Advanced Persistent Threats (APTs) have been a major challenge in securing both Information Technology (IT) and Operational Technology (OT) systems. APT is a sophisticated attack that masquerade their actions to navig...
详细信息
ISBN:
(纸本)9798350311259
Advanced Persistent Threats (APTs) have been a major challenge in securing both Information Technology (IT) and Operational Technology (OT) systems. APT is a sophisticated attack that masquerade their actions to navigates around defenses, breach networks, often, over multiple network hosts and evades detection. It also uses "low-and-slow" approach over a long period of time. Resource availability, integrity, and confidentiality of the operational cyber-physical systems (CPS) state and control is highly impacted by the safety and security measures in place. A framework multi-stage detection approach termed "APT(DASAC)" to detect different tactics, techniques, and procedures (TTPs) used during various APT steps is proposed. Implementation was carried out in three stages: (i) data input and probing layer - this involves data gathering and pre-processing, (ii) dataanalysis layer;applies the core process of "APT(DASAC)" to learn the behaviour of attack steps from the sequence data, correlate and link the related output and, (iii) Decision layer;the ensemble probability approach is utilized to integrate the output and make attack prediction. The framework was validated with three different datasets and three case studies. The proposed approach achieved a significant attacks detection capability of 86.36% with loss as 0.32%, demonstrating that attack detection techniques applied that performed well in one domain may not yield the same good result in another domain. This suggests that robustness and resilience of operational systems state to withstand attack and maintain system performance are regulated by the safety and security measures in place, which is specific to the system in question.
The proceedings contain 94 papers. The topics discussed include: development of deep learning model base on modified CNN architectures for brain tumors early diagnosis;metaverse-based learning media to increase wirele...
ISBN:
(纸本)9798350327762
The proceedings contain 94 papers. The topics discussed include: development of deep learning model base on modified CNN architectures for brain tumors early diagnosis;metaverse-based learning media to increase wireless security awareness;comparative study of maximum-power-point tracking with multiplier-based step-size variation;IoT based AC electric vehicle supply equipment;the usage of machine learning on penetration testing automation;implementation of design conformance measurement process between data entry form and class on SRS penguin;computer vision for determining trajectory and impact position of fighter-aircraft bombing;and sentiment analysis and topic modeling of e-grocery application reviews using naive bayes and support vector machine: a case study of Segari data review on the google play store.
In this study, we present a software solution (toolkit) for intelligent dataanalysis obtained using the selective laser melting (SLM) technology. We have developed a program that uses data Science approaches and mach...
详细信息
In the EU, the building sector significantly impacts energy consumption and greenhouse gas emissions, accounting for 40% of the total energy use and 35% of emissions, mainly due to the energy inefficiency of the build...
详细信息
In the EU, the building sector significantly impacts energy consumption and greenhouse gas emissions, accounting for 40% of the total energy use and 35% of emissions, mainly due to the energy inefficiency of the building stock. With energy demand expected to increase over the next decade, improving building energy efficiency is essential for meeting EU sustainability goals. Building Energy Models (BEMs) are crucial for evaluating and enhancing building performance throughout their lifecycle. However, a notable "energy performance gap" usually exists between predicted and actual energy use, exacerbated by challenges in accurately inputting numerous variables and the simplifications inherent in modeling. BEM calibration (BC) approaches are often adopted to reduce these discrepancies, aimed at adjusting model inputs to match output with the observed data. Yet, there is not a universal consensus on which is the best calibration method, with manual and automated approaches offering different benefits. Automated methods, especially those using optimization algorithms, have gained prominence for their efficiency and ability to handle uncertainties. However, BC still significantly depends on the energy modelers' expertise. This paper introduces a novel software tool for automated BC, aiming to simplify the process by integrating expert knowledge, sensitivity analysis, and optimization algorithms techniques in a unique workflow. This tool reduces the dependence of BC success on modeler expertise, representing a significant step towards more accessible automated BC in the research field and engineering practice, thence allowing a more effective design of energy conservation measures.
The proceedings contain 356 papers. The topics discussed include: demonstration of dual-junction ELO solar cells with strain-balanced and lattice-matched quantum well absorbers;silicon heterojunction cell metallizatio...
ISBN:
(纸本)9781665460590
The proceedings contain 356 papers. The topics discussed include: demonstration of dual-junction ELO solar cells with strain-balanced and lattice-matched quantum well absorbers;silicon heterojunction cell metallization with reactive silver inks: printing process, ink formula, and interconnection;performance of vertical bifacial 2T and 3T perovskite/silicon tandem solar farms;nanostructure analysis of parasitic oxides and contact resisitivity degradation during annealing of silicon heterojunction solar cells;multiple-reuse of Ge substrates: towards cost-effective and sustainable III-V solar cells fabrication;accelerating cycles of learning for silicon heterojunction architectures: experimental design and data-driven degradation pathway prediction;improving PbS colloidal quantum dot solar cell performance via solution-phase engineering;and modeling transposition for single-axis trackers using terrain-aware backtracking strategies.
The study of dynamic systems often assumes building a model based on numerical data describing the system’s behavior, i.e., its identification. This problem is relevant, since it is impossible to study properties of ...
详细信息
ISBN:
(数字)9798350365689
ISBN:
(纸本)9798350365696
The study of dynamic systems often assumes building a model based on numerical data describing the system’s behavior, i.e., its identification. This problem is relevant, since it is impossible to study properties of a real object, make predictions and select correct control without an adequate mathematical model. The representation of the object’s model in a symbolic form as differential equations or their systems is the most common and convenient for further application. The paper examines the efficiency of the evolutionary approach to the structural-parametric identification on test problems, the problem of modeling the longitudinal perturbed motion of an aircraft and the problem of modeling the viscous fluid movement when heated it from below.
Multivariate statistical analysis has been widely used in data-driven process monitoring and fault detection. However, the nonlinear and dynamic characteristics of industrial processdata bring significant challenges ...
详细信息
Multivariate statistical analysis has been widely used in data-driven process monitoring and fault detection. However, the nonlinear and dynamic characteristics of industrial processdata bring significant challenges to applying the method. In addition, the selection of hyperparameters has a significant impact on the monitoring results, but the selection process is tedious and random. For these reasons, an adaptive threshold strategy for nonlinear dynamic process monitoring based on genetic optimization is proposed in this paper. The proposed approach has two main contributions. Firstly, a research scheme combining kernel principal component analysis with adaptive threshold is proposed to handle industrial processes' nonlinear and dynamic characteristics. Then, the genetic algorithm selects the optimal hyperparameters for online process monitoring, which avoids the blindness of hyperparameters selection. The proposed strategy is tested by the Tennessee Eastman processdataset The research results show that this method effectively reduces the false alarm rate and missed detection rate of process monitoring. Copyright (C) 2022 The Authors.
Distributed data stream processing systems (DSPSs) such as Storm, Flink, and Spark Streaming are now routinely used to process continuous data streams in (near) real-time. However, achieving the low latency and high t...
详细信息
ISBN:
(数字)9781665408837
ISBN:
(纸本)9781665408837
Distributed data stream processing systems (DSPSs) such as Storm, Flink, and Spark Streaming are now routinely used to process continuous data streams in (near) real-time. However, achieving the low latency and high throughput demanded by today's streaming applications can be a daunting task, especially since the performance of DSPSs highly depends on a large number of system parameters that control load balancing, degree of parallelism, buffer sizes, and various other aspects of system execution. This tutorial offers a comprehensive review of the state-of-the-art automatic performance tuning approaches that have been proposed in recent years. The approaches are organized into five main categories based on their methodologies and features: cost modeling, simulation-based, experiment-driven, machine learning, and adaptive tuning. The categories of approaches will be analyzed in depth and compared to each other, exposing their various strengths and weaknesses. Finally, we will identify several open research problems and challenges related to automatic performance tuning for DSPSs.
With the rapid development of integrated energy system (IES), it is crucial to model subsystems and key equipment at different levels to meet the needs of characteristic analysis, planning and design, and operation co...
详细信息
ISBN:
(数字)9798350359558
ISBN:
(纸本)9798350359565
With the rapid development of integrated energy system (IES), it is crucial to model subsystems and key equipment at different levels to meet the needs of characteristic analysis, planning and design, and operation control. In this paper, a modeling method for the underlying equipment in an IES is proposed. The core of the method is the fusion of convolutional neural network (CNN) and Gated Recurrent Unit (GRU). On this basis, the physical model of the equipment is used to guide the modeling and avoid the physical inconsistency. Finally, the experimental data of the vortex expander are collected through the miniature compressed air energy storage system to verify the accuracy and practicability of the proposed method.
It is essential to achieve real-time fault detection of the industrial process to reduce the occurrence of accidents during the industrial process. However, there are some problems in the actual monitoring process, su...
详细信息
暂无评论