38 and SDN. Experiments were conducted using Mininet and the Ryu controller. The result demonstrated that the proposed approach corresponded to DDoS attacks with IP spoofing efficiently and effectively. © 2024 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

COVID-19 Classification Using Pre-Trained Models and Disease Severity Score Masks 1

COVID-19 Classification Using Pre-Trained Models and Disease...

引用

1st International Conference on Computing, Internet of Things and Microwave systems, ICCIMS 2024

作者： Nehary, Ebrahim A. Rajan, Sreeraman Rossa, Carlos Carleton University Department of Systems and Computer Engineering Ottawa Canada

ISBN: (纸本)9798350351736

The significance of early detection of COVID-19 has been widely acknowledged as a means of reducing its spread and mortality rates among patients. Deep learning techniques for COVID-19 classification based on ultrasound (US) data have been extensively employed. However, detecting COVID-19 based on US images continues to be challenging primarily due to limited datasets with noisy and low-resolution images. This study investigates methods to enhance classification performance by incorporating disease severity score masks while training pretrained models enhanced with self-attention mechanisms. The disease severity scores range from 0 for healthy lung tissue to 1 for initial signs of abnormality, and 2 and 3 for advanced pathological artifacts. These masks and their corresponding US images are employed as inputs to pre-trained models for feature extraction. Subsequently, features extracted from the masks are utilized to recalibrate features obtained from US images using self-attention mechanisms. The proposed method achieves classification accuracy of 95.4, 90.4, 95%, 83%, and 92% when using pre-trained models VGG16, NASNet-Mobile, MobileNet_V2, ResNet50, and Xception, respectively. Further, all pre-trained models yield a low standard deviation of less than 5%. The results demonstrate that incorporating disease severity masks improves the classification performance, thus offering promising techniques for enhancing COVID-19 detection using ultrasound imaging. © 2024 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Real-Time Data Processing Architectures: Kafka versus MQTT Broker in IoT 4

Comparative Analysis of Real-Time Data Processing Architectu...

引用

4th IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2024

作者： Ho, Chung Lai Deryck Lung, Chung-Horng Mao, Zhengding Carleton University Department of Systems and Computer Engineering Ottawa Canada

ISBN: (纸本)9798350360721

The exponential growth of Internet of Things (IoT) devices highlights the critical need for robust and efficient messaging systems to ensure seamless communication and real-time data exchange. In this research, a thorough comparative analysis was conducted focusing on the real-time data processing architectures of two leading messaging brokers in the IoT domain: Apache Kafka and Message Queuing Telemetry Transport (MQTT) broker. Despite widespread adoption, Kafka and MQTT brokers exhibit uniqueness in their architectures, features, and functionality in real-time data processing scenarios. The study aims to unravel the strengths and weaknesses of each technology within the context of real-time data processing, providing valuable insights to optimize their IoT data workflows. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Event Sourcing in Jason: Event-Driven State Reconstruction for BDI Agents

Event Sourcing in Jason: Event-Driven State Reconstruction f...

引用

2024 IEEE International Conference on Agents, ICA 2024

作者： Davies, Curtis Esfandiari, Babak Carleton University Department of Systems and Computer Engineering Ottawa Canada

ISBN: (纸本)9798331539917

Event sourcing is a software design pattern that uses a log of events as the ground truth for recreating an application's state and for auditing purposes. In the context of agents, event sourcing uses event data captured from an agent's runtime, allowing for complex queries to be made about its behaviour during a mission. We present a proof-of-concept of this insight in the form of an 'agent simulator' for Jason (a BDI agent framework) to replay an agent's decision-making process and reconstruct its state at any given point in time. Through this process, we identify discrepancies between Jason's formal semantics and its Java implementation, leading us to propose revised semantic rules that accurately reflect an agent's reasoning cycle during runtime and provide a foundation for event-based explainability in agent-based systems. © 2024 IEEE.

关键词： Software design

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：