One of the main challenges in cloud computing is resource management, the ability to schedule workloads and services over the infrastructure in the most automated way. By optimizing cloud assignment and resource usage...
详细信息
ISBN:
(纸本)9783031779404;9783031779411
One of the main challenges in cloud computing is resource management, the ability to schedule workloads and services over the infrastructure in the most automated way. By optimizing cloud assignment and resource usage, energy can be saved, production incident can be anticipated and services QoS improved. With the recent years emergence of light virtualisation, known as containerization, the resource allocation problem was brought back, notably to support containers elasticity, hence the dynamic allocation of ressource at runtime at a single service scale. In this paper we show that using an hybrid loop system, which combines unsupervised learning and optimization techniques, our algorithm provides and iteratively improves scheduling solutions to containers resource assignment, enabling capacity planning over dynamic resource loads. Within our benchmarks, these solutions outperform state of the art algorithms, by an average of 6.3%, while providing more expressivity and control over input parameters. We describe also the implementation of this method, through an open source Python library called HOTS, which allows hybrid optimization for time series based use cases.
The growing use of machine learning algorithms in decisions that significantly affect people necessitate interpretable and fair approaches. Mathematical programming based machine learning models have attracted attenti...
详细信息
ISBN:
(纸本)9783031779404;9783031779411
The growing use of machine learning algorithms in decisions that significantly affect people necessitate interpretable and fair approaches. Mathematical programming based machine learning models have attracted attention because of the flexibility they provide to integrate features like interpretability and fairness, combined with high accuracy. This work introduces a mathematical programming based classification tree that uses a game theoretic approach to address group fairness. The proposed mathematical formulation is a Mixed Integer Linear Programming model using a piecewise linearisation strategy based on special-ordered sets. The overall misclassification rate is the fairness metric examined and the Nash bargaining scheme is followed to balance the trade off between the misclassification error of the groups. The efficiency of the methodology is evaluated via three binary and multi-class literature datasets, which provide evidence for the fairness and accuracy of the predictions made by the model.
In this work, a novel method for selecting the optimal set of input features for classifying the presence of congestive heart failure (CHF) using a supervised machine learning approach is presented. A random forest cl...
详细信息
ISBN:
(纸本)9783031791024;9783031791031
In this work, a novel method for selecting the optimal set of input features for classifying the presence of congestive heart failure (CHF) using a supervised machine learning approach is presented. A random forest classifier (RFC) was utilized to carry out the binary classification task and two different models were explored. We employed the embedded RFC feature importance attribute for the first model, and a multi-classifier technique which integrates the feature weight importance correlation (F-WIC) method was adopted for the second model. Our results show that the second model using the F-WIC method offers superior performance (100% accuracy) and provides a generalized approach to feature engineering for machine learning models irrespective of the algorithm used. This work offers a novel method for selecting the optimal set of input features for classifying the presence of congestive heart failure (CHF) using a machine learning approach.
This study investigates the environmental impact of cherry production of the "Agios Loukas" Agricultural Cooperative of Rachis Pieria. For the quantification of the impact, the Life Cycle Assessment (LCA) me...
详细信息
ISBN:
(纸本)9783031693502;9783031693519
This study investigates the environmental impact of cherry production of the "Agios Loukas" Agricultural Cooperative of Rachis Pieria. For the quantification of the impact, the Life Cycle Assessment (LCA) methodology is used. The key objective of the work is to comprehensively document all stages of cherry production and associated processes in order to assess different environmental impacts' indicators. In brief, LCA assesses how the entire life cycle of a product influences the environment. The impact quantification employs the LCArt Simulations Engine, a web application developed under the KYKLOS 4.0 project, funded by the EU Horizon 2020 Programme. The methodology follows ReCipe 2016 v1.03 midpoint (H). Data for the year 2022 were sourced, with actual field data provided by cooperative executives and management. Data collection involved interviews with both the cooperative's scientific staff and its members.
This study aims to explore the integration of Augmented Reality (AR) and olfactory technology to enhance dining experience in restaurants. We present ARoma, an innovative AR olfactory menu application for Indian cuisi...
详细信息
ISBN:
(数字)9783031808326
ISBN:
(纸本)9783031808319;9783031808326
This study aims to explore the integration of Augmented Reality (AR) and olfactory technology to enhance dining experience in restaurants. We present ARoma, an innovative AR olfactory menu application for Indian cuisine which provides users with 3D visualisation of dishes, detailed ingredient and nutritional information, and historical context, as well as an olfaction device to deliver the aroma of the dishes. Our research compares the traditional menu experience with the AR menu and ARoma, aiming to understand how these technologies affect customers' perceptions of food quality, dining enjoyment, and immersion. Our user study involved a sample size of 30 participants, divided into two groups. Group A compared traditional menu experiences with AR menus, while Group B experienced traditional menus followed by ARoma. Using this control group study and mixed-method approach, including quantitative surveys and qualitative interviews, we found that AR menus significantly enhance the dining experience by providing detailed and engaging information. Our findings suggest that AR and olfactory technology can significantly improve customer satisfaction and engagement in the food industry.
In this paper, we present a method that integrates Bayesian network and generalized possibilistic model checking to improve the accuracy of initial diagnostics and quantify uncertainties in the rehabilitation process....
详细信息
ISBN:
(纸本)9789819614899;9789819614905
In this paper, we present a method that integrates Bayesian network and generalized possibilistic model checking to improve the accuracy of initial diagnostics and quantify uncertainties in the rehabilitation process. Bayesian network provides probabilistic decision support using data-driven statistical information from various sources. Computational tree logic, combined with generalized possibility measures, effectively manages the uncertainties associated with patient rehabilitation.
The Covid-19 pandemic has not only taught us about viral infections, but also provided employers with unique opportunities to experiment with different work modes. What leads employees to be more satisfied: working on...
详细信息
ISBN:
(纸本)9783031714115;9783031714122
The Covid-19 pandemic has not only taught us about viral infections, but also provided employers with unique opportunities to experiment with different work modes. What leads employees to be more satisfied: working onsite or working from home? The aim of this paper is to elucidate how the work environment impacts workplace satisfaction. In the framework of Herzberg's motivation theory, we define the physical, digital, and social environment as the most important hygiene factors. In our study, we investigate the relationship between these hygiene factors and workplace satisfaction. Based on the survey data from office workers in Switzerland, we identify the predictors of workplace satisfaction for working onsite and working from home respectively. Our statistical analysis shows that the three hygiene factors have a significant positive impact on workplace satisfaction both for working onsite and working from home. Specifically, the workplace design in the context of the physical environment stands out to have the strongest effect on the workplace satisfaction for onsite work. In contrast, for working from home, the software availability in the context of the digital environment exerts the greatest influence on workplace satisfaction. Thus, workplace satisfaction can be maximized by targeted optimization of specific aspects of the work environment depending on the work mode.
This study proposed a personalized recommender system based on LLM and explored how to better capture and utilize user preferences to increase recommendation accuracy and explainability. Traditional recommender method...
详细信息
ISBN:
(纸本)9789819616138;9789819616145
This study proposed a personalized recommender system based on LLM and explored how to better capture and utilize user preferences to increase recommendation accuracy and explainability. Traditional recommender methods, such as collaborative filtering, content-based, and hybrid approaches, often overlook the relationships between user preference attributes. This study leverages LLM, considers the relationships between user preference attributes, and combines it with a self-attention mechanism to achieve fine-grained scoring of user preferences. The system delved into user preferences through dialog, adjusting the recommendation content in each turn of the dialog. The experimental results demonstrated significant improvements in both the recommendation accuracy and the quality of the generated dialog content. Specifically, on the ReDial dataset, Recall@10 improved by 2.9%, and the informativeness increased by 3%. The study also emphasized the importance of attribute sorting order, further enhancing the system's explainability.
The highly heterogeneous workloads generated by current scientific and technological research complicate job scheduling in supercomputers, making commercial scheduling tools challenging to be configured effectively. R...
详细信息
ISBN:
(纸本)9783031800832;9783031800849
The highly heterogeneous workloads generated by current scientific and technological research complicate job scheduling in supercomputers, making commercial scheduling tools challenging to be configured effectively. Recent studies have analysed these workloads, but the impact of job scheduling policy changes on both job input and system output variables remains largely unexplored. This paper aims at a methodology for characterising both users' and system's behaviour in response to policy changes. As a case study, we use the Santos Dumont supercomputer at the National Laboratory for Scientific Computing (LNCC) in Brazil;we examine its job accounting records over two years, with a policy change in between them targeting a reduction in waiting times. Key findings of our study include differential impacts of the policy change on jobs with varying waiting times and the utility of grouping users to interpret eventual behavioral changes due to the policy change.
In this paper, the parameters involved in the chloride ions diffusion for concrete structures have been analysed. Usually, several factors for diffusivity and surface chloride concentration are introduced to consider ...
详细信息
ISBN:
(纸本)9783031734199;9783031734205
In this paper, the parameters involved in the chloride ions diffusion for concrete structures have been analysed. Usually, several factors for diffusivity and surface chloride concentration are introduced to consider all internal and external actions that contribute to the diffusion. However, the inter-correlations between them are neglected. This paper treats these inter-correlations. From experimental laboratory tests about 850 parameters and values have been filtered and collected. These values have been divided in 11 categories and combined with each other. More of 120 numerical analyses by using k-means algorithm have been carried out. This algorithm is considered an artificial intelligence (AI) to support the human limitations in managing and analysing an enormous quantity of parameter. Results provide disaggregated values where each parameter is correlated with other one. This allows to understand their weight and effects on chloride ions diffusion. This paper provides not only a new approach but also practical values for more accurate analyses.
暂无评论