this research examines the optimization of decision tree induction techniques by integrating evolutionary algorithms. It focuses on the Linear geneticprogramming Decision Tree (LGPDT). LGPDT employs a linear program ...
详细信息
ISBN:
(纸本)9798350373981;9798350373974
this research examines the optimization of decision tree induction techniques by integrating evolutionary algorithms. It focuses on the Linear geneticprogramming Decision Tree (LGPDT). LGPDT employs a linear program to encode decision trees, achieving an optimal balance between accuracy and interpretability. the study introduces C-LGPDT as an extension of LGPDT, aiming to enhance its efficiency through correlation-based feature selection. this integration reduces dataset dimensionality and eliminates irrelevant or redundant features, resulting in a more accurate and interpretable decision tree model. the performance of C-LGPDT is thoroughly examined, and it is shown that it consistently outperforms older approaches, especially C4.5, and that it is more robust and accurate. A tourism dataset is also used to evaluate the C-LGPDT's performance, with an emphasis on its stability in recall and precision. Results show that C-LGPDT is effective at solving decision tree induction problems, making it a good candidate for machine learning classification tasks.
Classical robot-programming approaches often require the definition of rigid sequences of elementary motions and actions by expert robot programmers through coding. Such solutions are suitable for environments that ar...
详细信息
ISBN:
(纸本)9798350373981;9798350373974
Classical robot-programming approaches often require the definition of rigid sequences of elementary motions and actions by expert robot programmers through coding. Such solutions are suitable for environments that are more structured and less dynamic with respect to construction ones. We propose a different approach with a novel software architecture that exploits Building Information Modelling (BIM) data for facilitating robot-programming and deployment in construction. It includes mission parametrization and customization tools that abstract elementary robot functionality in terms of behaviors, that can be easily understood, assembled, and adapted on-site by non-expert programmers. We verify the effectiveness of our proposed approach by considering the execution of a spray-painting use-case for interior walls and a usability study.
this paper focuses on the state estimation of a specific class of state-intermittent dynamical systems evolving in a high-dimensional state-space. As the dimension is large, a classical estimator such as a Kalman filt...
详细信息
ISBN:
(纸本)9798350373981;9798350373974
this paper focuses on the state estimation of a specific class of state-intermittent dynamical systems evolving in a high-dimensional state-space. As the dimension is large, a classical estimator such as a Kalman filter would require a large observation horizon to converge. To overcome this limitation, a mixed-integer formulation is proposed and solved by using a genetic Algorithm. We also propose a reduced-order state estimation as a variant of this approach under some mild assumptions, which reduces the observation window size even more. In particular, we show, through a case study in finance, that the reduced model and its associated genetic algorithm can reduce the observation window size needed by almost 75% and that this method is faster than the non-reduced mixed integer optimization problem. We also show that the reduced-order state estimation approach can be used to discover a mutual fund portfolio composition at each date of a given period.
In current machine learning research, deep learning methodologies have become the prevalent approach across various domains, including decision-making processes. However, the interpretability of solutions generated by...
详细信息
ISBN:
(纸本)9783031611391;9783031611407
In current machine learning research, deep learning methodologies have become the prevalent approach across various domains, including decision-making processes. However, the interpretability of solutions generated by these algorithms remains a significant challenge, as these models do not inherently prioritize explainability. this lack of interpretability hampers the analysis of decision-making rationales. One potential remedy to this issue is the employment of genetic Network programming (GNP), a method within the evolutionary computing paradigm, known for its ability to generate more interpretable solutions. this study provides a concise overview of GNP, exploring its modifications and applications to demonstrate its utility in addressing the interpretability challenge in machine learning algorithms.
the addressed problem considers a market model where a firm produces and sells a single product over a finite horizon divided into different periods. the firm aims to set the price of each period such that the total p...
详细信息
ISBN:
(纸本)9798350373981;9798350373974
the addressed problem considers a market model where a firm produces and sells a single product over a finite horizon divided into different periods. the firm aims to set the price of each period such that the total profit is maximized, while also satisfying constraints on available production capacity and price bounds. the market demand for each period is represented by the multinomial logit (MNL) model. this problem has been previously tackled in the literature, where it was formulated as a non-convex nonlinear programming (NLP) model. the solution approach involved the integration of neural networks and evolutionary algorithms. In this paper, the initial non-convex (NLP) model is transformed into a convex one based on properties of the MNL model. this new formulation enables the resolution of the addressed problem in an optimal way. A large experimental study is carried out to evaluate the solution quality and computational times of the two models. the obtained results show the effectiveness of the convex formulation compared to the non-convex one.
Recently, soft robotic procedures are being developed aiming at achieving targeted minimally invasive operations or drug administration in specific locations in the human body. Accordingly, specialized path-planning a...
详细信息
ISBN:
(纸本)9798350386523;9798350386530
Recently, soft robotic procedures are being developed aiming at achieving targeted minimally invasive operations or drug administration in specific locations in the human body. Accordingly, specialized path-planning algorithms need to be investigated for the estimation of efficient paths that would protect the delicate tissue structures and simultaneously satisfy a set of requirements for the efficient navigation of the robot. In this context, we propose an image-based 3D path-planning algorithm, which is an extension of the A* algorithm, for the navigation of a soft-growing robot inside the spinal subarachnoid space (SSS). the proposed algorithm is capable of estimating a safe pathway towards the goal location, while ensuring the establishment of anchor points that facilitate the efficient steering of the soft robot. the algorithm is evaluated using a highly detailed model of the SSS with respect to its capacity to satisfy the robot movement requirements and path efficiency.
Network and information security have become difficult problems as a result of the network's phenomenal expansion. the main aim of intrusion detection is to detect and prevent security flaws in information systems...
详细信息
Flexible job shop scheduling problem with energy and makespan minimization objectives, and uncertain processing times that are modeled with intervals is addressed in this work. the problem is solved by a genetic algor...
详细信息
ISBN:
(纸本)9783031611360;9783031611377
Flexible job shop scheduling problem with energy and makespan minimization objectives, and uncertain processing times that are modeled with intervals is addressed in this work. the problem is solved by a genetic algorithm using a lexicographic goal programming approach and the results evaluated with respect to the lower and upper bounds that come from various sources and methods.
Nowadays, the word knows an increase in energy demand and a scarcity in energy sources. Renewable energy sources are promising alternatives in the actual conditions. Particularly, several efforts are spent in system s...
详细信息
ISBN:
(纸本)9781665465076
Nowadays, the word knows an increase in energy demand and a scarcity in energy sources. Renewable energy sources are promising alternatives in the actual conditions. Particularly, several efforts are spent in system sizing and energy management strategies' development to make application as much profitable as possible in terms of autonomy and benefits. genetic algorithm is widely used in these fields and demonstrated high performances in optimization processes. On the other hand, linear programming algorithm is known by its simplicity and its high performances in energy management strategies optimization. In this paper, we propose a combined model composed by genetic algorithm and linear programming method to optimize boththe sizing of the installation and the energy management strategy optimization.
this paper introduces SeeQ, a programming model and an abstraction framework that facilitates the development of portable datadriven building applications. Data-driven approaches can provide insights into building ope...
详细信息
ISBN:
(纸本)9798400702303
this paper introduces SeeQ, a programming model and an abstraction framework that facilitates the development of portable datadriven building applications. Data-driven approaches can provide insights into building operations and guide decision-making to achieve operational objectives. Yet the configuration of such applications per building requires extensive effort and tacit knowledge. In SeeQ, we propose a portable programming model and build a software system that enables self-configuration and execution across diverse buildings. the configuration of each building is captured in a unified data model - in this paper, we work withthe Brick ontology without loss of generality. SeeQ focuses on the distinction between the application logic and the configuration of an application against building-specific data inputs and systems. We test the proposed approach by configuring and deploying a diverse range of applications across five heterogeneous real-world buildings. the analysis shows the potential of SeeQ to significantly reduce the efforts associated withthe delivery of building analytics.
暂无评论