检索结果-内蒙古大学图书馆

9th International Conference on Web Research, ICWR 2023

作者： Heidari, Mohsen Fasahat, Mohamad Ali Afsharian, Sanaz Artishdar, Parinaz Esfarayen University Dept. of Electrical Computer and Industrial Engineering North Khorasan Iran Mehr Alborz Higher Education Institute Dept. of Computer Science Tehran Iran Islamic Azad University Damavand Branch English Department Tehran Iran Islamic Azad University Yadegar Emam Khomeini Branch Dept. of Software Engineering Tehran Iran

ISBN: (纸本)9798350399691

For businesses, discovering key nodes in social networks has a high computational overhead and cost. Because of this, in the problem of influence maximization, at least key nodes with the most influence in social networks are chosen at the lowest possible cost. Numerous algorithms have been proposed to find key nodes in social networks using the technique of influence maximization under the characteristics of submodularity and monotonicity;however, these algorithms struggle with the issue of optimal influence spread because some graph characteristics are ignored when considering diffusion and influence spread in the social network. The HSMD method, which gives special weight to the structure of communities and selects key nodes hierarchically utilizing the structure of communities, has been presented as a solution to this challenge. Based on the characteristics and strategic placement of the nodes within each community, weight is given to each community in this algorithm. Seed nodes are then chosen hierarchically using BFS traversal. This method enhanced the influence spread rate and execution time of recently introduced algorithms such as CTIM, IMBC, RNR, HEDVGreedy, and k-shell. © 2023 IEEE.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Mobile Health Intervention System in Optimizing Healthcare Delivery for Cardiac Patients 5

Mobile Health Intervention System in Optimizing Healthcare D...

引用

5th International Conference on Advancements in Computing, ICAC 2023

作者： Prabashana, R.P.K. Nanayakkara, G.A.J.W. Wanniachchi, W.K.D.C. Arampath, S.B.A.M.B.S. Rajapaksha, Samantha Harshanath, S.M.B. Sri Lanka Institute of Information Technology Dept. of Computer Systems Engineering Malabe Sri Lanka Sri Lanka Institute of Information Technology Dept. of Information Technology Malabe Sri Lanka

ISBN: (纸本)9798350358131

The advent of mobile health (mHealth) technologies has ushered in a new era in healthcare delivery, transforming the way cardiac patients receive medical care and support. This research paper explores the role of a mobile health intervention system in optimizing healthcare delivery for cardiac patients. The prevalence of heart attacks has necessitated innovative solutions to enhance patient outcomes and reduce the burden on healthcare systems. The proposed mHealth intervention system leverages the ubiquity of mobile devices to provide real-time monitoring, personalized interventions with environment prediction, and seamless communication between patients and healthcare providers. Through a comprehensive review of existing literature and empirical studies, this paper examines the impact of the mHealth intervention system on patient engagement, adherence to treatment plans, early detection of cardiac events, and overall quality of care. The integration of wearable device, CardioCare mobile application, and telemedicine platforms creates a holistic approach to cardiac care, empowering patients to actively participate in their health management and enabling healthcare professionals to make informed decisions. The potential benefits, challenges, and ethical considerations surrounding the implementation of this system are discussed. © 2023 IEEE.

关键词： Wearable technology

来源：评论

学校读者我要写书评

暂无评论

AASH: A Lightweight and Efficient Static IoT Malware Detection Technique at Source Code Level 3

AASH: A Lightweight and Efficient Static IoT Malware Detecti...

引用

3rd Asia Conference on computers and Communications, ACCC 2022

作者： Glani, Yasir Ping, Luo Shah, Syed Asad Software School Tsinghua University Beijing China Dept. of Computer Engineering Bilkent University Ankara Turkey

ISBN: (纸本)9798350332957

IoT malware applications significantly threaten user privacy and security. Traditionally, IoT developers have focused primarily on hardware, but connectivity requires additional embedded software, usually developed by third-party developers. Unfortunately, third-party code is not always secure and trustworthy, and it frequently contains bugs and malicious code, which leaves IoT devices vulnerable. We propose the AASH technique (IoT Malware Detection) a novel technique that can detect malware at the source code level using the Adler-32 hash function and Fibonacci search. Previously, DROIDMD technique and SQVDT technique have been proposed to detect malware on Android and Linux devices. According to the authors, their schemes are scalable and can be deployed on IoT devices. However, their technique suffers from lower accuracy and takes longer to detect malicious code. The performance measurement shows that our proposed AASH technique is comparatively better than DROIDMD and SQVDT techniques in terms of accuracy and malware detection. AASH is reliable, efficient, and can be deployed on a large-scale level. © 2022 IEEE.

关键词： Malware

来源：评论

学校读者我要写书评

暂无评论

Autonomous Social Amenity, Pothole Detection and Reporting

Autonomous Social Amenity, Pothole Detection and Reporting

引用

International Multidisciplinary Information Technology and engineering Conference (IMITEC)

作者： David Mosela Moses Olaifa Pius Owolawi Vusi Malele Dept. Computer Systems Engineering Tshwane University of Technology Tshwane South Africa Dept. of Computer Systems Engineering Tshwane University of Technology Tshwane South Africa

ISBN: (数字)9798350387988

ISBN: (纸本)9798350387995

Challenges faced by traffic management in many developing nations across the globe is a result of the poor quality of road infrastructure. Inadequate and defective road infrastructure are major contributors to this effect. A key element that poses significant risk to road safety and that leads to increased road management cost is the increasing number of potholes and inefficient detection and reporting approach. This study provides an in-dept. exploration of the latest developments in pothole detection systems and examines various methodologies and technologies used in these systems, emphasizing the importance of real-time monitoring for proactive road maintenance. In addition, we proposed a system that addresses the persistent challenge of road infrastructure degradation by adopting cutting-edge technologies, including computer vision, machine learning, and sensor networks (such as ultrasonic and GPIO systems) that are used to identify and assess potholes on road surfaces. To achieve the aim of the study, the system adopts the use of RasberryPi 4 Model B for pothole detection and YOLOv4 for image processing.

关键词： YOLO computer vision Roads Computational modeling Machine learning Hardware Acoustics Road safety software tools Surface treatment

来源：评论

学校读者我要写书评

暂无评论

Ossintegrity: Collaborative Open Source Code Integrity Verification

SSRN

引用

SSRN 2024年

作者： Nahum, Mor Grolman, Edita Maimon, Inbar Mimran, Dudu Elyashar, Aviad Brodt, Oleg Elovici, Yuval Shabtai, Asaf Dept. of Software and Information Systems Engineering Ben-Gurion University of the Negev Israel

Open-source software (OSS) libraries have become popular among developers due to their ability to reduce development time and costs. However, OSS can also be exploited and used as a means of conducting OSS supply chain attacks. In OSS attacks, malicious code is injected into libraries that the target is using. Previous studies have proposed various methods for preventing and detecting such attacks, however most of them focused on untargeted attacks. In contrast, this paper focuses on targeted OSS supply chain attacks which are performed by skilled and persistent attackers with strong technical aptitude. Targeted OSS attacks are crafted towards a specific target (i.e., developer). Since these attacks do not appear in the general OSS repositories, they tend to go under the radar for a long period of time allowing an attacker to gain access to sensitive data or systems. In this paper, we propose (SC)2V – secure crowdsource-based code verification, a novel distributed and scalable framework for verifying OSS libraries. (SC)2V is aimed at preventing targeted supply chain attacks and is integrated with the build phase of software production, serving as an additional code verification step before packaging the application and deploying it. (SC)2V involves both users (developers seeking to verify an OSS library) and verifiers contributing to the collaborative verification effort. (SC)2V considers a library as verified and safe when a consensus is reached among verifiers. We evaluated the proposed method using eight different attack scenarios (including cold start and edge cases), on around 900 popular OSS libraries and their dependencies, each of which included an average of 10 files and was verified by at least five participants;a total of 127,000 files were evaluated, and the results indicate that it took our framework an average of just 26 seconds to issue an alert against the attacks. © 2024, The Authors. All rights reserved.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Neural Network-Based Analysis of Forest Fire Aftermath in Class-Imbalanced Remote Sensing Earth Image Classification

Neural Network-Based Analysis of Forest Fire Aftermath in Cl...

引用

2024 Symposium on Beyond the Canopy: Technologies and Applications of Remote Sensing

作者： Hnatushenko, Viktoriia Hnatushenko, Volodymyr Soldatenko, Dmytro Dept. Information Technologies and Systems Ukrainian State University of Science and Technologies Dnipro Ukraine Dept. Information Technologies and Computer Engineering Dnipro University of Technology Dnipro Ukraine Institute of Photogrammetry and GeoInformation Leibniz Universität Hannover Germany

Today's agricultural sector is characterized by an important role of accurate mapping and monitoring of agriculture with the help of satellite imagery, which allows to optimize the use of resources, to plan crop areas and to forecast productivity. Classification of satellite images with unbalanced sample distribution is a critical problem in this regard. Traditional machine learning algorithms in particular have limitations in dealing with sample imbalance. In this paper, we proposed convolution neural networks for semantic segmentation, where sample imbalance is considered based on a particular loss function coupled with data augmentation. To illustrate our method, we use Sentinel-2 remote sensing (RS) images covering a number of regions in Ukraine, and then we create an image dataset of the region and for training and testing make data augmentation. The models with different architectural features were investigated. The results demonstrate that the proposed CNN has a higher classification accuracy than the ones discussed in the paper: the classification accuracy on the test dataset reached 96.7% with intersection-over-union values of up to 89.7%. This opens the way for further research in the direction of refining algorithms for classify satellite data with an imbalanced class structure. © Author(s) 2024.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Unconventional Computing based on Four Wave Mixing in Highly Nonlinear Media

Unconventional Computing based on Four Wave Mixing in Highly...

引用

2023 Conference on Lasers and Electro-Optics Europe and European Quantum Electronics Conference, CLEO/Europe-EQEC 2023

作者： Sozos, Kostas Deligiannidis, Stavros Mesaritakis, Charis Bogris, Adonis University of West Attica Dept. of Informatics and Computer Engineering. Aghiou Spiridonos Egaleo Athens12243 Greece University of the Aegean Dept. of Information and Communication Systems Engineering Palama 2 Karlovassi Samos83200 Greece

ISBN: (纸本)9798350345995

Nowadays, photonic analog computing in the form of neuromorphic photonics or photonic neural networks has resulted in powerful hardware platforms that accelerate difficult tasks with marginal power consumption. Although linear transformations are efficiently carried out in the optical domain, nonlinear transformations are also of paramount importance. Here, we propose four wave mixing (FWM) process as an elegant solution for the generation of diverse nonlinear higher order products of an original signal. On one hand, these products can act as activation functions in different types of neural networks, either recurrent neural networks (RNNs) and reservoir computers or in any other type of brain-inspired frameworks. On the other hand, the same products can form the basis for polynomial regression which is a very powerful technique used in machine learning in different tasks i.e. for the prediction of COVID-19 transmission [1]. © 2023 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

A Multicore Implementation of an AUTOSAR-based XCP Module 12

A Multicore Implementation of an AUTOSAR-based XCP Module

引用

12th Mediterranean Conference on Embedded Computing, MECO 2023

作者： Osama, Mahmoud Hammad, Sherif Elhady, Nancy E. El-Kharashi, M. Watheq Ain Shams University Faculty of Engineering Dept. of Computer & Systems Eng. Cairo Egypt Garraio CEO Cairo Egypt Ain Shams University Faculty of Engineering Dept. of Mechatronics Eng. Cairo Egypt

ISBN: (纸本)9798350322910

The automotive industry depends on computers to control and monitor vehicles behaviour. The Universal Measurement and Calibration Protocol (XCP) connects calibration systems to electronic control units (ECUs). Nowadays, AUTOSAR-based XCP for single core ECUs is widely used in automotive industry. As the demand for computing power is rapidly increasing in the automotive domain, car manufacturers are gradually introducing multi-core ECUs in their electronic architectures. Multi-core ECUs provide high level of parallelism. This research work aims to deliver a multi-core implementation of an AUTOSAR-based XCP module, as it is important to have an efficient process of measurement and calibration on multi-core targets. The paper results are ensuring data consistency on the application level, avoiding race conditions between writer core and reader core which might result in processing rubbish data, and decreasing data dependency between cores. © 2023 IEEE.

关键词： Automotive industry

来源：评论

学校读者我要写书评

暂无评论

Distributionally Robust Reinforcement Learning with Human Feedback

arXiv

引用

arXiv 2025年

作者： Mandal, Debmalya Sasnauskas, Paulius Radanović, Goran Dept. of Computer Science University of Warwick United Kingdom Max-Planck Institute for Software Systems Germany

Reinforcement learning from human feedback (RLHF) has evolved to be one of the main methods for fine-tuning large language models (LLMs). However, existing RLHF methods are non-robust, and their performance deteriorates if the downstream task differs significantly from the preference dataset used in fine-tuning. In order to mitigate this problem, we introduce a distributionally robust RLHF for fine-tuning LLMs. In particular, our goal is to ensure that a fine-tuned model retains its performance even when the distribution of prompts significantly differs from the distribution encountered during fine-tuning. We formulate distributionally robust optimization (DRO) version of two popular fine-tuning methods – (1) reward-based RLHF and (2) reward-free DPO (direct preference optimization). We propose a minibatch gradient descent based algorithms for both of them, and theoretically prove convergence guarantees for the algorithms. Subsequently, we evaluate our algorithms on an out-of-distribution (OOD) task by first training the model on the Unified-Feedback dataset and evaluating its performance on two different datasets. The experimental results show that our robust training improves the accuracy of the learned reward models on average, and markedly on some tasks, such as reasoning. Furthermore, we show that the robust versions of policy optimization methods, similarly improve performance on OOD tasks. © 2025, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Stealthy Attack Detection of controlled ramp meters in freeway networks 63

Stealthy Attack Detection of controlled ramp meters in freew...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Menelaou, Charalambos Zhang, Kangkang Timotheou, Stelios Panayiotou, Christos G. Parisini, Thomas University of Cyprus Kios CoE Dept. of Electrical and Computer Engineering Cyprus Imperial College London Dept. of Electrical and Electronic Engineering LondonSW7 2AZ United Kingdom Aalborg University Department of Electronic Systems Denmark University of Trieste Department of Engineering and Architecture Italy

ISBN: (纸本)9798350316339

The increasing reliance on intelligent transportation systems (ITS) for traffic management has simultaneously heightened the potential for cybersecurity threats. Malicious cyber attacks on such systems can lead to operational inefficiencies, heightened congestion, and compromised safety. This work introduces a stealthy integrity attack tailored for ramp metered freeway systems. The attack model is conceptualized as a closed-loop dynamical system, formulated as an optimization problem based on the Cell Transmission Model. This work further proposes a distributed detection mechanism designed to identify attack residuals, which, by incorporating an adaptive threshold scheme, can detect the presence of an attack. To demonstrate the efficacy of our detection scheme, we present a scenario illustrating its application in freeway road networks. © 2024 IEEE.

关键词： Cyber attacks

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：