The proceedings contain 110 papers. The topics discussed include: review of machine learning models in cyberbullying detection problem;quantum computing in the object-oriented model of quality management;regression an...
ISBN:
(纸本)9798350374865
The proceedings contain 110 papers. The topics discussed include: review of machine learning models in cyberbullying detection problem;quantum computing in the object-oriented model of quality management;regression and machine learning methods for predicting human movements based on skeletal data;application of game theory methods to optimize the stakeholder management process;conceptualizing the ICT project management in the sustainability context;human-computer testing of students’ knowledge;fuzzy inference system for test case prioritization in software testing;mobile application of convolutional neural networks for melanoma classification;an investigation of sensing and technologies for supporting the intelligent transport management system in urban area;and a comparative study of supervised machine learning and deep learning techniques with feature selection methods for classifying Parkinson’s disease based on speech impairments.
Federated learning (FL) is a distributed learning method that reduces data transmission and privacy risks. However, the existence of a central server may become a target of attackers, resulting in an increased risk of...
详细信息
This article introduces a bio-inspired 3D flocking algorithm for a drone swarm, built upon a previously established 2D model, which has proven to be effective in promoting stability, alignment, and distance variation ...
详细信息
ISBN:
(纸本)9781665491907
This article introduces a bio-inspired 3D flocking algorithm for a drone swarm, built upon a previously established 2D model, which has proven to be effective in promoting stability, alignment, and distance variation between agents within large groups of agents. The study highlights how the incorporation of a vertical interaction between agents and the acquisition by each agent of a minimal amount of information about their most influential neighbor impacts the collective behavior of the swarm. Additionally, we present a comprehensive investigation of the impacts of the intensity of alignment and attraction interactions on the collective motion patterns that emerge at the group level. These results, mostly conducted in a validated simulator, have significant implications for designing efficient UAV swarm systems and using collective patterns, or phases, in operational contexts such as corridor tracking, surveillance, and exploration. Further research will explore the effectiveness and efficiency of this UAV swarm flocking algorithm, as well as its ability to ensure safe transitions between collective phases in different operational contexts.
The Hiperwalk package is designed to facilitate the simulation of quantum walks using heterogeneous high-performance computing, taking advantage of the parallel processing power of diverse processors such as CPUs, GPU...
详细信息
The rapid proliferation of mobile devices has dramatically increased energy consumption, presenting significant challenges for sustainability. Traditional energy-saving techniques often lack adaptability and fail to a...
详细信息
The Contemporary IoT implementations rely on cloud computing for data storage, encountering challenges such as suboptimal data processing performance and a diminished fault tolerance rate. In response, this research i...
详细信息
The emergence of edge computing helps to address issues such as transmission latency, bandwidth, and privacy. Operational Technology (OT) systems require high costs to maintain the continuous operation of devices and ...
详细信息
ISBN:
(纸本)9781665477260
The emergence of edge computing helps to address issues such as transmission latency, bandwidth, and privacy. Operational Technology (OT) systems require high costs to maintain the continuous operation of devices and generate large amounts of data. Combined with edge computing, the operational efficiency and data processing capability of OT systems can be improved. However, edge computing can also pose significant risks to OT systems. Many attackers are beginning to target OT systems, and attacks against industrial control systems have been growing these years. This paper focuses on protocol security, anomaly intrusion detection, and honeypot defense in industrial control systems (ICS). We propose an OTEC security framework that combines OT systems and edge computing to address these issues. The framework consists of three main vital functions: protocol improvement (enhancing the security of Modbus protocol), intrusion detection (detecting anomalous data from the system), and proactive defense (deploying honeypots). We verified the effectiveness of OTEC through simulation experiments. The results show that our framework enhances the Modbus protocol's security and guarantees the protocol's availability, integrity, and confidentiality. The intrusion detection module uses deep learning algorithms and can reach 94% detection accuracy. The honeynet we deployed recorded the attack behaviour of attackers from different regions, which can provide good training data for the intrusion detection module.
With the development of the socio-economy, the real estate industry has grown rapidly worldwide. Housing prices, as an important indicator for measuring a city's economic development level, have significant impact...
详细信息
Electronic Health Record (EHR) provides critical medical data. Sharing EHRs can add services and value for hospitals and patients and effectively improve medical services' quality. In the process of cross-hospital...
详细信息
Recently, research communities highlight the necessity of formulating a scalability continuum for large-scale graph processing, which gains the scale-out benefits from distributed graph systems, and the scale-up benef...
详细信息
ISBN:
(数字)9781665408837
ISBN:
(纸本)9781665408837
Recently, research communities highlight the necessity of formulating a scalability continuum for large-scale graph processing, which gains the scale-out benefits from distributed graph systems, and the scale-up benefits from high-performance accelerators. To this end, we propose a middleware, called the GX-plug, for the ease of integrating the merits of both. As a middleware, the GX-plug is versatile in supporting different runtime environments, computation models, and programming models. More, for improving the middleware performance, we study a series of techniques, including pipeline shuffle, synchronization caching and skipping, and workload balancing, for intra, inter-, and beyond-iteration optimizations, respectively. Experiments show that our middleware efficiently plugs accelerators to representative distributed graph systems, e.g., GraphX and Powergraph, with up-to 20x acceleration ratio.
暂无评论