Large-scale tabular data classification is a critical task and the complexity arises from the vast amount of structured data generated in these fields, coupled withthe challenges of high dimensionality and limited sa...
Large-scale tabular data classification is a critical task and the complexity arises from the vast amount of structured data generated in these fields, coupled withthe challenges of high dimensionality and limited sample sizes. To address these challenges, advanced machine learning algorithms are required to analyze and categorize instances within these datasets effectively. In this work, we propose the usage of a state-of-the-art classifier called XBNet, which combines the strengths of tree-based classifiers and neural networks to tackle large tabular datasets. Our methodology is validated on a dataset with 64 dimensions and 11 classes, showcasing the model's capability to detect patterns and extract relevant features automatically. Furthermore, we employ K-Fold cross-validation to assess the model's performance, achieving an impressive training accuracy of 61.9% and a validation accuracy of 31.7%. these results surpass those of competing algorithms, confirming the superiority of our proposed methodology in handling large-scale tabular data classification tasks.
the transition to agile manufacturing, Industry 4.0, and high-mix-low-volume tasks require robot programming solutions that are flexible. However, most deployed robot solutions are still statically programmed and use ...
the transition to agile manufacturing, Industry 4.0, and high-mix-low-volume tasks require robot programming solutions that are flexible. However, most deployed robot solutions are still statically programmed and use stiff position control, which limit their usefulness. In this paper, we show how a single robot skill that utilizes knowledge representation, task planning, and automatic selection of skill implementations based on the input parameters can be executed in different contexts. We demonstrate how the skill-based control platform enables this with contact-rich wiping tasks on different robot systems. To achieve that in this case study, our approach needs to address different kinematics, gripper types, vendors, and fundamentally different control interfaces. We conducted the experiments with a mobile platform that has a Universal Robots UR5e 6 degree-of-freedom robot arm with position control and a 7 degree-of-freedom KUKA iiwa with torque control.
Hydrogen offers excellent potential for cross-sector decarbonization through power-to-gas technologies necessary for climate policy. However, studies show that the planned expansion of electrolysis technologies accord...
Hydrogen offers excellent potential for cross-sector decarbonization through power-to-gas technologies necessary for climate policy. However, studies show that the planned expansion of electrolysis technologies according to current future scenarios will not produce sufficient quantities of hydrogen. One way to address this challenge is to optimize electrolysis technologies, which would increase efficiency and, at the same time, increase hydrogen yield. this approach raises the question of the limit of optimizability. this paper presents and discusses a model to represent an idealized reference process for water electrolysis. the reference model has the potential of identifying the optimum based on applicable laws of nature and the current state of the art, which can be used as a basis for the process design of an electrolysis cell. Furthermore, it allows the real-time evaluation of the operation of an electrolysis cell and, thus, the investigation of degradation effects.
In this paper, we consider the problem of assigning users to switches and controllers at minimum connectivity costs. We simultaneously minimize the existing latency between controllers and switch controllers for softw...
详细信息
Withthe continuous increase of the penetration rate of distributed generation (DG) in the distribution network, higher requirements have been put forward for the dependable and cost-effective operation of the distrib...
Withthe continuous increase of the penetration rate of distributed generation (DG) in the distribution network, higher requirements have been put forward for the dependable and cost-effective operation of the distribution network. In order to address the impact caused by the intermittent output of a large number of DGs on the distribution network, this article proposes a planning method for soft open point (SOP) using generative adversarial network (GAN). First, to accurately simulate the operating characteristics of DG, a GAN is employed for sce-nario generation. then, operational constraints for distribution networks with SOP are proposed, withthe objective function being the minimization of annual total cost. By relaxing and linearizing the original non-convex and non-linear constraints, a second-order cone programming model is derived, and the objective function is solved under the constraints. Finally, the proposed scenario generation algorithm and planning model are analyzed and veriffed on the IEEE 33- node test system.
Wireless Sensor Networks (WSNs) are made up of sensor nodes with a finite supply of energy that cooperate to accomplish a common goal. WSNs are widely used to carry out a variety of monitoring duties in challenging en...
Wireless Sensor Networks (WSNs) are made up of sensor nodes with a finite supply of energy that cooperate to accomplish a common goal. WSNs are widely used to carry out a variety of monitoring duties in challenging environments that are difficult to reach and even dangerous. the distributed nature of WSNs makes them vulnerable to a wide range of physical attacks, including eavesdropping, Sybil attacks, node replication attacks, signal or radio jamming, denial of service (DoS) attacks, flooding attacks, node outages, and DoS attacks. In order to stop communicating between source and destination, the flooding outbreak attacks the network with unwarranted bogus route requests. the goal of a data flooding attack is to obstruct the communication between source and destination by flooding the network with an overwhelming amount of useless data packets. Using the networks simulator NS 2.33, this research study has assessed and compared the suggested technique FDMM with native AODV and current state-of-the-art protocols. On an average, the proposed algorithm shows 1.34% and 0.18% increase in PDF, 6.03% and 5.47% increase in throughput, 1.93% and 0.54% increase in average residual energy, 3.30% and 4.09% decrease in end to end delay when compared with state-of-the-art algorithms.
E-mobility, or electric mobility, has emerged as a pivotal solution to address pressing environmental and sustainability concerns in the transportation sector. the depletion of fossil fuels, escalating greenhouse gas ...
E-mobility, or electric mobility, has emerged as a pivotal solution to address pressing environmental and sustainability concerns in the transportation sector. the depletion of fossil fuels, escalating greenhouse gas emissions, and the imperative to combat climate change underscore the significance of transitioning to electric vehicles (EVs). this paper seeks to explore the potential of artificial intelligence (AI) in addressing various challenges related to effective energy management in e-mobility systems (EMS). these challenges encompass critical factors such as range anxiety, charge rate optimization, and the longevity of energy storage in EVs. By analyzing existing literature, we delve into the role that AI can play in tackling these challenges and enabling efficient energy management in EMS. Our objectives are twofold: to provide an overview of the current state-of-the-art in this research domain and propose effective avenues for future investigations. through this analysis, we aim to contribute to the advancement of sustainable and efficient e-mobility solutions, shaping a greener and more sustainable future for transportation.
Function-as-a-Service (FaaS) has been the primary component to drive the movement toward serverless computing. these lightweight and scalable components, though attractive, are non-trivial to accommodate the needs of ...
Function-as-a-Service (FaaS) has been the primary component to drive the movement toward serverless computing. these lightweight and scalable components, though attractive, are non-trivial to accommodate the needs of long-running stateful applications. In this paper, we highlight the drawbacks of existing stateful FaaS proposals, in turn motivating the need to rethink the stateful serverless model for building general-purpose applications, while maintaining its benefits such as auto-scaling and pay-per-use cost model. We present a novel serverless model based on the object-oriented (OO) programming paradigm, with Object-as-a-Service (OaaS), acting as the only component of the serverless design. through our experimental evaluations, we demonstrate that the proposed architecture, named SCOOP, can improve the end-to-end latency of applications by 52% and 58%, compared to the state-of-the-art stateless and stateful FaaS implementations, respectively, while reducing the SLO violations by up to 14% by scaling resources based on the traffic fluctuations in the WITS and Berkeley traces.
Analytics that define the most valuable and possible automation are referred to as augmented analytics. Analytics is the name given to the scientific method of identifying and communicating critical patterns in data. ...
Analytics that define the most valuable and possible automation are referred to as augmented analytics. Analytics is the name given to the scientific method of identifying and communicating critical patterns in data. To improve decision-making, gain understanding, prepare data, and exchange data, augmented analytics focused on turning raw data into information. Measurement and insights of data are obtained through augmented analytics. It employs operations research, computer programming, and statistics. It is functional in places with an enormous amount of information. When it comes to analytics and decision-making, augmented analytics can be supplemented and eventually fully automated. Augmented analytics is the most recent method for considering data and analytics. artificial intelligence (AI) and analytics are combined. It involves combining artificial intelligence (AI) with conventional analytics, the most popular machine learning (ML), and natural language processing (NLP). It differs from typical analytics or business intelligence (BI) tools in that ML technology is constantly learning and improving outcomes behind the scenes. Augmented analytics, in particular, allows for faster access to insights gained from vast volumes of structured and unstructured data to provide ML-based recommendations. this intelligence contributes to discovering hidden patterns and deviations in data, as well as the removal of human bias and the development of forecasting capabilities that can help an organization decide the future course of action.
暂无评论